{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [], "collapsed_sections": [ "tF42HvI7-gs5" ], "gpuType": "T4" }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" }, "accelerator": "GPU", "widgets": { "application/vnd.jupyter.widget-state+json": { "22b65f742f6f45a3ab528282d65986f7": { "model_module": "@jupyter-widgets/controls", "model_name": "VBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "VBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "VBoxView", "box_style": "", "children": [], "layout": "IPY_MODEL_4cfaa0dfe03d4bdda729589e726f9cfb" } }, "7d6994a82ca64dbeb50f4da1da4f91d5": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_201aaad9b1584ee9ab88ce4981e7bba5", "placeholder": "​", "style": "IPY_MODEL_728faf318a614500b86307f8040feb72", "value": "

Copy a token from your Hugging Face\ntokens page and paste it below.
Immediately click login after copying\nyour token or it might be stored in plain text in this notebook file.
" } }, "4b44bef636d04083bd1e74ec8a37abcf": { "model_module": "@jupyter-widgets/controls", "model_name": "PasswordModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "PasswordModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "PasswordView", "continuous_update": true, "description": "Token:", "description_tooltip": null, "disabled": false, "layout": "IPY_MODEL_35b068cc0fd048fcb1fb5366086d1ac8", "placeholder": "​", "style": "IPY_MODEL_4403d9ed2124488d87b99c40e8d15ea0", "value": "" } }, "988419020b2c488ca01de9c855e3b871": { "model_module": "@jupyter-widgets/controls", "model_name": "CheckboxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "CheckboxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "CheckboxView", "description": "Add token as git credential?", "description_tooltip": null, "disabled": false, "indent": true, "layout": "IPY_MODEL_63cfd7ef19cf47228ba195bf102d0bb3", "style": "IPY_MODEL_8c8a0d6c29b0419d884f33d7291dad03", "value": true } }, "f74fcf731f004609b3030a645ce55e40": { "model_module": "@jupyter-widgets/controls", "model_name": "ButtonModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ButtonModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ButtonView", "button_style": "", "description": "Login", "disabled": false, "icon": "", "layout": "IPY_MODEL_6175e78506e248adb108e2014565ef26", "style": "IPY_MODEL_9a3933af0ae34b07a3646f03a0cb16b6", "tooltip": "" } }, "31ade0b42e624c50a698df43c705306b": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_a4deebba544347dc8da3bc880d1c69e8", "placeholder": "​", "style": "IPY_MODEL_4d5e7e271d7c4083a9c84d04a5e14d7e", "value": "\nPro Tip: If you don't already have one, you can create a dedicated\n'notebooks' token with 'write' access, that you can then easily reuse for all\nnotebooks. " } }, "4cfaa0dfe03d4bdda729589e726f9cfb": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": "center", "align_self": null, "border": null, "bottom": null, "display": "flex", "flex": null, "flex_flow": "column", "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": "50%" } }, "201aaad9b1584ee9ab88ce4981e7bba5": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "728faf318a614500b86307f8040feb72": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "35b068cc0fd048fcb1fb5366086d1ac8": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "4403d9ed2124488d87b99c40e8d15ea0": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "63cfd7ef19cf47228ba195bf102d0bb3": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "8c8a0d6c29b0419d884f33d7291dad03": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "6175e78506e248adb108e2014565ef26": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "9a3933af0ae34b07a3646f03a0cb16b6": { "model_module": "@jupyter-widgets/controls", "model_name": "ButtonStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ButtonStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "button_color": null, "font_weight": "" } }, "a4deebba544347dc8da3bc880d1c69e8": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "4d5e7e271d7c4083a9c84d04a5e14d7e": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "6f78103f996d4dcf81bfba72af2bfb86": { "model_module": "@jupyter-widgets/controls", "model_name": "LabelModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "LabelModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "LabelView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_22d2466c15084c39a6a9af8dac759916", "placeholder": "​", "style": "IPY_MODEL_3c9f1a666be240c3a68bd7d04b22ec34", "value": "Connecting..." } }, "22d2466c15084c39a6a9af8dac759916": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "3c9f1a666be240c3a68bd7d04b22ec34": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "2d18d874546f42999766fbf7ca2101e9": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_91b34f4df2f344cd8e29cac067b7bc3b", "IPY_MODEL_f5da8ef4870e4c40914fb8033078c56e", "IPY_MODEL_aef821b334c445b1bbc0738b31570a65" ], "layout": "IPY_MODEL_d942f422513f4712bb58869859b670e0" } }, "91b34f4df2f344cd8e29cac067b7bc3b": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_981b9447a2fb4a2b89574e8e7f25da86", "placeholder": "​", "style": "IPY_MODEL_00ef4e1c80c2428a8d0b1095f39cf1a4", "value": "policy.pth: 100%" } }, "f5da8ef4870e4c40914fb8033078c56e": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_3e9b5f8659b042719097efdaa4aeb523", "max": 46447, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_38049ce9bae04de19e01cb8627f95e2d", "value": 46447 } }, "aef821b334c445b1bbc0738b31570a65": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_036ba3379c1e495883d63ec12f931fa2", "placeholder": "​", "style": "IPY_MODEL_91e4ba8a93c74f1f82867c9769df2dfd", "value": " 46.4k/46.4k [00:00<00:00, 178kB/s]" } }, "d942f422513f4712bb58869859b670e0": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "981b9447a2fb4a2b89574e8e7f25da86": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "00ef4e1c80c2428a8d0b1095f39cf1a4": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "3e9b5f8659b042719097efdaa4aeb523": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "38049ce9bae04de19e01cb8627f95e2d": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "036ba3379c1e495883d63ec12f931fa2": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "91e4ba8a93c74f1f82867c9769df2dfd": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "e714b6f2478d48b4834e16250f7bebe4": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_436631cb9eb3435eb3753b7562dd5296", "IPY_MODEL_c25a97c4fc6d4d53aaf7f859dc72fd8d", "IPY_MODEL_ba938dd829434c23b4ce1a2811477cdb" ], "layout": "IPY_MODEL_2d62bb81f0b747d5accd5b0d7379e2c1" } }, "436631cb9eb3435eb3753b7562dd5296": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_20be170568d142a980a8f9a918f8188d", "placeholder": "​", "style": "IPY_MODEL_b8ce34bb2a02407fbd57eb13c28b7a40", "value": "policy.optimizer.pth: 100%" } }, "c25a97c4fc6d4d53aaf7f859dc72fd8d": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_bb177a07e9ab4740a8e417a739b9aae3", "max": 48456, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_0ea4719cff3b4d438fca90ae32e0c787", "value": 48456 } }, "ba938dd829434c23b4ce1a2811477cdb": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_042b476836f9460ea5e6f2792f66bc5b", "placeholder": "​", "style": "IPY_MODEL_af27930627644adab08f45a3f58a7ef1", "value": " 48.5k/48.5k [00:00<00:00, 163kB/s]" } }, "2d62bb81f0b747d5accd5b0d7379e2c1": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "20be170568d142a980a8f9a918f8188d": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "b8ce34bb2a02407fbd57eb13c28b7a40": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "bb177a07e9ab4740a8e417a739b9aae3": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "0ea4719cff3b4d438fca90ae32e0c787": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "042b476836f9460ea5e6f2792f66bc5b": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "af27930627644adab08f45a3f58a7ef1": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "422b4e3ffc8d43f59fba9c96d53b2a6b": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_b117b01dd51a4ae08ae68b91ea8cd884", "IPY_MODEL_a965ed2d1a1e4433871b9de1e75ec696", "IPY_MODEL_27d3bad0a78341ce88e86ceee0907aee" ], "layout": "IPY_MODEL_dd9f5b2777534ff898a591341b4be0a8" } }, "b117b01dd51a4ae08ae68b91ea8cd884": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_ce156a52ab5e41b79e9be9b9b75b766d", "placeholder": "​", "style": "IPY_MODEL_968176d368974252b45f525d96affa43", "value": "vec_normalize.pkl: 100%" } }, "a965ed2d1a1e4433871b9de1e75ec696": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_8dc27ba1aacd4a0491bb5a6b735580fc", "max": 2644, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_4306fcb4052b4ea49326e0d614dba25f", "value": 2644 } }, "27d3bad0a78341ce88e86ceee0907aee": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_bb3d4ed9054c495488a4c3c5bfb5e5e1", "placeholder": "​", "style": "IPY_MODEL_8d175b53a4044e7192f7320a8eb67ab5", "value": " 2.64k/2.64k [00:00<00:00, 14.0kB/s]" } }, "dd9f5b2777534ff898a591341b4be0a8": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "ce156a52ab5e41b79e9be9b9b75b766d": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "968176d368974252b45f525d96affa43": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "8dc27ba1aacd4a0491bb5a6b735580fc": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "4306fcb4052b4ea49326e0d614dba25f": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "bb3d4ed9054c495488a4c3c5bfb5e5e1": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "8d175b53a4044e7192f7320a8eb67ab5": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "f42f221a73b84bd5a5a6fd5557e7ab7e": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_287cf07517054b808b23933313219dc6", "IPY_MODEL_b7c365a3fbdd4569beceb9d380e3c91c", "IPY_MODEL_f0d4af81631f4291a6fa160db5dfe48a" ], "layout": "IPY_MODEL_d113b614cfc8454f8dda34250e912a50" } }, "287cf07517054b808b23933313219dc6": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_866e25e934914532b8c70e6a368dd71a", "placeholder": "​", "style": "IPY_MODEL_307bf04fcb8641cda868cc9b65d34bdd", "value": "pytorch_variables.pth: 100%" } }, "b7c365a3fbdd4569beceb9d380e3c91c": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_2e6214c0ab9740149780812e2c501abc", "max": 864, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_59a8ea4f53e541f5a8ddcbef971f0a90", "value": 864 } }, "f0d4af81631f4291a6fa160db5dfe48a": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_74b60527ee234f50ac706c8fd23a5b79", "placeholder": "​", "style": "IPY_MODEL_254cf5e2e0054f909c603a0f63a41b9b", "value": " 864/864 [00:00<00:00, 3.85kB/s]" } }, "d113b614cfc8454f8dda34250e912a50": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "866e25e934914532b8c70e6a368dd71a": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "307bf04fcb8641cda868cc9b65d34bdd": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "2e6214c0ab9740149780812e2c501abc": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "59a8ea4f53e541f5a8ddcbef971f0a90": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "74b60527ee234f50ac706c8fd23a5b79": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "254cf5e2e0054f909c603a0f63a41b9b": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "c1082e8387ea43908a9d8efec52088d5": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_29b79eba42344ae9bcfdb05de2f09d2b", "IPY_MODEL_25de51183e1140219a7ee5bb20b89656", "IPY_MODEL_e16b708d2f5849809a5a05e0ec943358" ], "layout": "IPY_MODEL_3d6a5d5929f94a54b5787ba73cc3adfb" } }, "29b79eba42344ae9bcfdb05de2f09d2b": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_8a0800f893204ed58c43dec909010bf7", "placeholder": "​", "style": "IPY_MODEL_eb62829f84fe4395a704d11d1e127005", "value": "a2c-PandaReachDense-v3.zip: 100%" } }, "25de51183e1140219a7ee5bb20b89656": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_3ddb0e63548041c4adb9e9755a3883b4", "max": 114068, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_d4ae74192aed44948bc35aec7596febc", "value": 114068 } }, "e16b708d2f5849809a5a05e0ec943358": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_223779006df241059ad6c36cbe66c196", "placeholder": "​", "style": "IPY_MODEL_c3b865a0b9d14d7c9ceb8b147b12f39e", "value": " 114k/114k [00:00<00:00, 915kB/s]" } }, "3d6a5d5929f94a54b5787ba73cc3adfb": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "8a0800f893204ed58c43dec909010bf7": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "eb62829f84fe4395a704d11d1e127005": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "3ddb0e63548041c4adb9e9755a3883b4": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "d4ae74192aed44948bc35aec7596febc": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "223779006df241059ad6c36cbe66c196": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "c3b865a0b9d14d7c9ceb8b147b12f39e": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "60623fde8bf44395ae0ce53112546fd5": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_614362841cb84af8909d411bc81a518c", "IPY_MODEL_cc8028a18fb244b6a38886a111614790", "IPY_MODEL_43a02385d512419393452db67311a424" ], "layout": "IPY_MODEL_dfcd36551bad4a50a8d75698088bcee8" } }, "614362841cb84af8909d411bc81a518c": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_6c8ddfca0954497b96e48bffd8baa99f", "placeholder": "​", "style": "IPY_MODEL_5348b168b52c40549aa1e15e216351c1", "value": "Upload 5 LFS files: 100%" } }, "cc8028a18fb244b6a38886a111614790": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_35080c3017b345bf865e123139053b8f", "max": 5, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_4724992ecab3406f8e1e73ea95b86159", "value": 5 } }, "43a02385d512419393452db67311a424": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_325f0b9e2a02459e8a48bce8b9cdcfb6", "placeholder": "​", "style": "IPY_MODEL_e1a268d789cd4a689e50b6a199a95be5", "value": " 5/5 [00:00<00:00,  8.54it/s]" } }, "dfcd36551bad4a50a8d75698088bcee8": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "6c8ddfca0954497b96e48bffd8baa99f": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "5348b168b52c40549aa1e15e216351c1": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "35080c3017b345bf865e123139053b8f": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "4724992ecab3406f8e1e73ea95b86159": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "325f0b9e2a02459e8a48bce8b9cdcfb6": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "e1a268d789cd4a689e50b6a199a95be5": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } } } } }, "cells": [ { "cell_type": "markdown", "source": [ "# Unit 6: Advantage Actor Critic (A2C) using Robotics Simulations with Panda-Gym 🤖\n", "\n", "\"Thumbnail\"/\n", "\n", "In this notebook, you'll learn to use A2C with [Panda-Gym](https://github.com/qgallouedec/panda-gym). You're going **to train a robotic arm** (Franka Emika Panda robot) to perform a task:\n", "\n", "- `Reach`: the robot must place its end-effector at a target position.\n", "\n", "After that, you'll be able **to train in other robotics tasks**.\n" ], "metadata": { "id": "-PTReiOw-RAN" } }, { "cell_type": "markdown", "source": [ "### 🎮 Environments:\n", "\n", "- [Panda-Gym](https://github.com/qgallouedec/panda-gym)\n", "\n", "###📚 RL-Library:\n", "\n", "- [Stable-Baselines3](https://stable-baselines3.readthedocs.io/)" ], "metadata": { "id": "QInFitfWno1Q" } }, { "cell_type": "markdown", "source": [ "We're constantly trying to improve our tutorials, so **if you find some issues in this notebook**, please [open an issue on the GitHub Repo](https://github.com/huggingface/deep-rl-class/issues)." ], "metadata": { "id": "2CcdX4g3oFlp" } }, { "cell_type": "markdown", "source": [ "## Objectives of this notebook 🏆\n", "\n", "At the end of the notebook, you will:\n", "\n", "- Be able to use **Panda-Gym**, the environment library.\n", "- Be able to **train robots using A2C**.\n", "- Understand why **we need to normalize the input**.\n", "- Be able to **push your trained agent and the code to the Hub** with a nice video replay and an evaluation score 🔥.\n", "\n", "\n" ], "metadata": { "id": "MoubJX20oKaQ" } }, { "cell_type": "markdown", "source": [ "## This notebook is from the Deep Reinforcement Learning Course\n", "\"Deep\n", "\n", "In this free course, you will:\n", "\n", "- 📖 Study Deep Reinforcement Learning in **theory and practice**.\n", "- 🧑‍💻 Learn to **use famous Deep RL libraries** such as Stable Baselines3, RL Baselines3 Zoo, CleanRL and Sample Factory 2.0.\n", "- 🤖 Train **agents in unique environments**\n", "\n", "And more check 📚 the syllabus 👉 https://simoninithomas.github.io/deep-rl-course\n", "\n", "Don’t forget to **sign up to the course** (we are collecting your email to be able to **send you the links when each Unit is published and give you information about the challenges and updates).**\n", "\n", "\n", "The best way to keep in touch is to join our discord server to exchange with the community and with us 👉🏻 https://discord.gg/ydHrjt3WP5" ], "metadata": { "id": "DoUNkTExoUED" } }, { "cell_type": "markdown", "source": [ "## Prerequisites 🏗️\n", "Before diving into the notebook, you need to:\n", "\n", "🔲 📚 Study [Actor-Critic methods by reading Unit 6](https://huggingface.co/deep-rl-course/unit6/introduction) 🤗 " ], "metadata": { "id": "BTuQAUAPoa5E" } }, { "cell_type": "markdown", "source": [ "# Let's train our first robots 🤖" ], "metadata": { "id": "iajHvVDWoo01" } }, { "cell_type": "markdown", "source": [ "To validate this hands-on for the [certification process](https://huggingface.co/deep-rl-course/en/unit0/introduction#certification-process), you need to push your trained model to the Hub and get the following results:\n", "\n", "- `PandaReachDense-v3` get a result of >= -3.5.\n", "\n", "To find your result, go to the [leaderboard](https://huggingface.co/spaces/huggingface-projects/Deep-Reinforcement-Learning-Leaderboard) and find your model, **the result = mean_reward - std of reward**\n", "\n", "For more information about the certification process, check this section 👉 https://huggingface.co/deep-rl-course/en/unit0/introduction#certification-process" ], "metadata": { "id": "zbOENTE2os_D" } }, { "cell_type": "markdown", "source": [ "## Set the GPU 💪\n", "- To **accelerate the agent's training, we'll use a GPU**. To do that, go to `Runtime > Change Runtime type`\n", "\n", "\"GPU" ], "metadata": { "id": "PU4FVzaoM6fC" } }, { "cell_type": "markdown", "source": [ "- `Hardware Accelerator > GPU`\n", "\n", "\"GPU" ], "metadata": { "id": "KV0NyFdQM9ZG" } }, { "cell_type": "markdown", "source": [ "## Create a virtual display 🔽\n", "\n", "During the notebook, we'll need to generate a replay video. To do so, with colab, **we need to have a virtual screen to be able to render the environment** (and thus record the frames).\n", "\n", "Hence the following cell will install the librairies and create and run a virtual screen 🖥" ], "metadata": { "id": "bTpYcVZVMzUI" } }, { "cell_type": "code", "execution_count": 1, "metadata": { "id": "jV6wjQ7Be7p5" }, "outputs": [], "source": [ "%%capture\n", "!apt install python-opengl\n", "!apt install ffmpeg\n", "!apt install xvfb\n", "!pip3 install pyvirtualdisplay" ] }, { "cell_type": "code", "source": [ "# Virtual display\n", "from pyvirtualdisplay import Display\n", "\n", "virtual_display = Display(visible=0, size=(1400, 900))\n", "virtual_display.start()" ], "metadata": { "id": "ww5PQH1gNLI4", "colab": { "base_uri": "https://localhost:8080/" }, "outputId": "68c8f7b6-8cf6-4f60-9c26-44a17a7cd2b0" }, "execution_count": 2, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "" ] }, "metadata": {}, "execution_count": 2 } ] }, { "cell_type": "markdown", "source": [ "### Install dependencies 🔽\n", "\n", "The first step is to install the dependencies, we’ll install multiple ones:\n", "- `gymnasium`\n", "- `panda-gym`: Contains the robotics arm environments.\n", "- `stable-baselines3`: The SB3 deep reinforcement learning library.\n", "- `huggingface_sb3`: Additional code for Stable-baselines3 to load and upload models from the Hugging Face 🤗 Hub.\n", "- `huggingface_hub`: Library allowing anyone to work with the Hub repositories.\n", "\n", "⏲ The installation can **take 10 minutes**." ], "metadata": { "id": "e1obkbdJ_KnG" } }, { "cell_type": "code", "source": [ "!pip install stable-baselines3[extra]\n", "!pip install gymnasium" ], "metadata": { "id": "TgZUkjKYSgvn", "colab": { "base_uri": "https://localhost:8080/" }, "outputId": "6b187667-ead4-48dd-bc4e-2e1c4fca159a" }, "execution_count": 3, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Collecting stable-baselines3[extra]\n", " Downloading stable_baselines3-2.6.0-py3-none-any.whl.metadata (4.8 kB)\n", "Requirement already satisfied: gymnasium<1.2.0,>=0.29.1 in /usr/local/lib/python3.11/dist-packages (from stable-baselines3[extra]) (1.1.1)\n", "Requirement already satisfied: numpy<3.0,>=1.20 in /usr/local/lib/python3.11/dist-packages (from stable-baselines3[extra]) (2.0.2)\n", "Requirement already satisfied: torch<3.0,>=2.3 in /usr/local/lib/python3.11/dist-packages (from stable-baselines3[extra]) (2.6.0+cu124)\n", "Requirement already satisfied: cloudpickle in /usr/local/lib/python3.11/dist-packages (from stable-baselines3[extra]) (3.1.1)\n", "Requirement already satisfied: pandas in /usr/local/lib/python3.11/dist-packages (from stable-baselines3[extra]) (2.2.2)\n", "Requirement already satisfied: matplotlib in /usr/local/lib/python3.11/dist-packages (from stable-baselines3[extra]) (3.10.0)\n", "Requirement already satisfied: opencv-python in /usr/local/lib/python3.11/dist-packages (from stable-baselines3[extra]) (4.11.0.86)\n", "Requirement already satisfied: pygame in /usr/local/lib/python3.11/dist-packages (from stable-baselines3[extra]) (2.6.1)\n", "Requirement already satisfied: tensorboard>=2.9.1 in /usr/local/lib/python3.11/dist-packages (from stable-baselines3[extra]) (2.18.0)\n", "Requirement already satisfied: psutil in /usr/local/lib/python3.11/dist-packages (from stable-baselines3[extra]) (5.9.5)\n", "Requirement already satisfied: tqdm in /usr/local/lib/python3.11/dist-packages (from stable-baselines3[extra]) (4.67.1)\n", "Requirement already satisfied: rich in /usr/local/lib/python3.11/dist-packages (from stable-baselines3[extra]) (13.9.4)\n", "Requirement already satisfied: ale-py>=0.9.0 in /usr/local/lib/python3.11/dist-packages (from stable-baselines3[extra]) (0.10.2)\n", "Requirement already satisfied: pillow in /usr/local/lib/python3.11/dist-packages (from stable-baselines3[extra]) (11.1.0)\n", "Requirement already satisfied: typing-extensions>=4.3.0 in /usr/local/lib/python3.11/dist-packages (from gymnasium<1.2.0,>=0.29.1->stable-baselines3[extra]) (4.13.2)\n", "Requirement already satisfied: farama-notifications>=0.0.1 in /usr/local/lib/python3.11/dist-packages (from gymnasium<1.2.0,>=0.29.1->stable-baselines3[extra]) (0.0.4)\n", "Requirement already satisfied: absl-py>=0.4 in /usr/local/lib/python3.11/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]) (1.4.0)\n", "Requirement already satisfied: grpcio>=1.48.2 in /usr/local/lib/python3.11/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]) (1.71.0)\n", "Requirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.11/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]) (3.8)\n", "Requirement already satisfied: packaging in /usr/local/lib/python3.11/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]) (24.2)\n", "Requirement already satisfied: protobuf!=4.24.0,>=3.19.6 in /usr/local/lib/python3.11/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]) (5.29.4)\n", "Requirement already satisfied: setuptools>=41.0.0 in /usr/local/lib/python3.11/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]) (75.2.0)\n", "Requirement already satisfied: six>1.9 in /usr/local/lib/python3.11/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]) (1.17.0)\n", "Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in /usr/local/lib/python3.11/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]) (0.7.2)\n", "Requirement already satisfied: werkzeug>=1.0.1 in /usr/local/lib/python3.11/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]) (3.1.3)\n", "Requirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from torch<3.0,>=2.3->stable-baselines3[extra]) (3.18.0)\n", "Requirement already satisfied: networkx in /usr/local/lib/python3.11/dist-packages (from torch<3.0,>=2.3->stable-baselines3[extra]) (3.4.2)\n", "Requirement already satisfied: jinja2 in /usr/local/lib/python3.11/dist-packages (from torch<3.0,>=2.3->stable-baselines3[extra]) (3.1.6)\n", "Requirement already satisfied: fsspec in /usr/local/lib/python3.11/dist-packages (from torch<3.0,>=2.3->stable-baselines3[extra]) (2025.3.2)\n", "Collecting nvidia-cuda-nvrtc-cu12==12.4.127 (from torch<3.0,>=2.3->stable-baselines3[extra])\n", " Downloading nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n", "Collecting nvidia-cuda-runtime-cu12==12.4.127 (from torch<3.0,>=2.3->stable-baselines3[extra])\n", " Downloading nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n", "Collecting nvidia-cuda-cupti-cu12==12.4.127 (from torch<3.0,>=2.3->stable-baselines3[extra])\n", " Downloading nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n", "Collecting nvidia-cudnn-cu12==9.1.0.70 (from torch<3.0,>=2.3->stable-baselines3[extra])\n", " Downloading nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n", "Collecting nvidia-cublas-cu12==12.4.5.8 (from torch<3.0,>=2.3->stable-baselines3[extra])\n", " Downloading nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n", "Collecting nvidia-cufft-cu12==11.2.1.3 (from torch<3.0,>=2.3->stable-baselines3[extra])\n", " Downloading nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n", "Collecting nvidia-curand-cu12==10.3.5.147 (from torch<3.0,>=2.3->stable-baselines3[extra])\n", " Downloading nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n", "Collecting nvidia-cusolver-cu12==11.6.1.9 (from torch<3.0,>=2.3->stable-baselines3[extra])\n", " Downloading nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n", "Collecting nvidia-cusparse-cu12==12.3.1.170 (from torch<3.0,>=2.3->stable-baselines3[extra])\n", " Downloading nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n", "Requirement already satisfied: nvidia-cusparselt-cu12==0.6.2 in /usr/local/lib/python3.11/dist-packages (from torch<3.0,>=2.3->stable-baselines3[extra]) (0.6.2)\n", "Requirement already satisfied: nvidia-nccl-cu12==2.21.5 in /usr/local/lib/python3.11/dist-packages (from torch<3.0,>=2.3->stable-baselines3[extra]) (2.21.5)\n", "Requirement already satisfied: nvidia-nvtx-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch<3.0,>=2.3->stable-baselines3[extra]) (12.4.127)\n", "Collecting nvidia-nvjitlink-cu12==12.4.127 (from torch<3.0,>=2.3->stable-baselines3[extra])\n", " Downloading nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n", "Requirement already satisfied: triton==3.2.0 in /usr/local/lib/python3.11/dist-packages (from torch<3.0,>=2.3->stable-baselines3[extra]) (3.2.0)\n", "Requirement already satisfied: sympy==1.13.1 in /usr/local/lib/python3.11/dist-packages (from torch<3.0,>=2.3->stable-baselines3[extra]) (1.13.1)\n", "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.11/dist-packages (from sympy==1.13.1->torch<3.0,>=2.3->stable-baselines3[extra]) (1.3.0)\n", "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib->stable-baselines3[extra]) (1.3.2)\n", "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.11/dist-packages (from matplotlib->stable-baselines3[extra]) (0.12.1)\n", "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.11/dist-packages (from matplotlib->stable-baselines3[extra]) (4.57.0)\n", "Requirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib->stable-baselines3[extra]) (1.4.8)\n", "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib->stable-baselines3[extra]) (3.2.3)\n", "Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.11/dist-packages (from matplotlib->stable-baselines3[extra]) (2.8.2)\n", "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.11/dist-packages (from pandas->stable-baselines3[extra]) (2025.2)\n", "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.11/dist-packages (from pandas->stable-baselines3[extra]) (2025.2)\n", "Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.11/dist-packages (from rich->stable-baselines3[extra]) (3.0.0)\n", "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.11/dist-packages (from rich->stable-baselines3[extra]) (2.18.0)\n", "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.11/dist-packages (from markdown-it-py>=2.2.0->rich->stable-baselines3[extra]) (0.1.2)\n", "Requirement already satisfied: MarkupSafe>=2.1.1 in /usr/local/lib/python3.11/dist-packages (from werkzeug>=1.0.1->tensorboard>=2.9.1->stable-baselines3[extra]) (3.0.2)\n", "Downloading nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl (363.4 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m363.4/363.4 MB\u001b[0m \u001b[31m3.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (13.8 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m13.8/13.8 MB\u001b[0m \u001b[31m69.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (24.6 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m24.6/24.6 MB\u001b[0m \u001b[31m34.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (883 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m883.7/883.7 kB\u001b[0m \u001b[31m49.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl (664.8 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m664.8/664.8 MB\u001b[0m \u001b[31m2.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl (211.5 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m211.5/211.5 MB\u001b[0m \u001b[31m5.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl (56.3 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m56.3/56.3 MB\u001b[0m \u001b[31m13.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl (127.9 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m127.9/127.9 MB\u001b[0m \u001b[31m7.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl (207.5 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m207.5/207.5 MB\u001b[0m \u001b[31m5.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (21.1 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m21.1/21.1 MB\u001b[0m \u001b[31m112.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading stable_baselines3-2.6.0-py3-none-any.whl (184 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m184.5/184.5 kB\u001b[0m \u001b[31m18.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hInstalling collected packages: nvidia-nvjitlink-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, nvidia-cusparse-cu12, nvidia-cudnn-cu12, nvidia-cusolver-cu12, stable-baselines3\n", " Attempting uninstall: nvidia-nvjitlink-cu12\n", " Found existing installation: nvidia-nvjitlink-cu12 12.5.82\n", " Uninstalling nvidia-nvjitlink-cu12-12.5.82:\n", " Successfully uninstalled nvidia-nvjitlink-cu12-12.5.82\n", " Attempting uninstall: nvidia-curand-cu12\n", " Found existing installation: nvidia-curand-cu12 10.3.6.82\n", " Uninstalling nvidia-curand-cu12-10.3.6.82:\n", " Successfully uninstalled nvidia-curand-cu12-10.3.6.82\n", " Attempting uninstall: nvidia-cufft-cu12\n", " Found existing installation: nvidia-cufft-cu12 11.2.3.61\n", " Uninstalling nvidia-cufft-cu12-11.2.3.61:\n", " Successfully uninstalled nvidia-cufft-cu12-11.2.3.61\n", " Attempting uninstall: nvidia-cuda-runtime-cu12\n", " Found existing installation: nvidia-cuda-runtime-cu12 12.5.82\n", " Uninstalling nvidia-cuda-runtime-cu12-12.5.82:\n", " Successfully uninstalled nvidia-cuda-runtime-cu12-12.5.82\n", " Attempting uninstall: nvidia-cuda-nvrtc-cu12\n", " Found existing installation: nvidia-cuda-nvrtc-cu12 12.5.82\n", " Uninstalling nvidia-cuda-nvrtc-cu12-12.5.82:\n", " Successfully uninstalled nvidia-cuda-nvrtc-cu12-12.5.82\n", " Attempting uninstall: nvidia-cuda-cupti-cu12\n", " Found existing installation: nvidia-cuda-cupti-cu12 12.5.82\n", " Uninstalling nvidia-cuda-cupti-cu12-12.5.82:\n", " Successfully uninstalled nvidia-cuda-cupti-cu12-12.5.82\n", " Attempting uninstall: nvidia-cublas-cu12\n", " Found existing installation: nvidia-cublas-cu12 12.5.3.2\n", " Uninstalling nvidia-cublas-cu12-12.5.3.2:\n", " Successfully uninstalled nvidia-cublas-cu12-12.5.3.2\n", " Attempting uninstall: nvidia-cusparse-cu12\n", " Found existing installation: nvidia-cusparse-cu12 12.5.1.3\n", " Uninstalling nvidia-cusparse-cu12-12.5.1.3:\n", " Successfully uninstalled nvidia-cusparse-cu12-12.5.1.3\n", " Attempting uninstall: nvidia-cudnn-cu12\n", " Found existing installation: nvidia-cudnn-cu12 9.3.0.75\n", " Uninstalling nvidia-cudnn-cu12-9.3.0.75:\n", " Successfully uninstalled nvidia-cudnn-cu12-9.3.0.75\n", " Attempting uninstall: nvidia-cusolver-cu12\n", " Found existing installation: nvidia-cusolver-cu12 11.6.3.83\n", " Uninstalling nvidia-cusolver-cu12-11.6.3.83:\n", " Successfully uninstalled nvidia-cusolver-cu12-11.6.3.83\n", "Successfully installed nvidia-cublas-cu12-12.4.5.8 nvidia-cuda-cupti-cu12-12.4.127 nvidia-cuda-nvrtc-cu12-12.4.127 nvidia-cuda-runtime-cu12-12.4.127 nvidia-cudnn-cu12-9.1.0.70 nvidia-cufft-cu12-11.2.1.3 nvidia-curand-cu12-10.3.5.147 nvidia-cusolver-cu12-11.6.1.9 nvidia-cusparse-cu12-12.3.1.170 nvidia-nvjitlink-cu12-12.4.127 stable-baselines3-2.6.0\n", "Requirement already satisfied: gymnasium in /usr/local/lib/python3.11/dist-packages (1.1.1)\n", "Requirement already satisfied: numpy>=1.21.0 in /usr/local/lib/python3.11/dist-packages (from gymnasium) (2.0.2)\n", "Requirement already satisfied: cloudpickle>=1.2.0 in /usr/local/lib/python3.11/dist-packages (from gymnasium) (3.1.1)\n", "Requirement already satisfied: typing-extensions>=4.3.0 in /usr/local/lib/python3.11/dist-packages (from gymnasium) (4.13.2)\n", "Requirement already satisfied: farama-notifications>=0.0.1 in /usr/local/lib/python3.11/dist-packages (from gymnasium) (0.0.4)\n" ] } ] }, { "cell_type": "code", "source": [ "!pip install huggingface_sb3\n", "!pip install huggingface_hub\n", "!pip install panda_gym" ], "metadata": { "id": "ABneW6tOSpyU", "colab": { "base_uri": "https://localhost:8080/" }, "outputId": "c40bf498-3c35-4e8a-fc97-275608b59d4f" }, "execution_count": 4, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Collecting huggingface_sb3\n", " Downloading huggingface_sb3-3.0-py3-none-any.whl.metadata (6.3 kB)\n", "Requirement already satisfied: huggingface-hub~=0.8 in /usr/local/lib/python3.11/dist-packages (from huggingface_sb3) (0.30.2)\n", "Requirement already satisfied: pyyaml~=6.0 in /usr/local/lib/python3.11/dist-packages (from huggingface_sb3) (6.0.2)\n", "Requirement already satisfied: wasabi in /usr/local/lib/python3.11/dist-packages (from huggingface_sb3) (1.1.3)\n", "Requirement already satisfied: numpy in /usr/local/lib/python3.11/dist-packages (from huggingface_sb3) (2.0.2)\n", "Requirement already satisfied: cloudpickle>=1.6 in /usr/local/lib/python3.11/dist-packages (from huggingface_sb3) (3.1.1)\n", "Requirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from huggingface-hub~=0.8->huggingface_sb3) (3.18.0)\n", "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.11/dist-packages (from huggingface-hub~=0.8->huggingface_sb3) (2025.3.2)\n", "Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.11/dist-packages (from huggingface-hub~=0.8->huggingface_sb3) (24.2)\n", "Requirement already satisfied: requests in /usr/local/lib/python3.11/dist-packages (from huggingface-hub~=0.8->huggingface_sb3) (2.32.3)\n", "Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.11/dist-packages (from huggingface-hub~=0.8->huggingface_sb3) (4.67.1)\n", "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.11/dist-packages (from huggingface-hub~=0.8->huggingface_sb3) (4.13.2)\n", "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests->huggingface-hub~=0.8->huggingface_sb3) (3.4.1)\n", "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/dist-packages (from requests->huggingface-hub~=0.8->huggingface_sb3) (3.10)\n", "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/dist-packages (from requests->huggingface-hub~=0.8->huggingface_sb3) (2.3.0)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/dist-packages (from requests->huggingface-hub~=0.8->huggingface_sb3) (2025.1.31)\n", "Downloading huggingface_sb3-3.0-py3-none-any.whl (9.7 kB)\n", "Installing collected packages: huggingface_sb3\n", "Successfully installed huggingface_sb3-3.0\n", "Requirement already satisfied: huggingface_hub in /usr/local/lib/python3.11/dist-packages (0.30.2)\n", "Requirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from huggingface_hub) (3.18.0)\n", "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.11/dist-packages (from huggingface_hub) (2025.3.2)\n", "Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.11/dist-packages (from huggingface_hub) (24.2)\n", "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.11/dist-packages (from huggingface_hub) (6.0.2)\n", "Requirement already satisfied: requests in /usr/local/lib/python3.11/dist-packages (from huggingface_hub) (2.32.3)\n", "Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.11/dist-packages (from huggingface_hub) (4.67.1)\n", "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.11/dist-packages (from huggingface_hub) (4.13.2)\n", "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests->huggingface_hub) (3.4.1)\n", "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/dist-packages (from requests->huggingface_hub) (3.10)\n", "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/dist-packages (from requests->huggingface_hub) (2.3.0)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/dist-packages (from requests->huggingface_hub) (2025.1.31)\n", "Collecting panda_gym\n", " Downloading panda_gym-3.0.7-py3-none-any.whl.metadata (4.3 kB)\n", "Requirement already satisfied: gymnasium>=0.26 in /usr/local/lib/python3.11/dist-packages (from panda_gym) (1.1.1)\n", "Collecting pybullet (from panda_gym)\n", " Downloading pybullet-3.2.7-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (1.8 kB)\n", "Requirement already satisfied: numpy in /usr/local/lib/python3.11/dist-packages (from panda_gym) (2.0.2)\n", "Requirement already satisfied: scipy in /usr/local/lib/python3.11/dist-packages (from panda_gym) (1.14.1)\n", "Requirement already satisfied: cloudpickle>=1.2.0 in /usr/local/lib/python3.11/dist-packages (from gymnasium>=0.26->panda_gym) (3.1.1)\n", "Requirement already satisfied: typing-extensions>=4.3.0 in /usr/local/lib/python3.11/dist-packages (from gymnasium>=0.26->panda_gym) (4.13.2)\n", "Requirement already satisfied: farama-notifications>=0.0.1 in /usr/local/lib/python3.11/dist-packages (from gymnasium>=0.26->panda_gym) (0.0.4)\n", "Downloading panda_gym-3.0.7-py3-none-any.whl (23 kB)\n", "Downloading pybullet-3.2.7-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (103.2 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m103.2/103.2 MB\u001b[0m \u001b[31m9.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hInstalling collected packages: pybullet, panda_gym\n", "Successfully installed panda_gym-3.0.7 pybullet-3.2.7\n" ] } ] }, { "cell_type": "markdown", "source": [ "## Import the packages 📦" ], "metadata": { "id": "QTep3PQQABLr" } }, { "cell_type": "code", "source": [ "import os\n", "\n", "import gymnasium as gym\n", "import panda_gym\n", "\n", "from huggingface_sb3 import load_from_hub, package_to_hub\n", "\n", "from stable_baselines3 import A2C\n", "from stable_baselines3.common.evaluation import evaluate_policy\n", "from stable_baselines3.common.vec_env import DummyVecEnv, VecNormalize\n", "from stable_baselines3.common.env_util import make_vec_env\n", "\n", "from huggingface_hub import notebook_login" ], "metadata": { "id": "HpiB8VdnQ7Bk" }, "execution_count": 5, "outputs": [] }, { "cell_type": "markdown", "source": [ "## PandaReachDense-v3 🦾\n", "\n", "The agent we're going to train is a robotic arm that needs to do controls (moving the arm and using the end-effector).\n", "\n", "In robotics, the *end-effector* is the device at the end of a robotic arm designed to interact with the environment.\n", "\n", "In `PandaReach`, the robot must place its end-effector at a target position (green ball).\n", "\n", "We're going to use the dense version of this environment. It means we'll get a *dense reward function* that **will provide a reward at each timestep** (the closer the agent is to completing the task, the higher the reward). Contrary to a *sparse reward function* where the environment **return a reward if and only if the task is completed**.\n", "\n", "Also, we're going to use the *End-effector displacement control*, it means the **action corresponds to the displacement of the end-effector**. We don't control the individual motion of each joint (joint control).\n", "\n", "\"Robotics\"/\n", "\n", "\n", "This way **the training will be easier**.\n", "\n" ], "metadata": { "id": "lfBwIS_oAVXI" } }, { "cell_type": "markdown", "source": [ "### Create the environment\n", "\n", "#### The environment 🎮\n", "\n", "In `PandaReachDense-v3` the robotic arm must place its end-effector at a target position (green ball)." ], "metadata": { "id": "frVXOrnlBerQ" } }, { "cell_type": "code", "source": [ "env_id = \"PandaReachDense-v3\"\n", "\n", "# Create the env\n", "env = gym.make(env_id)\n", "\n", "# Get the state space and action space\n", "s_size = env.observation_space.shape\n", "a_size = env.action_space" ], "metadata": { "id": "zXzAu3HYF1WD" }, "execution_count": 6, "outputs": [] }, { "cell_type": "code", "source": [ "print(\"_____OBSERVATION SPACE_____ \\n\")\n", "print(\"The State Space is: \", s_size)\n", "print(\"Sample observation\", env.observation_space.sample()) # Get a random observation" ], "metadata": { "id": "E-U9dexcF-FB", "colab": { "base_uri": "https://localhost:8080/" }, "outputId": "e0d5c225-ddce-410b-b669-2058e5cfefc0" }, "execution_count": 7, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "_____OBSERVATION SPACE_____ \n", "\n", "The State Space is: None\n", "Sample observation {'achieved_goal': array([-3.082749 , -6.84897 , -6.2908344], dtype=float32), 'desired_goal': array([2.3434515, 9.533496 , 6.9731393], dtype=float32), 'observation': array([ 1.9053264, 9.117922 , 8.848725 , -9.939038 , -4.997441 ,\n", " 3.1596105], dtype=float32)}\n" ] } ] }, { "cell_type": "markdown", "source": [ "The observation space **is a dictionary with 3 different elements**:\n", "- `achieved_goal`: (x,y,z) the current position of the end-effector.\n", "- `desired_goal`: (x,y,z) the target position for the end-effector.\n", "- `observation`: position (x,y,z) and velocity of the end-effector (vx, vy, vz).\n", "\n", "Given it's a dictionary as observation, **we will need to use a MultiInputPolicy policy instead of MlpPolicy**." ], "metadata": { "id": "g_JClfElGFnF" } }, { "cell_type": "code", "source": [ "print(\"\\n _____ACTION SPACE_____ \\n\")\n", "print(\"The Action Space is: \", a_size)\n", "print(\"Action Space Sample\", env.action_space.sample()) # Take a random action" ], "metadata": { "id": "ib1Kxy4AF-FC", "colab": { "base_uri": "https://localhost:8080/" }, "outputId": "24656c68-bed6-44c6-fb43-adc49d7913f6" }, "execution_count": 8, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\n", " _____ACTION SPACE_____ \n", "\n", "The Action Space is: Box(-1.0, 1.0, (3,), float32)\n", "Action Space Sample [-0.05352502 0.19605625 -0.7072932 ]\n" ] } ] }, { "cell_type": "markdown", "source": [ "The action space is a vector with 3 values:\n", "- Control x, y, z movement" ], "metadata": { "id": "5MHTHEHZS4yp" } }, { "cell_type": "markdown", "source": [ "### Normalize observation and rewards" ], "metadata": { "id": "S5sXcg469ysB" } }, { "cell_type": "markdown", "source": [ "A good practice in reinforcement learning is to [normalize input features](https://stable-baselines3.readthedocs.io/en/master/guide/rl_tips.html).\n", "\n", "For that purpose, there is a wrapper that will compute a running average and standard deviation of input features.\n", "\n", "We also normalize rewards with this same wrapper by adding `norm_reward = True`\n", "\n", "[You should check the documentation to fill this cell](https://stable-baselines3.readthedocs.io/en/master/guide/vec_envs.html#vecnormalize)" ], "metadata": { "id": "1ZyX6qf3Zva9" } }, { "cell_type": "code", "source": [ "env = make_vec_env(env_id, n_envs=4)\n", "\n", "# Adding this wrapper to normalize the observation and the reward\n", "env = VecNormalize(env, norm_obs=True, norm_reward=True, clip_obs=10.) # TODO: Add the wrapper" ], "metadata": { "id": "1RsDtHHAQ9Ie" }, "execution_count": 9, "outputs": [] }, { "cell_type": "markdown", "source": [ "### Create the A2C Model 🤖\n", "\n", "For more information about A2C implementation with StableBaselines3 check: https://stable-baselines3.readthedocs.io/en/master/modules/a2c.html#notes\n", "\n", "To find the best parameters I checked the [official trained agents by Stable-Baselines3 team](https://huggingface.co/sb3)." ], "metadata": { "id": "4JmEVU6z1ZA-" } }, { "cell_type": "code", "source": [ "model = A2C(policy = \"MultiInputPolicy\",\n", " env = env,\n", " verbose=1)" ], "metadata": { "id": "vR3T4qFt164I", "colab": { "base_uri": "https://localhost:8080/" }, "outputId": "8e020615-2704-470f-b761-678a99cb6cf5" }, "execution_count": 10, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Using cuda device\n" ] } ] }, { "cell_type": "markdown", "source": [ "### Train the A2C agent 🏃\n", "- Let's train our agent for 1,000,000 timesteps, don't forget to use GPU on Colab. It will take approximately ~25-40min" ], "metadata": { "id": "opyK3mpJ1-m9" } }, { "cell_type": "code", "source": [ "model.learn(1_000_000)" ], "metadata": { "id": "4TuGHZD7RF1G", "colab": { "base_uri": "https://localhost:8080/" }, "outputId": "c4115cc3-c756-4682-ccea-dc53bc113e10" }, "execution_count": 11, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\u001b[1;30;43mStreaming output truncated to the last 5000 lines.\u001b[0m\n", "| std | 0.427 |\n", "| value_loss | 6.84e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.7 |\n", "| ep_rew_mean | -0.211 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 23800 |\n", "| time_elapsed | 1098 |\n", "| total_timesteps | 476000 |\n", "| train/ | |\n", "| entropy_loss | -1.46 |\n", "| explained_variance | 0.985 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 23799 |\n", "| policy_loss | -0.0111 |\n", "| std | 0.425 |\n", "| value_loss | 0.000113 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.83 |\n", "| ep_rew_mean | -0.222 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 23900 |\n", "| time_elapsed | 1103 |\n", "| total_timesteps | 478000 |\n", "| train/ | |\n", "| entropy_loss | -1.44 |\n", "| explained_variance | 0.906 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 23899 |\n", "| policy_loss | -0.00159 |\n", "| std | 0.424 |\n", "| value_loss | 0.000297 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.71 |\n", "| ep_rew_mean | -0.204 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 24000 |\n", "| time_elapsed | 1107 |\n", "| total_timesteps | 480000 |\n", "| train/ | |\n", "| entropy_loss | -1.42 |\n", "| explained_variance | 0.932 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 23999 |\n", "| policy_loss | 0.000609 |\n", "| std | 0.421 |\n", "| value_loss | 0.000226 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.69 |\n", "| ep_rew_mean | -0.215 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 24100 |\n", "| time_elapsed | 1112 |\n", "| total_timesteps | 482000 |\n", "| train/ | |\n", "| entropy_loss | -1.43 |\n", "| explained_variance | 0.947 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 24099 |\n", "| policy_loss | 0.0105 |\n", "| std | 0.423 |\n", "| value_loss | 0.000207 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.65 |\n", "| ep_rew_mean | -0.198 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 24200 |\n", "| time_elapsed | 1116 |\n", "| total_timesteps | 484000 |\n", "| train/ | |\n", "| entropy_loss | -1.41 |\n", "| explained_variance | 0.953 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 24199 |\n", "| policy_loss | 0.00712 |\n", "| std | 0.419 |\n", "| value_loss | 7.76e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.87 |\n", "| ep_rew_mean | -0.231 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 24300 |\n", "| time_elapsed | 1120 |\n", "| total_timesteps | 486000 |\n", "| train/ | |\n", "| entropy_loss | -1.38 |\n", "| explained_variance | 0.972 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 24299 |\n", "| policy_loss | -0.00217 |\n", "| std | 0.416 |\n", "| value_loss | 0.000111 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.63 |\n", "| ep_rew_mean | -0.206 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 24400 |\n", "| time_elapsed | 1125 |\n", "| total_timesteps | 488000 |\n", "| train/ | |\n", "| entropy_loss | -1.38 |\n", "| explained_variance | 0.991 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 24399 |\n", "| policy_loss | -0.0139 |\n", "| std | 0.416 |\n", "| value_loss | 0.000124 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.67 |\n", "| ep_rew_mean | -0.2 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 24500 |\n", "| time_elapsed | 1130 |\n", "| total_timesteps | 490000 |\n", "| train/ | |\n", "| entropy_loss | -1.36 |\n", "| explained_variance | 0.922 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 24499 |\n", "| policy_loss | -0.00156 |\n", "| std | 0.414 |\n", "| value_loss | 0.000142 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.67 |\n", "| ep_rew_mean | -0.205 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 24600 |\n", "| time_elapsed | 1134 |\n", "| total_timesteps | 492000 |\n", "| train/ | |\n", "| entropy_loss | -1.36 |\n", "| explained_variance | 0.903 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 24599 |\n", "| policy_loss | -0.00296 |\n", "| std | 0.416 |\n", "| value_loss | 0.000404 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.93 |\n", "| ep_rew_mean | -0.229 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 24700 |\n", "| time_elapsed | 1139 |\n", "| total_timesteps | 494000 |\n", "| train/ | |\n", "| entropy_loss | -1.37 |\n", "| explained_variance | 0.938 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 24699 |\n", "| policy_loss | -0.00411 |\n", "| std | 0.418 |\n", "| value_loss | 0.000287 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.69 |\n", "| ep_rew_mean | -0.213 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 24800 |\n", "| time_elapsed | 1143 |\n", "| total_timesteps | 496000 |\n", "| train/ | |\n", "| entropy_loss | -1.37 |\n", "| explained_variance | 0.912 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 24799 |\n", "| policy_loss | -0.00394 |\n", "| std | 0.418 |\n", "| value_loss | 0.000222 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.86 |\n", "| ep_rew_mean | -0.226 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 24900 |\n", "| time_elapsed | 1148 |\n", "| total_timesteps | 498000 |\n", "| train/ | |\n", "| entropy_loss | -1.32 |\n", "| explained_variance | 0.961 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 24899 |\n", "| policy_loss | 0.0116 |\n", "| std | 0.413 |\n", "| value_loss | 0.000189 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.75 |\n", "| ep_rew_mean | -0.209 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 25000 |\n", "| time_elapsed | 1153 |\n", "| total_timesteps | 500000 |\n", "| train/ | |\n", "| entropy_loss | -1.3 |\n", "| explained_variance | 0.935 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 24999 |\n", "| policy_loss | -0.0115 |\n", "| std | 0.411 |\n", "| value_loss | 0.000382 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.75 |\n", "| ep_rew_mean | -0.209 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 25100 |\n", "| time_elapsed | 1157 |\n", "| total_timesteps | 502000 |\n", "| train/ | |\n", "| entropy_loss | -1.3 |\n", "| explained_variance | 0.98 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 25099 |\n", "| policy_loss | -0.00227 |\n", "| std | 0.41 |\n", "| value_loss | 9.26e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.7 |\n", "| ep_rew_mean | -0.204 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 25200 |\n", "| time_elapsed | 1162 |\n", "| total_timesteps | 504000 |\n", "| train/ | |\n", "| entropy_loss | -1.31 |\n", "| explained_variance | 0.978 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 25199 |\n", "| policy_loss | 0.00298 |\n", "| std | 0.413 |\n", "| value_loss | 7.67e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.69 |\n", "| ep_rew_mean | -0.205 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 25300 |\n", "| time_elapsed | 1166 |\n", "| total_timesteps | 506000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0.94 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 25299 |\n", "| policy_loss | -0.00614 |\n", "| std | 0.409 |\n", "| value_loss | 0.000277 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.77 |\n", "| ep_rew_mean | -0.208 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 25400 |\n", "| time_elapsed | 1171 |\n", "| total_timesteps | 508000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0.95 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 25399 |\n", "| policy_loss | -0.00842 |\n", "| std | 0.406 |\n", "| value_loss | 0.000249 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.75 |\n", "| ep_rew_mean | -0.211 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 25500 |\n", "| time_elapsed | 1176 |\n", "| total_timesteps | 510000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0.983 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 25499 |\n", "| policy_loss | -0.00034 |\n", "| std | 0.402 |\n", "| value_loss | 6.92e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.77 |\n", "| ep_rew_mean | -0.212 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 25600 |\n", "| time_elapsed | 1180 |\n", "| total_timesteps | 512000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0.978 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 25599 |\n", "| policy_loss | -0.00104 |\n", "| std | 0.399 |\n", "| value_loss | 6.99e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.66 |\n", "| ep_rew_mean | -0.198 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 25700 |\n", "| time_elapsed | 1185 |\n", "| total_timesteps | 514000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0.979 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 25699 |\n", "| policy_loss | 0.0101 |\n", "| std | 0.396 |\n", "| value_loss | 0.000122 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.86 |\n", "| ep_rew_mean | -0.227 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 25800 |\n", "| time_elapsed | 1190 |\n", "| total_timesteps | 516000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0.981 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 25799 |\n", "| policy_loss | 0.0121 |\n", "| std | 0.393 |\n", "| value_loss | 0.000243 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.61 |\n", "| ep_rew_mean | -0.199 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 25900 |\n", "| time_elapsed | 1194 |\n", "| total_timesteps | 518000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0.876 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 25899 |\n", "| policy_loss | 0.0156 |\n", "| std | 0.394 |\n", "| value_loss | 0.000562 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.77 |\n", "| ep_rew_mean | -0.218 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 26000 |\n", "| time_elapsed | 1199 |\n", "| total_timesteps | 520000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0.976 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 25999 |\n", "| policy_loss | 0.00771 |\n", "| std | 0.393 |\n", "| value_loss | 0.000189 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.71 |\n", "| ep_rew_mean | -0.21 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 26100 |\n", "| time_elapsed | 1204 |\n", "| total_timesteps | 522000 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0.972 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 26099 |\n", "| policy_loss | 0.00407 |\n", "| std | 0.392 |\n", "| value_loss | 0.000216 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.74 |\n", "| ep_rew_mean | -0.213 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 26200 |\n", "| time_elapsed | 1208 |\n", "| total_timesteps | 524000 |\n", "| train/ | |\n", "| entropy_loss | -1.13 |\n", "| explained_variance | 0.956 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 26199 |\n", "| policy_loss | -0.0164 |\n", "| std | 0.39 |\n", "| value_loss | 0.00054 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.68 |\n", "| ep_rew_mean | -0.207 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 26300 |\n", "| time_elapsed | 1213 |\n", "| total_timesteps | 526000 |\n", "| train/ | |\n", "| entropy_loss | -1.1 |\n", "| explained_variance | 0.869 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 26299 |\n", "| policy_loss | 0.0146 |\n", "| std | 0.387 |\n", "| value_loss | 0.000809 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.75 |\n", "| ep_rew_mean | -0.215 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 26400 |\n", "| time_elapsed | 1217 |\n", "| total_timesteps | 528000 |\n", "| train/ | |\n", "| entropy_loss | -1.1 |\n", "| explained_variance | 0.931 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 26399 |\n", "| policy_loss | 0.00581 |\n", "| std | 0.386 |\n", "| value_loss | 0.000348 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.68 |\n", "| ep_rew_mean | -0.213 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 26500 |\n", "| time_elapsed | 1222 |\n", "| total_timesteps | 530000 |\n", "| train/ | |\n", "| entropy_loss | -1.09 |\n", "| explained_variance | 0.984 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 26499 |\n", "| policy_loss | -0.00137 |\n", "| std | 0.387 |\n", "| value_loss | 9.24e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.82 |\n", "| ep_rew_mean | -0.215 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 26600 |\n", "| time_elapsed | 1227 |\n", "| total_timesteps | 532000 |\n", "| train/ | |\n", "| entropy_loss | -1.09 |\n", "| explained_variance | 0.968 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 26599 |\n", "| policy_loss | 0.00834 |\n", "| std | 0.385 |\n", "| value_loss | 0.000264 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.87 |\n", "| ep_rew_mean | -0.228 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 26700 |\n", "| time_elapsed | 1231 |\n", "| total_timesteps | 534000 |\n", "| train/ | |\n", "| entropy_loss | -1.09 |\n", "| explained_variance | 0.93 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 26699 |\n", "| policy_loss | 0.0187 |\n", "| std | 0.386 |\n", "| value_loss | 0.000679 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.76 |\n", "| ep_rew_mean | -0.215 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 26800 |\n", "| time_elapsed | 1236 |\n", "| total_timesteps | 536000 |\n", "| train/ | |\n", "| entropy_loss | -1.07 |\n", "| explained_variance | 0.94 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 26799 |\n", "| policy_loss | 0.0174 |\n", "| std | 0.383 |\n", "| value_loss | 0.000832 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.89 |\n", "| ep_rew_mean | -0.228 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 26900 |\n", "| time_elapsed | 1240 |\n", "| total_timesteps | 538000 |\n", "| train/ | |\n", "| entropy_loss | -1.04 |\n", "| explained_variance | 0.973 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 26899 |\n", "| policy_loss | -0.0175 |\n", "| std | 0.38 |\n", "| value_loss | 0.000376 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.85 |\n", "| ep_rew_mean | -0.219 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 27000 |\n", "| time_elapsed | 1245 |\n", "| total_timesteps | 540000 |\n", "| train/ | |\n", "| entropy_loss | -1.03 |\n", "| explained_variance | 0.948 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 26999 |\n", "| policy_loss | -0.01 |\n", "| std | 0.377 |\n", "| value_loss | 0.000345 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.68 |\n", "| ep_rew_mean | -0.207 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 27100 |\n", "| time_elapsed | 1250 |\n", "| total_timesteps | 542000 |\n", "| train/ | |\n", "| entropy_loss | -1.03 |\n", "| explained_variance | 0.975 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 27099 |\n", "| policy_loss | 0.000292 |\n", "| std | 0.377 |\n", "| value_loss | 8.51e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.83 |\n", "| ep_rew_mean | -0.226 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 27200 |\n", "| time_elapsed | 1254 |\n", "| total_timesteps | 544000 |\n", "| train/ | |\n", "| entropy_loss | -1.01 |\n", "| explained_variance | 0.977 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 27199 |\n", "| policy_loss | -0.00472 |\n", "| std | 0.377 |\n", "| value_loss | 0.000147 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.79 |\n", "| ep_rew_mean | -0.225 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 27300 |\n", "| time_elapsed | 1258 |\n", "| total_timesteps | 546000 |\n", "| train/ | |\n", "| entropy_loss | -1.02 |\n", "| explained_variance | 0.981 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 27299 |\n", "| policy_loss | -0.0088 |\n", "| std | 0.378 |\n", "| value_loss | 0.000117 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.63 |\n", "| ep_rew_mean | -0.2 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 27400 |\n", "| time_elapsed | 1264 |\n", "| total_timesteps | 548000 |\n", "| train/ | |\n", "| entropy_loss | -1.02 |\n", "| explained_variance | 0.956 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 27399 |\n", "| policy_loss | -0.00246 |\n", "| std | 0.377 |\n", "| value_loss | 0.000209 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.6 |\n", "| ep_rew_mean | -0.197 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 27500 |\n", "| time_elapsed | 1268 |\n", "| total_timesteps | 550000 |\n", "| train/ | |\n", "| entropy_loss | -0.998 |\n", "| explained_variance | 0.973 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 27499 |\n", "| policy_loss | -0.00589 |\n", "| std | 0.374 |\n", "| value_loss | 0.000168 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.71 |\n", "| ep_rew_mean | -0.213 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 27600 |\n", "| time_elapsed | 1273 |\n", "| total_timesteps | 552000 |\n", "| train/ | |\n", "| entropy_loss | -1.01 |\n", "| explained_variance | 0.855 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 27599 |\n", "| policy_loss | 0.00725 |\n", "| std | 0.376 |\n", "| value_loss | 0.000459 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.76 |\n", "| ep_rew_mean | -0.222 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 27700 |\n", "| time_elapsed | 1277 |\n", "| total_timesteps | 554000 |\n", "| train/ | |\n", "| entropy_loss | -0.992 |\n", "| explained_variance | 0.969 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 27699 |\n", "| policy_loss | -0.00445 |\n", "| std | 0.374 |\n", "| value_loss | 0.000155 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.74 |\n", "| ep_rew_mean | -0.205 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 27800 |\n", "| time_elapsed | 1282 |\n", "| total_timesteps | 556000 |\n", "| train/ | |\n", "| entropy_loss | -0.98 |\n", "| explained_variance | 0.863 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 27799 |\n", "| policy_loss | -0.0196 |\n", "| std | 0.373 |\n", "| value_loss | 0.000531 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.78 |\n", "| ep_rew_mean | -0.216 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 27900 |\n", "| time_elapsed | 1287 |\n", "| total_timesteps | 558000 |\n", "| train/ | |\n", "| entropy_loss | -0.961 |\n", "| explained_variance | 0.963 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 27899 |\n", "| policy_loss | 0.00533 |\n", "| std | 0.371 |\n", "| value_loss | 0.000169 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.74 |\n", "| ep_rew_mean | -0.223 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 28000 |\n", "| time_elapsed | 1291 |\n", "| total_timesteps | 560000 |\n", "| train/ | |\n", "| entropy_loss | -0.974 |\n", "| explained_variance | 0.989 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 27999 |\n", "| policy_loss | 0.00383 |\n", "| std | 0.373 |\n", "| value_loss | 5.68e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.59 |\n", "| ep_rew_mean | -0.196 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 28100 |\n", "| time_elapsed | 1295 |\n", "| total_timesteps | 562000 |\n", "| train/ | |\n", "| entropy_loss | -0.966 |\n", "| explained_variance | 0.985 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 28099 |\n", "| policy_loss | -0.00681 |\n", "| std | 0.372 |\n", "| value_loss | 0.000135 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.78 |\n", "| ep_rew_mean | -0.213 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 28200 |\n", "| time_elapsed | 1300 |\n", "| total_timesteps | 564000 |\n", "| train/ | |\n", "| entropy_loss | -0.953 |\n", "| explained_variance | 0.993 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 28199 |\n", "| policy_loss | 0.00558 |\n", "| std | 0.371 |\n", "| value_loss | 6.37e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.7 |\n", "| ep_rew_mean | -0.213 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 28300 |\n", "| time_elapsed | 1305 |\n", "| total_timesteps | 566000 |\n", "| train/ | |\n", "| entropy_loss | -0.93 |\n", "| explained_variance | 0.978 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 28299 |\n", "| policy_loss | -0.0115 |\n", "| std | 0.367 |\n", "| value_loss | 0.000165 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.87 |\n", "| ep_rew_mean | -0.222 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 28400 |\n", "| time_elapsed | 1309 |\n", "| total_timesteps | 568000 |\n", "| train/ | |\n", "| entropy_loss | -0.899 |\n", "| explained_variance | 0.947 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 28399 |\n", "| policy_loss | -0.00193 |\n", "| std | 0.364 |\n", "| value_loss | 0.000349 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.57 |\n", "| ep_rew_mean | -0.201 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 28500 |\n", "| time_elapsed | 1314 |\n", "| total_timesteps | 570000 |\n", "| train/ | |\n", "| entropy_loss | -0.909 |\n", "| explained_variance | 0.987 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 28499 |\n", "| policy_loss | 0.00874 |\n", "| std | 0.365 |\n", "| value_loss | 0.000116 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.71 |\n", "| ep_rew_mean | -0.211 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 28600 |\n", "| time_elapsed | 1319 |\n", "| total_timesteps | 572000 |\n", "| train/ | |\n", "| entropy_loss | -0.919 |\n", "| explained_variance | 0.706 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 28599 |\n", "| policy_loss | -0.00867 |\n", "| std | 0.366 |\n", "| value_loss | 0.00318 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.74 |\n", "| ep_rew_mean | -0.211 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 28700 |\n", "| time_elapsed | 1324 |\n", "| total_timesteps | 574000 |\n", "| train/ | |\n", "| entropy_loss | -0.91 |\n", "| explained_variance | 0.983 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 28699 |\n", "| policy_loss | 0.00229 |\n", "| std | 0.365 |\n", "| value_loss | 9.89e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.73 |\n", "| ep_rew_mean | -0.208 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 28800 |\n", "| time_elapsed | 1328 |\n", "| total_timesteps | 576000 |\n", "| train/ | |\n", "| entropy_loss | -0.899 |\n", "| explained_variance | 0.933 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 28799 |\n", "| policy_loss | 0.0212 |\n", "| std | 0.365 |\n", "| value_loss | 0.000345 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.64 |\n", "| ep_rew_mean | -0.205 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 28900 |\n", "| time_elapsed | 1332 |\n", "| total_timesteps | 578000 |\n", "| train/ | |\n", "| entropy_loss | -0.899 |\n", "| explained_variance | 0.993 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 28899 |\n", "| policy_loss | 0.0012 |\n", "| std | 0.365 |\n", "| value_loss | 5.8e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.82 |\n", "| ep_rew_mean | -0.214 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 29000 |\n", "| time_elapsed | 1337 |\n", "| total_timesteps | 580000 |\n", "| train/ | |\n", "| entropy_loss | -0.906 |\n", "| explained_variance | 0.973 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 28999 |\n", "| policy_loss | -0.00343 |\n", "| std | 0.368 |\n", "| value_loss | 0.000101 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.83 |\n", "| ep_rew_mean | -0.226 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 29100 |\n", "| time_elapsed | 1342 |\n", "| total_timesteps | 582000 |\n", "| train/ | |\n", "| entropy_loss | -0.905 |\n", "| explained_variance | 0.957 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 29099 |\n", "| policy_loss | 0.0102 |\n", "| std | 0.367 |\n", "| value_loss | 0.000602 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.64 |\n", "| ep_rew_mean | -0.198 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 29200 |\n", "| time_elapsed | 1347 |\n", "| total_timesteps | 584000 |\n", "| train/ | |\n", "| entropy_loss | -0.905 |\n", "| explained_variance | 0.992 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 29199 |\n", "| policy_loss | -0.00065 |\n", "| std | 0.368 |\n", "| value_loss | 6.95e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.78 |\n", "| ep_rew_mean | -0.215 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 29300 |\n", "| time_elapsed | 1352 |\n", "| total_timesteps | 586000 |\n", "| train/ | |\n", "| entropy_loss | -0.898 |\n", "| explained_variance | 0.979 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 29299 |\n", "| policy_loss | -0.00696 |\n", "| std | 0.366 |\n", "| value_loss | 0.00023 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.6 |\n", "| ep_rew_mean | -0.193 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 29400 |\n", "| time_elapsed | 1356 |\n", "| total_timesteps | 588000 |\n", "| train/ | |\n", "| entropy_loss | -0.897 |\n", "| explained_variance | 0.993 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 29399 |\n", "| policy_loss | -0.00641 |\n", "| std | 0.366 |\n", "| value_loss | 7.38e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.75 |\n", "| ep_rew_mean | -0.214 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 29500 |\n", "| time_elapsed | 1361 |\n", "| total_timesteps | 590000 |\n", "| train/ | |\n", "| entropy_loss | -0.877 |\n", "| explained_variance | 0.945 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 29499 |\n", "| policy_loss | 0.0121 |\n", "| std | 0.365 |\n", "| value_loss | 0.00051 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.74 |\n", "| ep_rew_mean | -0.217 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 29600 |\n", "| time_elapsed | 1365 |\n", "| total_timesteps | 592000 |\n", "| train/ | |\n", "| entropy_loss | -0.848 |\n", "| explained_variance | 0.951 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 29599 |\n", "| policy_loss | 0.00817 |\n", "| std | 0.362 |\n", "| value_loss | 0.000239 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.67 |\n", "| ep_rew_mean | -0.211 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 29700 |\n", "| time_elapsed | 1370 |\n", "| total_timesteps | 594000 |\n", "| train/ | |\n", "| entropy_loss | -0.831 |\n", "| explained_variance | 0.738 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 29699 |\n", "| policy_loss | 0.00339 |\n", "| std | 0.36 |\n", "| value_loss | 0.001 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.71 |\n", "| ep_rew_mean | -0.219 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 29800 |\n", "| time_elapsed | 1375 |\n", "| total_timesteps | 596000 |\n", "| train/ | |\n", "| entropy_loss | -0.821 |\n", "| explained_variance | 0.99 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 29799 |\n", "| policy_loss | 0.00661 |\n", "| std | 0.36 |\n", "| value_loss | 0.000115 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.7 |\n", "| ep_rew_mean | -0.21 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 29900 |\n", "| time_elapsed | 1379 |\n", "| total_timesteps | 598000 |\n", "| train/ | |\n", "| entropy_loss | -0.811 |\n", "| explained_variance | 0.983 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 29899 |\n", "| policy_loss | 0.0109 |\n", "| std | 0.359 |\n", "| value_loss | 0.000162 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.75 |\n", "| ep_rew_mean | -0.215 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 30000 |\n", "| time_elapsed | 1384 |\n", "| total_timesteps | 600000 |\n", "| train/ | |\n", "| entropy_loss | -0.788 |\n", "| explained_variance | 0.958 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 29999 |\n", "| policy_loss | 0.0089 |\n", "| std | 0.357 |\n", "| value_loss | 0.000172 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.67 |\n", "| ep_rew_mean | -0.204 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 30100 |\n", "| time_elapsed | 1389 |\n", "| total_timesteps | 602000 |\n", "| train/ | |\n", "| entropy_loss | -0.773 |\n", "| explained_variance | 0.968 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 30099 |\n", "| policy_loss | -0.012 |\n", "| std | 0.354 |\n", "| value_loss | 0.000517 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.66 |\n", "| ep_rew_mean | -0.209 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 30200 |\n", "| time_elapsed | 1394 |\n", "| total_timesteps | 604000 |\n", "| train/ | |\n", "| entropy_loss | -0.763 |\n", "| explained_variance | 0.969 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 30199 |\n", "| policy_loss | -0.00892 |\n", "| std | 0.353 |\n", "| value_loss | 0.000289 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.61 |\n", "| ep_rew_mean | -0.198 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 30300 |\n", "| time_elapsed | 1399 |\n", "| total_timesteps | 606000 |\n", "| train/ | |\n", "| entropy_loss | -0.765 |\n", "| explained_variance | 0.948 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 30299 |\n", "| policy_loss | 0.00261 |\n", "| std | 0.354 |\n", "| value_loss | 0.000432 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.71 |\n", "| ep_rew_mean | -0.209 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 30400 |\n", "| time_elapsed | 1403 |\n", "| total_timesteps | 608000 |\n", "| train/ | |\n", "| entropy_loss | -0.746 |\n", "| explained_variance | 0.963 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 30399 |\n", "| policy_loss | -0.00757 |\n", "| std | 0.352 |\n", "| value_loss | 0.000156 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.53 |\n", "| ep_rew_mean | -0.193 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 30500 |\n", "| time_elapsed | 1408 |\n", "| total_timesteps | 610000 |\n", "| train/ | |\n", "| entropy_loss | -0.752 |\n", "| explained_variance | 0.983 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 30499 |\n", "| policy_loss | -0.006 |\n", "| std | 0.352 |\n", "| value_loss | 0.000156 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.74 |\n", "| ep_rew_mean | -0.224 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 30600 |\n", "| time_elapsed | 1413 |\n", "| total_timesteps | 612000 |\n", "| train/ | |\n", "| entropy_loss | -0.751 |\n", "| explained_variance | 0.992 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 30599 |\n", "| policy_loss | 0.000845 |\n", "| std | 0.353 |\n", "| value_loss | 9.19e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.74 |\n", "| ep_rew_mean | -0.217 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 30700 |\n", "| time_elapsed | 1417 |\n", "| total_timesteps | 614000 |\n", "| train/ | |\n", "| entropy_loss | -0.758 |\n", "| explained_variance | 0.981 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 30699 |\n", "| policy_loss | 0.00193 |\n", "| std | 0.354 |\n", "| value_loss | 9.43e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.81 |\n", "| ep_rew_mean | -0.227 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 30800 |\n", "| time_elapsed | 1422 |\n", "| total_timesteps | 616000 |\n", "| train/ | |\n", "| entropy_loss | -0.727 |\n", "| explained_variance | 0.993 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 30799 |\n", "| policy_loss | 0.00262 |\n", "| std | 0.35 |\n", "| value_loss | 3.4e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.52 |\n", "| ep_rew_mean | -0.192 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 30900 |\n", "| time_elapsed | 1427 |\n", "| total_timesteps | 618000 |\n", "| train/ | |\n", "| entropy_loss | -0.711 |\n", "| explained_variance | 0.974 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 30899 |\n", "| policy_loss | 0.00125 |\n", "| std | 0.348 |\n", "| value_loss | 0.000112 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.65 |\n", "| ep_rew_mean | -0.2 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 31000 |\n", "| time_elapsed | 1431 |\n", "| total_timesteps | 620000 |\n", "| train/ | |\n", "| entropy_loss | -0.714 |\n", "| explained_variance | 0.963 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 30999 |\n", "| policy_loss | 0.0064 |\n", "| std | 0.348 |\n", "| value_loss | 0.000133 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.81 |\n", "| ep_rew_mean | -0.215 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 31100 |\n", "| time_elapsed | 1436 |\n", "| total_timesteps | 622000 |\n", "| train/ | |\n", "| entropy_loss | -0.692 |\n", "| explained_variance | 0.95 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 31099 |\n", "| policy_loss | 0.0134 |\n", "| std | 0.346 |\n", "| value_loss | 0.000355 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.86 |\n", "| ep_rew_mean | -0.224 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 31200 |\n", "| time_elapsed | 1440 |\n", "| total_timesteps | 624000 |\n", "| train/ | |\n", "| entropy_loss | -0.701 |\n", "| explained_variance | 0.956 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 31199 |\n", "| policy_loss | -0.00874 |\n", "| std | 0.347 |\n", "| value_loss | 0.000189 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.73 |\n", "| ep_rew_mean | -0.21 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 31300 |\n", "| time_elapsed | 1445 |\n", "| total_timesteps | 626000 |\n", "| train/ | |\n", "| entropy_loss | -0.692 |\n", "| explained_variance | 0.934 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 31299 |\n", "| policy_loss | -0.00105 |\n", "| std | 0.347 |\n", "| value_loss | 0.000326 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.69 |\n", "| ep_rew_mean | -0.208 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 31400 |\n", "| time_elapsed | 1450 |\n", "| total_timesteps | 628000 |\n", "| train/ | |\n", "| entropy_loss | -0.694 |\n", "| explained_variance | 0.982 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 31399 |\n", "| policy_loss | -0.00142 |\n", "| std | 0.348 |\n", "| value_loss | 0.000126 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.79 |\n", "| ep_rew_mean | -0.221 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 31500 |\n", "| time_elapsed | 1454 |\n", "| total_timesteps | 630000 |\n", "| train/ | |\n", "| entropy_loss | -0.673 |\n", "| explained_variance | 0.963 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 31499 |\n", "| policy_loss | 0.016 |\n", "| std | 0.347 |\n", "| value_loss | 0.000297 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.79 |\n", "| ep_rew_mean | -0.213 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 31600 |\n", "| time_elapsed | 1459 |\n", "| total_timesteps | 632000 |\n", "| train/ | |\n", "| entropy_loss | -0.645 |\n", "| explained_variance | 0.974 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 31599 |\n", "| policy_loss | -0.00516 |\n", "| std | 0.343 |\n", "| value_loss | 0.000264 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.8 |\n", "| ep_rew_mean | -0.223 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 31700 |\n", "| time_elapsed | 1464 |\n", "| total_timesteps | 634000 |\n", "| train/ | |\n", "| entropy_loss | -0.62 |\n", "| explained_variance | 0.992 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 31699 |\n", "| policy_loss | 0.00225 |\n", "| std | 0.341 |\n", "| value_loss | 5.26e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.79 |\n", "| ep_rew_mean | -0.218 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 31800 |\n", "| time_elapsed | 1468 |\n", "| total_timesteps | 636000 |\n", "| train/ | |\n", "| entropy_loss | -0.604 |\n", "| explained_variance | 0.9 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 31799 |\n", "| policy_loss | 6.26e-05 |\n", "| std | 0.34 |\n", "| value_loss | 0.00108 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.77 |\n", "| ep_rew_mean | -0.22 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 31900 |\n", "| time_elapsed | 1473 |\n", "| total_timesteps | 638000 |\n", "| train/ | |\n", "| entropy_loss | -0.59 |\n", "| explained_variance | 0.977 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 31899 |\n", "| policy_loss | -0.00306 |\n", "| std | 0.339 |\n", "| value_loss | 0.000224 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.88 |\n", "| ep_rew_mean | -0.231 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 32000 |\n", "| time_elapsed | 1478 |\n", "| total_timesteps | 640000 |\n", "| train/ | |\n", "| entropy_loss | -0.585 |\n", "| explained_variance | 0.967 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 31999 |\n", "| policy_loss | 0.00328 |\n", "| std | 0.337 |\n", "| value_loss | 0.000582 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.76 |\n", "| ep_rew_mean | -0.213 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 433 |\n", "| iterations | 32100 |\n", "| time_elapsed | 1482 |\n", "| total_timesteps | 642000 |\n", "| train/ | |\n", "| entropy_loss | -0.585 |\n", "| explained_variance | 0.99 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 32099 |\n", "| policy_loss | -0.00058 |\n", "| std | 0.337 |\n", "| value_loss | 4.08e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.64 |\n", "| ep_rew_mean | -0.197 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 32200 |\n", "| time_elapsed | 1487 |\n", "| total_timesteps | 644000 |\n", "| train/ | |\n", "| entropy_loss | -0.593 |\n", "| explained_variance | 0.976 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 32199 |\n", "| policy_loss | -0.00649 |\n", "| std | 0.337 |\n", "| value_loss | 0.000138 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.76 |\n", "| ep_rew_mean | -0.212 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 32300 |\n", "| time_elapsed | 1492 |\n", "| total_timesteps | 646000 |\n", "| train/ | |\n", "| entropy_loss | -0.576 |\n", "| explained_variance | 0.978 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 32299 |\n", "| policy_loss | 0.00547 |\n", "| std | 0.335 |\n", "| value_loss | 0.000353 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.63 |\n", "| ep_rew_mean | -0.195 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 32400 |\n", "| time_elapsed | 1497 |\n", "| total_timesteps | 648000 |\n", "| train/ | |\n", "| entropy_loss | -0.564 |\n", "| explained_variance | 0.848 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 32399 |\n", "| policy_loss | -0.00399 |\n", "| std | 0.334 |\n", "| value_loss | 0.000486 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.82 |\n", "| ep_rew_mean | -0.233 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 32500 |\n", "| time_elapsed | 1501 |\n", "| total_timesteps | 650000 |\n", "| train/ | |\n", "| entropy_loss | -0.586 |\n", "| explained_variance | 0.985 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 32499 |\n", "| policy_loss | 0.000189 |\n", "| std | 0.337 |\n", "| value_loss | 0.000254 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.77 |\n", "| ep_rew_mean | -0.212 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 32600 |\n", "| time_elapsed | 1506 |\n", "| total_timesteps | 652000 |\n", "| train/ | |\n", "| entropy_loss | -0.579 |\n", "| explained_variance | 0.943 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 32599 |\n", "| policy_loss | -0.00197 |\n", "| std | 0.337 |\n", "| value_loss | 0.000429 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.72 |\n", "| ep_rew_mean | -0.203 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 32700 |\n", "| time_elapsed | 1511 |\n", "| total_timesteps | 654000 |\n", "| train/ | |\n", "| entropy_loss | -0.563 |\n", "| explained_variance | 0.982 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 32699 |\n", "| policy_loss | 0.00398 |\n", "| std | 0.335 |\n", "| value_loss | 0.000116 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.75 |\n", "| ep_rew_mean | -0.208 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 32800 |\n", "| time_elapsed | 1516 |\n", "| total_timesteps | 656000 |\n", "| train/ | |\n", "| entropy_loss | -0.55 |\n", "| explained_variance | 0.963 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 32799 |\n", "| policy_loss | -0.0137 |\n", "| std | 0.334 |\n", "| value_loss | 0.000719 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.66 |\n", "| ep_rew_mean | -0.204 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 32900 |\n", "| time_elapsed | 1520 |\n", "| total_timesteps | 658000 |\n", "| train/ | |\n", "| entropy_loss | -0.531 |\n", "| explained_variance | 0.99 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 32899 |\n", "| policy_loss | -0.000716 |\n", "| std | 0.332 |\n", "| value_loss | 7.43e-05 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.72 |\n", "| ep_rew_mean | -0.212 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 33000 |\n", "| time_elapsed | 1525 |\n", "| total_timesteps | 660000 |\n", "| train/ | |\n", "| entropy_loss | -0.523 |\n", "| explained_variance | 0.993 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 32999 |\n", "| policy_loss | -0.00301 |\n", "| std | 0.332 |\n", "| value_loss | 4.99e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.7 |\n", "| ep_rew_mean | -0.214 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 33100 |\n", "| time_elapsed | 1530 |\n", "| total_timesteps | 662000 |\n", "| train/ | |\n", "| entropy_loss | -0.524 |\n", "| explained_variance | 0.978 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 33099 |\n", "| policy_loss | -0.00316 |\n", "| std | 0.332 |\n", "| value_loss | 7.77e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.66 |\n", "| ep_rew_mean | -0.199 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 33200 |\n", "| time_elapsed | 1535 |\n", "| total_timesteps | 664000 |\n", "| train/ | |\n", "| entropy_loss | -0.517 |\n", "| explained_variance | 0.915 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 33199 |\n", "| policy_loss | 0.0205 |\n", "| std | 0.332 |\n", "| value_loss | 0.000846 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.66 |\n", "| ep_rew_mean | -0.199 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 33300 |\n", "| time_elapsed | 1539 |\n", "| total_timesteps | 666000 |\n", "| train/ | |\n", "| entropy_loss | -0.507 |\n", "| explained_variance | 0.964 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 33299 |\n", "| policy_loss | -0.00035 |\n", "| std | 0.331 |\n", "| value_loss | 8.37e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.77 |\n", "| ep_rew_mean | -0.229 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 33400 |\n", "| time_elapsed | 1543 |\n", "| total_timesteps | 668000 |\n", "| train/ | |\n", "| entropy_loss | -0.492 |\n", "| explained_variance | 0.986 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 33399 |\n", "| policy_loss | 0.00185 |\n", "| std | 0.329 |\n", "| value_loss | 7.62e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.8 |\n", "| ep_rew_mean | -0.219 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 33500 |\n", "| time_elapsed | 1549 |\n", "| total_timesteps | 670000 |\n", "| train/ | |\n", "| entropy_loss | -0.485 |\n", "| explained_variance | 0.978 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 33499 |\n", "| policy_loss | -0.00321 |\n", "| std | 0.329 |\n", "| value_loss | 0.000134 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.68 |\n", "| ep_rew_mean | -0.202 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 33600 |\n", "| time_elapsed | 1553 |\n", "| total_timesteps | 672000 |\n", "| train/ | |\n", "| entropy_loss | -0.492 |\n", "| explained_variance | 0.976 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 33599 |\n", "| policy_loss | 0.00493 |\n", "| std | 0.33 |\n", "| value_loss | 0.000134 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.54 |\n", "| ep_rew_mean | -0.188 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 33700 |\n", "| time_elapsed | 1557 |\n", "| total_timesteps | 674000 |\n", "| train/ | |\n", "| entropy_loss | -0.479 |\n", "| explained_variance | 0.97 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 33699 |\n", "| policy_loss | 0.0015 |\n", "| std | 0.328 |\n", "| value_loss | 0.000174 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.62 |\n", "| ep_rew_mean | -0.197 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 33800 |\n", "| time_elapsed | 1563 |\n", "| total_timesteps | 676000 |\n", "| train/ | |\n", "| entropy_loss | -0.476 |\n", "| explained_variance | 0.993 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 33799 |\n", "| policy_loss | -0.00173 |\n", "| std | 0.328 |\n", "| value_loss | 5.85e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.63 |\n", "| ep_rew_mean | -0.2 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 33900 |\n", "| time_elapsed | 1567 |\n", "| total_timesteps | 678000 |\n", "| train/ | |\n", "| entropy_loss | -0.465 |\n", "| explained_variance | 0.986 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 33899 |\n", "| policy_loss | 0.015 |\n", "| std | 0.328 |\n", "| value_loss | 0.000321 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.7 |\n", "| ep_rew_mean | -0.212 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 34000 |\n", "| time_elapsed | 1572 |\n", "| total_timesteps | 680000 |\n", "| train/ | |\n", "| entropy_loss | -0.456 |\n", "| explained_variance | 0.977 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 33999 |\n", "| policy_loss | 0.00215 |\n", "| std | 0.328 |\n", "| value_loss | 9.97e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.73 |\n", "| ep_rew_mean | -0.208 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 34100 |\n", "| time_elapsed | 1576 |\n", "| total_timesteps | 682000 |\n", "| train/ | |\n", "| entropy_loss | -0.449 |\n", "| explained_variance | 0.957 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 34099 |\n", "| policy_loss | 0.000991 |\n", "| std | 0.327 |\n", "| value_loss | 0.00024 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.66 |\n", "| ep_rew_mean | -0.208 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 34200 |\n", "| time_elapsed | 1581 |\n", "| total_timesteps | 684000 |\n", "| train/ | |\n", "| entropy_loss | -0.445 |\n", "| explained_variance | 0.938 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 34199 |\n", "| policy_loss | 0.000525 |\n", "| std | 0.327 |\n", "| value_loss | 0.000207 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.58 |\n", "| ep_rew_mean | -0.19 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 34300 |\n", "| time_elapsed | 1586 |\n", "| total_timesteps | 686000 |\n", "| train/ | |\n", "| entropy_loss | -0.435 |\n", "| explained_variance | 0.98 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 34299 |\n", "| policy_loss | 0.00221 |\n", "| std | 0.326 |\n", "| value_loss | 0.000176 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.83 |\n", "| ep_rew_mean | -0.221 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 34400 |\n", "| time_elapsed | 1590 |\n", "| total_timesteps | 688000 |\n", "| train/ | |\n", "| entropy_loss | -0.414 |\n", "| explained_variance | 0.986 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 34399 |\n", "| policy_loss | 0.00251 |\n", "| std | 0.324 |\n", "| value_loss | 0.000225 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.78 |\n", "| ep_rew_mean | -0.213 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 34500 |\n", "| time_elapsed | 1595 |\n", "| total_timesteps | 690000 |\n", "| train/ | |\n", "| entropy_loss | -0.424 |\n", "| explained_variance | 0.992 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 34499 |\n", "| policy_loss | -0.00139 |\n", "| std | 0.326 |\n", "| value_loss | 4.68e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.76 |\n", "| ep_rew_mean | -0.217 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 34600 |\n", "| time_elapsed | 1600 |\n", "| total_timesteps | 692000 |\n", "| train/ | |\n", "| entropy_loss | -0.38 |\n", "| explained_variance | 0.987 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 34599 |\n", "| policy_loss | -6.2e-06 |\n", "| std | 0.322 |\n", "| value_loss | 0.000133 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.88 |\n", "| ep_rew_mean | -0.233 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 34700 |\n", "| time_elapsed | 1604 |\n", "| total_timesteps | 694000 |\n", "| train/ | |\n", "| entropy_loss | -0.389 |\n", "| explained_variance | 0.97 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 34699 |\n", "| policy_loss | -0.000427 |\n", "| std | 0.323 |\n", "| value_loss | 0.000172 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.66 |\n", "| ep_rew_mean | -0.21 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 34800 |\n", "| time_elapsed | 1609 |\n", "| total_timesteps | 696000 |\n", "| train/ | |\n", "| entropy_loss | -0.383 |\n", "| explained_variance | 0.968 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 34799 |\n", "| policy_loss | -0.000613 |\n", "| std | 0.323 |\n", "| value_loss | 0.000137 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.74 |\n", "| ep_rew_mean | -0.213 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 34900 |\n", "| time_elapsed | 1614 |\n", "| total_timesteps | 698000 |\n", "| train/ | |\n", "| entropy_loss | -0.386 |\n", "| explained_variance | 0.99 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 34899 |\n", "| policy_loss | -0.00306 |\n", "| std | 0.324 |\n", "| value_loss | 6.01e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.58 |\n", "| ep_rew_mean | -0.2 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 35000 |\n", "| time_elapsed | 1618 |\n", "| total_timesteps | 700000 |\n", "| train/ | |\n", "| entropy_loss | -0.395 |\n", "| explained_variance | 0.974 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 34999 |\n", "| policy_loss | 0.00447 |\n", "| std | 0.325 |\n", "| value_loss | 0.000156 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.85 |\n", "| ep_rew_mean | -0.226 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 35100 |\n", "| time_elapsed | 1623 |\n", "| total_timesteps | 702000 |\n", "| train/ | |\n", "| entropy_loss | -0.384 |\n", "| explained_variance | 0.986 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 35099 |\n", "| policy_loss | -0.000863 |\n", "| std | 0.324 |\n", "| value_loss | 8.63e-05 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.78 |\n", "| ep_rew_mean | -0.21 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 35200 |\n", "| time_elapsed | 1628 |\n", "| total_timesteps | 704000 |\n", "| train/ | |\n", "| entropy_loss | -0.383 |\n", "| explained_variance | 0.978 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 35199 |\n", "| policy_loss | -0.000694 |\n", "| std | 0.324 |\n", "| value_loss | 0.00017 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.73 |\n", "| ep_rew_mean | -0.208 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 35300 |\n", "| time_elapsed | 1632 |\n", "| total_timesteps | 706000 |\n", "| train/ | |\n", "| entropy_loss | -0.409 |\n", "| explained_variance | 0.982 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 35299 |\n", "| policy_loss | -0.00421 |\n", "| std | 0.328 |\n", "| value_loss | 0.000123 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.71 |\n", "| ep_rew_mean | -0.21 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 35400 |\n", "| time_elapsed | 1637 |\n", "| total_timesteps | 708000 |\n", "| train/ | |\n", "| entropy_loss | -0.4 |\n", "| explained_variance | 0.994 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 35399 |\n", "| policy_loss | -0.00492 |\n", "| std | 0.327 |\n", "| value_loss | 0.00011 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.75 |\n", "| ep_rew_mean | -0.213 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 35500 |\n", "| time_elapsed | 1642 |\n", "| total_timesteps | 710000 |\n", "| train/ | |\n", "| entropy_loss | -0.384 |\n", "| explained_variance | 0.985 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 35499 |\n", "| policy_loss | -0.00391 |\n", "| std | 0.327 |\n", "| value_loss | 0.000111 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.8 |\n", "| ep_rew_mean | -0.222 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 35600 |\n", "| time_elapsed | 1647 |\n", "| total_timesteps | 712000 |\n", "| train/ | |\n", "| entropy_loss | -0.362 |\n", "| explained_variance | 0.836 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 35599 |\n", "| policy_loss | -0.00558 |\n", "| std | 0.324 |\n", "| value_loss | 0.00128 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.67 |\n", "| ep_rew_mean | -0.209 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 35700 |\n", "| time_elapsed | 1651 |\n", "| total_timesteps | 714000 |\n", "| train/ | |\n", "| entropy_loss | -0.337 |\n", "| explained_variance | 0.976 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 35699 |\n", "| policy_loss | -0.00879 |\n", "| std | 0.32 |\n", "| value_loss | 0.000147 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.6 |\n", "| ep_rew_mean | -0.193 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 35800 |\n", "| time_elapsed | 1656 |\n", "| total_timesteps | 716000 |\n", "| train/ | |\n", "| entropy_loss | -0.325 |\n", "| explained_variance | 0.979 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 35799 |\n", "| policy_loss | -0.00435 |\n", "| std | 0.32 |\n", "| value_loss | 0.000204 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.83 |\n", "| ep_rew_mean | -0.222 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 35900 |\n", "| time_elapsed | 1661 |\n", "| total_timesteps | 718000 |\n", "| train/ | |\n", "| entropy_loss | -0.313 |\n", "| explained_variance | 0.939 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 35899 |\n", "| policy_loss | -0.00616 |\n", "| std | 0.32 |\n", "| value_loss | 0.00042 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.7 |\n", "| ep_rew_mean | -0.203 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 36000 |\n", "| time_elapsed | 1665 |\n", "| total_timesteps | 720000 |\n", "| train/ | |\n", "| entropy_loss | -0.297 |\n", "| explained_variance | 0.982 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 35999 |\n", "| policy_loss | -4.17e-05 |\n", "| std | 0.318 |\n", "| value_loss | 9.99e-05 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.63 |\n", "| ep_rew_mean | -0.21 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 36100 |\n", "| time_elapsed | 1669 |\n", "| total_timesteps | 722000 |\n", "| train/ | |\n", "| entropy_loss | -0.295 |\n", "| explained_variance | 0.973 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 36099 |\n", "| policy_loss | 0.00161 |\n", "| std | 0.318 |\n", "| value_loss | 5.94e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.68 |\n", "| ep_rew_mean | -0.211 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 36200 |\n", "| time_elapsed | 1675 |\n", "| total_timesteps | 724000 |\n", "| train/ | |\n", "| entropy_loss | -0.287 |\n", "| explained_variance | 0.954 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 36199 |\n", "| policy_loss | 0.00532 |\n", "| std | 0.318 |\n", "| value_loss | 0.000746 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.61 |\n", "| ep_rew_mean | -0.197 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 36300 |\n", "| time_elapsed | 1679 |\n", "| total_timesteps | 726000 |\n", "| train/ | |\n", "| entropy_loss | -0.277 |\n", "| explained_variance | 0.971 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 36299 |\n", "| policy_loss | -0.00285 |\n", "| std | 0.317 |\n", "| value_loss | 0.000281 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.67 |\n", "| ep_rew_mean | -0.205 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 36400 |\n", "| time_elapsed | 1684 |\n", "| total_timesteps | 728000 |\n", "| train/ | |\n", "| entropy_loss | -0.27 |\n", "| explained_variance | 0.981 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 36399 |\n", "| policy_loss | -0.0107 |\n", "| std | 0.317 |\n", "| value_loss | 0.000198 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.95 |\n", "| ep_rew_mean | -0.234 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 36500 |\n", "| time_elapsed | 1688 |\n", "| total_timesteps | 730000 |\n", "| train/ | |\n", "| entropy_loss | -0.263 |\n", "| explained_variance | 0.995 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 36499 |\n", "| policy_loss | -0.0041 |\n", "| std | 0.318 |\n", "| value_loss | 7.7e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.53 |\n", "| ep_rew_mean | -0.192 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 36600 |\n", "| time_elapsed | 1693 |\n", "| total_timesteps | 732000 |\n", "| train/ | |\n", "| entropy_loss | -0.283 |\n", "| explained_variance | 0.984 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 36599 |\n", "| policy_loss | -0.00161 |\n", "| std | 0.321 |\n", "| value_loss | 0.000171 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.63 |\n", "| ep_rew_mean | -0.197 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 36700 |\n", "| time_elapsed | 1698 |\n", "| total_timesteps | 734000 |\n", "| train/ | |\n", "| entropy_loss | -0.269 |\n", "| explained_variance | 0.957 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 36699 |\n", "| policy_loss | -0.0029 |\n", "| std | 0.319 |\n", "| value_loss | 0.00021 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.6 |\n", "| ep_rew_mean | -0.191 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 36800 |\n", "| time_elapsed | 1702 |\n", "| total_timesteps | 736000 |\n", "| train/ | |\n", "| entropy_loss | -0.249 |\n", "| explained_variance | 0.937 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 36799 |\n", "| policy_loss | -0.00525 |\n", "| std | 0.316 |\n", "| value_loss | 0.000259 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.72 |\n", "| ep_rew_mean | -0.209 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 36900 |\n", "| time_elapsed | 1707 |\n", "| total_timesteps | 738000 |\n", "| train/ | |\n", "| entropy_loss | -0.25 |\n", "| explained_variance | 0.985 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 36899 |\n", "| policy_loss | -0.00129 |\n", "| std | 0.317 |\n", "| value_loss | 0.00015 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.62 |\n", "| ep_rew_mean | -0.199 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 37000 |\n", "| time_elapsed | 1712 |\n", "| total_timesteps | 740000 |\n", "| train/ | |\n", "| entropy_loss | -0.238 |\n", "| explained_variance | 0.994 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 36999 |\n", "| policy_loss | -0.00078 |\n", "| std | 0.316 |\n", "| value_loss | 4.19e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.63 |\n", "| ep_rew_mean | -0.207 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 37100 |\n", "| time_elapsed | 1716 |\n", "| total_timesteps | 742000 |\n", "| train/ | |\n", "| entropy_loss | -0.223 |\n", "| explained_variance | 0.953 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 37099 |\n", "| policy_loss | 0.00142 |\n", "| std | 0.314 |\n", "| value_loss | 0.00027 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.72 |\n", "| ep_rew_mean | -0.207 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 37200 |\n", "| time_elapsed | 1721 |\n", "| total_timesteps | 744000 |\n", "| train/ | |\n", "| entropy_loss | -0.217 |\n", "| explained_variance | 0.978 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 37199 |\n", "| policy_loss | -0.00135 |\n", "| std | 0.314 |\n", "| value_loss | 0.000151 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.48 |\n", "| ep_rew_mean | -0.181 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 37300 |\n", "| time_elapsed | 1726 |\n", "| total_timesteps | 746000 |\n", "| train/ | |\n", "| entropy_loss | -0.201 |\n", "| explained_variance | 0.676 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 37299 |\n", "| policy_loss | -0.00338 |\n", "| std | 0.312 |\n", "| value_loss | 0.00381 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.73 |\n", "| ep_rew_mean | -0.215 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 37400 |\n", "| time_elapsed | 1730 |\n", "| total_timesteps | 748000 |\n", "| train/ | |\n", "| entropy_loss | -0.193 |\n", "| explained_variance | 0.973 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 37399 |\n", "| policy_loss | 0.00931 |\n", "| std | 0.311 |\n", "| value_loss | 0.000176 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.74 |\n", "| ep_rew_mean | -0.22 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 37500 |\n", "| time_elapsed | 1735 |\n", "| total_timesteps | 750000 |\n", "| train/ | |\n", "| entropy_loss | -0.199 |\n", "| explained_variance | 0.974 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 37499 |\n", "| policy_loss | 0.0011 |\n", "| std | 0.31 |\n", "| value_loss | 0.000109 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.68 |\n", "| ep_rew_mean | -0.206 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 37600 |\n", "| time_elapsed | 1739 |\n", "| total_timesteps | 752000 |\n", "| train/ | |\n", "| entropy_loss | -0.162 |\n", "| explained_variance | 0.987 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 37599 |\n", "| policy_loss | 2.12e-05 |\n", "| std | 0.307 |\n", "| value_loss | 9.62e-05 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.88 |\n", "| ep_rew_mean | -0.222 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 37700 |\n", "| time_elapsed | 1744 |\n", "| total_timesteps | 754000 |\n", "| train/ | |\n", "| entropy_loss | -0.16 |\n", "| explained_variance | 0.981 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 37699 |\n", "| policy_loss | -5.64e-05 |\n", "| std | 0.306 |\n", "| value_loss | 0.000347 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.68 |\n", "| ep_rew_mean | -0.207 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 37800 |\n", "| time_elapsed | 1749 |\n", "| total_timesteps | 756000 |\n", "| train/ | |\n", "| entropy_loss | -0.144 |\n", "| explained_variance | 0.993 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 37799 |\n", "| policy_loss | 0.00285 |\n", "| std | 0.304 |\n", "| value_loss | 6.19e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.58 |\n", "| ep_rew_mean | -0.187 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 37900 |\n", "| time_elapsed | 1754 |\n", "| total_timesteps | 758000 |\n", "| train/ | |\n", "| entropy_loss | -0.137 |\n", "| explained_variance | 0.957 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 37899 |\n", "| policy_loss | -0.00804 |\n", "| std | 0.303 |\n", "| value_loss | 0.000336 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.77 |\n", "| ep_rew_mean | -0.218 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 38000 |\n", "| time_elapsed | 1759 |\n", "| total_timesteps | 760000 |\n", "| train/ | |\n", "| entropy_loss | -0.142 |\n", "| explained_variance | 0.991 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 37999 |\n", "| policy_loss | 0.00262 |\n", "| std | 0.304 |\n", "| value_loss | 8.46e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.73 |\n", "| ep_rew_mean | -0.218 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 38100 |\n", "| time_elapsed | 1763 |\n", "| total_timesteps | 762000 |\n", "| train/ | |\n", "| entropy_loss | -0.136 |\n", "| explained_variance | 0.992 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 38099 |\n", "| policy_loss | 0.000756 |\n", "| std | 0.304 |\n", "| value_loss | 0.000203 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.52 |\n", "| ep_rew_mean | -0.187 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 38200 |\n", "| time_elapsed | 1768 |\n", "| total_timesteps | 764000 |\n", "| train/ | |\n", "| entropy_loss | -0.142 |\n", "| explained_variance | 0.96 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 38199 |\n", "| policy_loss | -0.00564 |\n", "| std | 0.306 |\n", "| value_loss | 0.000497 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.66 |\n", "| ep_rew_mean | -0.205 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 38300 |\n", "| time_elapsed | 1773 |\n", "| total_timesteps | 766000 |\n", "| train/ | |\n", "| entropy_loss | -0.137 |\n", "| explained_variance | 0.969 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 38299 |\n", "| policy_loss | 0.00346 |\n", "| std | 0.305 |\n", "| value_loss | 9.52e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.61 |\n", "| ep_rew_mean | -0.199 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 38400 |\n", "| time_elapsed | 1777 |\n", "| total_timesteps | 768000 |\n", "| train/ | |\n", "| entropy_loss | -0.121 |\n", "| explained_variance | 0.923 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 38399 |\n", "| policy_loss | -0.0125 |\n", "| std | 0.305 |\n", "| value_loss | 0.000241 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.75 |\n", "| ep_rew_mean | -0.215 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 432 |\n", "| iterations | 38500 |\n", "| time_elapsed | 1782 |\n", "| total_timesteps | 770000 |\n", "| train/ | |\n", "| entropy_loss | -0.121 |\n", "| explained_variance | 0.973 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 38499 |\n", "| policy_loss | -0.00281 |\n", "| std | 0.305 |\n", "| value_loss | 0.000117 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.76 |\n", "| ep_rew_mean | -0.211 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 38600 |\n", "| time_elapsed | 1787 |\n", "| total_timesteps | 772000 |\n", "| train/ | |\n", "| entropy_loss | -0.115 |\n", "| explained_variance | 0.973 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 38599 |\n", "| policy_loss | 0.00289 |\n", "| std | 0.305 |\n", "| value_loss | 0.000194 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.84 |\n", "| ep_rew_mean | -0.223 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 38700 |\n", "| time_elapsed | 1791 |\n", "| total_timesteps | 774000 |\n", "| train/ | |\n", "| entropy_loss | -0.0949 |\n", "| explained_variance | 0.901 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 38699 |\n", "| policy_loss | 0.0119 |\n", "| std | 0.303 |\n", "| value_loss | 0.000461 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.74 |\n", "| ep_rew_mean | -0.212 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 38800 |\n", "| time_elapsed | 1797 |\n", "| total_timesteps | 776000 |\n", "| train/ | |\n", "| entropy_loss | -0.0901 |\n", "| explained_variance | 0.961 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 38799 |\n", "| policy_loss | 0.00157 |\n", "| std | 0.304 |\n", "| value_loss | 0.00017 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.76 |\n", "| ep_rew_mean | -0.224 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 38900 |\n", "| time_elapsed | 1801 |\n", "| total_timesteps | 778000 |\n", "| train/ | |\n", "| entropy_loss | -0.0844 |\n", "| explained_variance | 0.985 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 38899 |\n", "| policy_loss | 0.00117 |\n", "| std | 0.302 |\n", "| value_loss | 6.44e-05 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.67 |\n", "| ep_rew_mean | -0.206 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 39000 |\n", "| time_elapsed | 1805 |\n", "| total_timesteps | 780000 |\n", "| train/ | |\n", "| entropy_loss | -0.0788 |\n", "| explained_variance | 0.989 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 38999 |\n", "| policy_loss | -6.98e-05 |\n", "| std | 0.302 |\n", "| value_loss | 0.000211 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.9 |\n", "| ep_rew_mean | -0.227 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 39100 |\n", "| time_elapsed | 1811 |\n", "| total_timesteps | 782000 |\n", "| train/ | |\n", "| entropy_loss | -0.08 |\n", "| explained_variance | 0.985 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 39099 |\n", "| policy_loss | -0.000166 |\n", "| std | 0.303 |\n", "| value_loss | 0.000202 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.64 |\n", "| ep_rew_mean | -0.204 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 39200 |\n", "| time_elapsed | 1815 |\n", "| total_timesteps | 784000 |\n", "| train/ | |\n", "| entropy_loss | -0.0742 |\n", "| explained_variance | 0.987 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 39199 |\n", "| policy_loss | -0.00467 |\n", "| std | 0.301 |\n", "| value_loss | 0.000102 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.53 |\n", "| ep_rew_mean | -0.195 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 39300 |\n", "| time_elapsed | 1820 |\n", "| total_timesteps | 786000 |\n", "| train/ | |\n", "| entropy_loss | -0.0851 |\n", "| explained_variance | 0.992 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 39299 |\n", "| policy_loss | 0.00121 |\n", "| std | 0.302 |\n", "| value_loss | 7.18e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.81 |\n", "| ep_rew_mean | -0.216 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 39400 |\n", "| time_elapsed | 1825 |\n", "| total_timesteps | 788000 |\n", "| train/ | |\n", "| entropy_loss | -0.0886 |\n", "| explained_variance | 0.9 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 39399 |\n", "| policy_loss | -0.00132 |\n", "| std | 0.303 |\n", "| value_loss | 0.000579 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.75 |\n", "| ep_rew_mean | -0.212 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 39500 |\n", "| time_elapsed | 1829 |\n", "| total_timesteps | 790000 |\n", "| train/ | |\n", "| entropy_loss | -0.078 |\n", "| explained_variance | 0.972 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 39499 |\n", "| policy_loss | 0.00142 |\n", "| std | 0.302 |\n", "| value_loss | 0.000153 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.67 |\n", "| ep_rew_mean | -0.201 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 39600 |\n", "| time_elapsed | 1834 |\n", "| total_timesteps | 792000 |\n", "| train/ | |\n", "| entropy_loss | -0.0758 |\n", "| explained_variance | 0.975 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 39599 |\n", "| policy_loss | 0.000636 |\n", "| std | 0.302 |\n", "| value_loss | 0.000133 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.63 |\n", "| ep_rew_mean | -0.198 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 39700 |\n", "| time_elapsed | 1839 |\n", "| total_timesteps | 794000 |\n", "| train/ | |\n", "| entropy_loss | -0.0713 |\n", "| explained_variance | 0.959 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 39699 |\n", "| policy_loss | -0.006 |\n", "| std | 0.302 |\n", "| value_loss | 0.000114 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.53 |\n", "| ep_rew_mean | -0.184 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 39800 |\n", "| time_elapsed | 1843 |\n", "| total_timesteps | 796000 |\n", "| train/ | |\n", "| entropy_loss | -0.0707 |\n", "| explained_variance | 0.99 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 39799 |\n", "| policy_loss | -0.00113 |\n", "| std | 0.304 |\n", "| value_loss | 7.64e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.69 |\n", "| ep_rew_mean | -0.204 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 39900 |\n", "| time_elapsed | 1848 |\n", "| total_timesteps | 798000 |\n", "| train/ | |\n", "| entropy_loss | -0.0602 |\n", "| explained_variance | 0.969 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 39899 |\n", "| policy_loss | 0.000165 |\n", "| std | 0.302 |\n", "| value_loss | 0.000191 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.72 |\n", "| ep_rew_mean | -0.212 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 40000 |\n", "| time_elapsed | 1853 |\n", "| total_timesteps | 800000 |\n", "| train/ | |\n", "| entropy_loss | -0.0523 |\n", "| explained_variance | 0.984 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 39999 |\n", "| policy_loss | -0.00046 |\n", "| std | 0.3 |\n", "| value_loss | 0.00017 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.96 |\n", "| ep_rew_mean | -0.242 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 40100 |\n", "| time_elapsed | 1858 |\n", "| total_timesteps | 802000 |\n", "| train/ | |\n", "| entropy_loss | -0.0559 |\n", "| explained_variance | 0.979 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 40099 |\n", "| policy_loss | -0.00452 |\n", "| std | 0.299 |\n", "| value_loss | 0.00024 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.84 |\n", "| ep_rew_mean | -0.216 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 40200 |\n", "| time_elapsed | 1862 |\n", "| total_timesteps | 804000 |\n", "| train/ | |\n", "| entropy_loss | -0.0533 |\n", "| explained_variance | 0.988 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 40199 |\n", "| policy_loss | -0.00149 |\n", "| std | 0.298 |\n", "| value_loss | 0.000114 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.62 |\n", "| ep_rew_mean | -0.206 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 40300 |\n", "| time_elapsed | 1867 |\n", "| total_timesteps | 806000 |\n", "| train/ | |\n", "| entropy_loss | -0.0458 |\n", "| explained_variance | 0.991 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 40299 |\n", "| policy_loss | -0.00234 |\n", "| std | 0.298 |\n", "| value_loss | 6.27e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.68 |\n", "| ep_rew_mean | -0.21 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 40400 |\n", "| time_elapsed | 1872 |\n", "| total_timesteps | 808000 |\n", "| train/ | |\n", "| entropy_loss | -0.0388 |\n", "| explained_variance | 0.988 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 40399 |\n", "| policy_loss | 0.00289 |\n", "| std | 0.297 |\n", "| value_loss | 7.65e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.69 |\n", "| ep_rew_mean | -0.208 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 40500 |\n", "| time_elapsed | 1876 |\n", "| total_timesteps | 810000 |\n", "| train/ | |\n", "| entropy_loss | -0.0211 |\n", "| explained_variance | 0.933 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 40499 |\n", "| policy_loss | -0.00744 |\n", "| std | 0.296 |\n", "| value_loss | 0.000777 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.87 |\n", "| ep_rew_mean | -0.224 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 40600 |\n", "| time_elapsed | 1881 |\n", "| total_timesteps | 812000 |\n", "| train/ | |\n", "| entropy_loss | -0.0439 |\n", "| explained_variance | 0.979 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 40599 |\n", "| policy_loss | 0.00407 |\n", "| std | 0.297 |\n", "| value_loss | 0.000189 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.87 |\n", "| ep_rew_mean | -0.232 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 40700 |\n", "| time_elapsed | 1886 |\n", "| total_timesteps | 814000 |\n", "| train/ | |\n", "| entropy_loss | -0.0377 |\n", "| explained_variance | 0.99 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 40699 |\n", "| policy_loss | -0.00251 |\n", "| std | 0.298 |\n", "| value_loss | 4.84e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.67 |\n", "| ep_rew_mean | -0.21 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 40800 |\n", "| time_elapsed | 1890 |\n", "| total_timesteps | 816000 |\n", "| train/ | |\n", "| entropy_loss | -0.0309 |\n", "| explained_variance | 0.941 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 40799 |\n", "| policy_loss | 0.00653 |\n", "| std | 0.297 |\n", "| value_loss | 0.000218 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.59 |\n", "| ep_rew_mean | -0.194 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 40900 |\n", "| time_elapsed | 1896 |\n", "| total_timesteps | 818000 |\n", "| train/ | |\n", "| entropy_loss | -0.0147 |\n", "| explained_variance | 0.985 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 40899 |\n", "| policy_loss | 0.00103 |\n", "| std | 0.295 |\n", "| value_loss | 0.000268 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.63 |\n", "| ep_rew_mean | -0.198 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 41000 |\n", "| time_elapsed | 1900 |\n", "| total_timesteps | 820000 |\n", "| train/ | |\n", "| entropy_loss | -0.0126 |\n", "| explained_variance | 0.99 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 40999 |\n", "| policy_loss | -0.000645 |\n", "| std | 0.294 |\n", "| value_loss | 4.97e-05 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.88 |\n", "| ep_rew_mean | -0.228 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 41100 |\n", "| time_elapsed | 1904 |\n", "| total_timesteps | 822000 |\n", "| train/ | |\n", "| entropy_loss | -0.00199 |\n", "| explained_variance | 0.985 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 41099 |\n", "| policy_loss | 0.00323 |\n", "| std | 0.295 |\n", "| value_loss | 6.24e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.65 |\n", "| ep_rew_mean | -0.197 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 41200 |\n", "| time_elapsed | 1910 |\n", "| total_timesteps | 824000 |\n", "| train/ | |\n", "| entropy_loss | -0.0141 |\n", "| explained_variance | 0.955 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 41199 |\n", "| policy_loss | 0.00799 |\n", "| std | 0.295 |\n", "| value_loss | 0.000309 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.84 |\n", "| ep_rew_mean | -0.226 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 41300 |\n", "| time_elapsed | 1914 |\n", "| total_timesteps | 826000 |\n", "| train/ | |\n", "| entropy_loss | -0.00763 |\n", "| explained_variance | 0.975 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 41299 |\n", "| policy_loss | 0.0034 |\n", "| std | 0.295 |\n", "| value_loss | 0.000362 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.7 |\n", "| ep_rew_mean | -0.206 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 41400 |\n", "| time_elapsed | 1919 |\n", "| total_timesteps | 828000 |\n", "| train/ | |\n", "| entropy_loss | -0.017 |\n", "| explained_variance | 0.989 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 41399 |\n", "| policy_loss | 0.00027 |\n", "| std | 0.297 |\n", "| value_loss | 8.56e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.77 |\n", "| ep_rew_mean | -0.223 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 41500 |\n", "| time_elapsed | 1924 |\n", "| total_timesteps | 830000 |\n", "| train/ | |\n", "| entropy_loss | -0.0098 |\n", "| explained_variance | 0.989 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 41499 |\n", "| policy_loss | -0.00947 |\n", "| std | 0.297 |\n", "| value_loss | 0.000184 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.82 |\n", "| ep_rew_mean | -0.219 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 41600 |\n", "| time_elapsed | 1928 |\n", "| total_timesteps | 832000 |\n", "| train/ | |\n", "| entropy_loss | -0.00994 |\n", "| explained_variance | 0.965 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 41599 |\n", "| policy_loss | 0.000307 |\n", "| std | 0.298 |\n", "| value_loss | 0.00035 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.69 |\n", "| ep_rew_mean | -0.219 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 41700 |\n", "| time_elapsed | 1933 |\n", "| total_timesteps | 834000 |\n", "| train/ | |\n", "| entropy_loss | -0.00696 |\n", "| explained_variance | 0.981 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 41699 |\n", "| policy_loss | -0.00288 |\n", "| std | 0.298 |\n", "| value_loss | 0.0002 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.82 |\n", "| ep_rew_mean | -0.219 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 41800 |\n", "| time_elapsed | 1938 |\n", "| total_timesteps | 836000 |\n", "| train/ | |\n", "| entropy_loss | -0.00667 |\n", "| explained_variance | 0.977 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 41799 |\n", "| policy_loss | 0.00145 |\n", "| std | 0.299 |\n", "| value_loss | 0.000393 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.79 |\n", "| ep_rew_mean | -0.225 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 41900 |\n", "| time_elapsed | 1942 |\n", "| total_timesteps | 838000 |\n", "| train/ | |\n", "| entropy_loss | 0.00995 |\n", "| explained_variance | 0.987 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 41899 |\n", "| policy_loss | -0.000929 |\n", "| std | 0.298 |\n", "| value_loss | 0.000247 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.88 |\n", "| ep_rew_mean | -0.222 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 42000 |\n", "| time_elapsed | 1947 |\n", "| total_timesteps | 840000 |\n", "| train/ | |\n", "| entropy_loss | 0.0191 |\n", "| explained_variance | 0.982 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 41999 |\n", "| policy_loss | 0.00255 |\n", "| std | 0.297 |\n", "| value_loss | 0.000244 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.72 |\n", "| ep_rew_mean | -0.221 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 42100 |\n", "| time_elapsed | 1952 |\n", "| total_timesteps | 842000 |\n", "| train/ | |\n", "| entropy_loss | 0.0123 |\n", "| explained_variance | 0.984 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 42099 |\n", "| policy_loss | 0.00233 |\n", "| std | 0.299 |\n", "| value_loss | 0.000316 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.7 |\n", "| ep_rew_mean | -0.214 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 42200 |\n", "| time_elapsed | 1956 |\n", "| total_timesteps | 844000 |\n", "| train/ | |\n", "| entropy_loss | 0.0242 |\n", "| explained_variance | 0.992 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 42199 |\n", "| policy_loss | 0.00258 |\n", "| std | 0.298 |\n", "| value_loss | 9.24e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.69 |\n", "| ep_rew_mean | -0.207 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 42300 |\n", "| time_elapsed | 1961 |\n", "| total_timesteps | 846000 |\n", "| train/ | |\n", "| entropy_loss | 0.00287 |\n", "| explained_variance | 0.917 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 42299 |\n", "| policy_loss | 0.00202 |\n", "| std | 0.301 |\n", "| value_loss | 0.00065 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.84 |\n", "| ep_rew_mean | -0.231 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 42400 |\n", "| time_elapsed | 1966 |\n", "| total_timesteps | 848000 |\n", "| train/ | |\n", "| entropy_loss | 0.0132 |\n", "| explained_variance | 0.993 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 42399 |\n", "| policy_loss | 0.00434 |\n", "| std | 0.3 |\n", "| value_loss | 0.000254 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.75 |\n", "| ep_rew_mean | -0.21 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 42500 |\n", "| time_elapsed | 1971 |\n", "| total_timesteps | 850000 |\n", "| train/ | |\n", "| entropy_loss | 0.0136 |\n", "| explained_variance | 0.981 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 42499 |\n", "| policy_loss | 0.00203 |\n", "| std | 0.299 |\n", "| value_loss | 0.000179 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.65 |\n", "| ep_rew_mean | -0.21 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 42600 |\n", "| time_elapsed | 1975 |\n", "| total_timesteps | 852000 |\n", "| train/ | |\n", "| entropy_loss | 0.043 |\n", "| explained_variance | 0.985 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 42599 |\n", "| policy_loss | -0.000721 |\n", "| std | 0.297 |\n", "| value_loss | 0.000181 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.78 |\n", "| ep_rew_mean | -0.222 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 42700 |\n", "| time_elapsed | 1980 |\n", "| total_timesteps | 854000 |\n", "| train/ | |\n", "| entropy_loss | 0.0457 |\n", "| explained_variance | 0.982 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 42699 |\n", "| policy_loss | 0.000374 |\n", "| std | 0.296 |\n", "| value_loss | 0.000111 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.8 |\n", "| ep_rew_mean | -0.224 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 42800 |\n", "| time_elapsed | 1985 |\n", "| total_timesteps | 856000 |\n", "| train/ | |\n", "| entropy_loss | 0.0415 |\n", "| explained_variance | 0.97 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 42799 |\n", "| policy_loss | -0.00211 |\n", "| std | 0.297 |\n", "| value_loss | 0.00011 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.71 |\n", "| ep_rew_mean | -0.214 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 42900 |\n", "| time_elapsed | 1989 |\n", "| total_timesteps | 858000 |\n", "| train/ | |\n", "| entropy_loss | 0.0685 |\n", "| explained_variance | 0.98 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 42899 |\n", "| policy_loss | 0.00544 |\n", "| std | 0.295 |\n", "| value_loss | 0.000185 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.62 |\n", "| ep_rew_mean | -0.204 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 43000 |\n", "| time_elapsed | 1994 |\n", "| total_timesteps | 860000 |\n", "| train/ | |\n", "| entropy_loss | 0.0614 |\n", "| explained_variance | 0.991 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 42999 |\n", "| policy_loss | -0.00196 |\n", "| std | 0.296 |\n", "| value_loss | 0.000111 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.71 |\n", "| ep_rew_mean | -0.211 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 43100 |\n", "| time_elapsed | 1999 |\n", "| total_timesteps | 862000 |\n", "| train/ | |\n", "| entropy_loss | 0.0608 |\n", "| explained_variance | 0.98 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 43099 |\n", "| policy_loss | -0.000274 |\n", "| std | 0.297 |\n", "| value_loss | 0.000109 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.6 |\n", "| ep_rew_mean | -0.199 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 43200 |\n", "| time_elapsed | 2003 |\n", "| total_timesteps | 864000 |\n", "| train/ | |\n", "| entropy_loss | 0.059 |\n", "| explained_variance | 0.963 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 43199 |\n", "| policy_loss | 0.0027 |\n", "| std | 0.297 |\n", "| value_loss | 0.000145 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.78 |\n", "| ep_rew_mean | -0.223 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 43300 |\n", "| time_elapsed | 2009 |\n", "| total_timesteps | 866000 |\n", "| train/ | |\n", "| entropy_loss | 0.0647 |\n", "| explained_variance | 0.847 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 43299 |\n", "| policy_loss | -0.0152 |\n", "| std | 0.296 |\n", "| value_loss | 0.00104 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.77 |\n", "| ep_rew_mean | -0.216 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 43400 |\n", "| time_elapsed | 2013 |\n", "| total_timesteps | 868000 |\n", "| train/ | |\n", "| entropy_loss | 0.0753 |\n", "| explained_variance | 0.99 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 43399 |\n", "| policy_loss | 0.00271 |\n", "| std | 0.296 |\n", "| value_loss | 0.000114 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.75 |\n", "| ep_rew_mean | -0.215 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 43500 |\n", "| time_elapsed | 2017 |\n", "| total_timesteps | 870000 |\n", "| train/ | |\n", "| entropy_loss | 0.0826 |\n", "| explained_variance | 0.974 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 43499 |\n", "| policy_loss | -0.0151 |\n", "| std | 0.295 |\n", "| value_loss | 0.000924 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.73 |\n", "| ep_rew_mean | -0.211 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 43600 |\n", "| time_elapsed | 2023 |\n", "| total_timesteps | 872000 |\n", "| train/ | |\n", "| entropy_loss | 0.0827 |\n", "| explained_variance | 0.26 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 43599 |\n", "| policy_loss | -0.0236 |\n", "| std | 0.296 |\n", "| value_loss | 0.011 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.2 |\n", "| ep_rew_mean | -0.259 |\n", "| success_rate | 0.99 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 43700 |\n", "| time_elapsed | 2027 |\n", "| total_timesteps | 874000 |\n", "| train/ | |\n", "| entropy_loss | 0.0865 |\n", "| explained_variance | 0.953 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 43699 |\n", "| policy_loss | 0.044 |\n", "| std | 0.294 |\n", "| value_loss | 0.0317 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.92 |\n", "| ep_rew_mean | -0.316 |\n", "| success_rate | 0.98 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 43800 |\n", "| time_elapsed | 2032 |\n", "| total_timesteps | 876000 |\n", "| train/ | |\n", "| entropy_loss | 0.0722 |\n", "| explained_variance | 0.983 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 43799 |\n", "| policy_loss | -0.00279 |\n", "| std | 0.298 |\n", "| value_loss | 0.0689 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 7.7 |\n", "| ep_rew_mean | -0.873 |\n", "| success_rate | 0.9 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 43900 |\n", "| time_elapsed | 2037 |\n", "| total_timesteps | 878000 |\n", "| train/ | |\n", "| entropy_loss | 0.0952 |\n", "| explained_variance | 0.677 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 43899 |\n", "| policy_loss | 0.0767 |\n", "| std | 0.294 |\n", "| value_loss | 0.613 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 6.14 |\n", "| ep_rew_mean | -0.695 |\n", "| success_rate | 0.94 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 44000 |\n", "| time_elapsed | 2042 |\n", "| total_timesteps | 880000 |\n", "| train/ | |\n", "| entropy_loss | 0.0858 |\n", "| explained_variance | 0.962 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 43999 |\n", "| policy_loss | -0.264 |\n", "| std | 0.295 |\n", "| value_loss | 0.334 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.7 |\n", "| ep_rew_mean | -0.311 |\n", "| success_rate | 0.99 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 44100 |\n", "| time_elapsed | 2047 |\n", "| total_timesteps | 882000 |\n", "| train/ | |\n", "| entropy_loss | 0.0944 |\n", "| explained_variance | 0.972 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 44099 |\n", "| policy_loss | -0.0473 |\n", "| std | 0.295 |\n", "| value_loss | 0.0931 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 4.35 |\n", "| ep_rew_mean | -0.384 |\n", "| success_rate | 0.98 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 44200 |\n", "| time_elapsed | 2052 |\n", "| total_timesteps | 884000 |\n", "| train/ | |\n", "| entropy_loss | 0.0921 |\n", "| explained_variance | 0.74 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 44199 |\n", "| policy_loss | -0.00837 |\n", "| std | 0.295 |\n", "| value_loss | 0.142 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.01 |\n", "| ep_rew_mean | -0.249 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 44300 |\n", "| time_elapsed | 2056 |\n", "| total_timesteps | 886000 |\n", "| train/ | |\n", "| entropy_loss | 0.0893 |\n", "| explained_variance | 0.984 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 44299 |\n", "| policy_loss | -0.0354 |\n", "| std | 0.295 |\n", "| value_loss | 0.0202 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.88 |\n", "| ep_rew_mean | -0.303 |\n", "| success_rate | 0.99 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 44400 |\n", "| time_elapsed | 2061 |\n", "| total_timesteps | 888000 |\n", "| train/ | |\n", "| entropy_loss | 0.112 |\n", "| explained_variance | 0.686 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 44399 |\n", "| policy_loss | 0.0258 |\n", "| std | 0.293 |\n", "| value_loss | 0.0179 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.38 |\n", "| ep_rew_mean | -0.263 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 44500 |\n", "| time_elapsed | 2066 |\n", "| total_timesteps | 890000 |\n", "| train/ | |\n", "| entropy_loss | 0.125 |\n", "| explained_variance | 0.861 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 44499 |\n", "| policy_loss | -0.0423 |\n", "| std | 0.292 |\n", "| value_loss | 0.0166 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.76 |\n", "| ep_rew_mean | -0.298 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 44600 |\n", "| time_elapsed | 2071 |\n", "| total_timesteps | 892000 |\n", "| train/ | |\n", "| entropy_loss | 0.132 |\n", "| explained_variance | 0.667 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 44599 |\n", "| policy_loss | 0.0781 |\n", "| std | 0.292 |\n", "| value_loss | 0.0204 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.05 |\n", "| ep_rew_mean | -0.238 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 44700 |\n", "| time_elapsed | 2075 |\n", "| total_timesteps | 894000 |\n", "| train/ | |\n", "| entropy_loss | 0.118 |\n", "| explained_variance | 0.93 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 44699 |\n", "| policy_loss | -0.0327 |\n", "| std | 0.292 |\n", "| value_loss | 0.00521 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.72 |\n", "| ep_rew_mean | -0.209 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 44800 |\n", "| time_elapsed | 2080 |\n", "| total_timesteps | 896000 |\n", "| train/ | |\n", "| entropy_loss | 0.126 |\n", "| explained_variance | 0.81 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 44799 |\n", "| policy_loss | -0.00388 |\n", "| std | 0.29 |\n", "| value_loss | 0.00396 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.87 |\n", "| ep_rew_mean | -0.231 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 44900 |\n", "| time_elapsed | 2085 |\n", "| total_timesteps | 898000 |\n", "| train/ | |\n", "| entropy_loss | 0.124 |\n", "| explained_variance | 0.881 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 44899 |\n", "| policy_loss | 0.00545 |\n", "| std | 0.291 |\n", "| value_loss | 0.00169 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.79 |\n", "| ep_rew_mean | -0.206 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 45000 |\n", "| time_elapsed | 2089 |\n", "| total_timesteps | 900000 |\n", "| train/ | |\n", "| entropy_loss | 0.134 |\n", "| explained_variance | 0.708 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 44999 |\n", "| policy_loss | -0.00069 |\n", "| std | 0.29 |\n", "| value_loss | 0.00144 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.92 |\n", "| ep_rew_mean | -0.236 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 45100 |\n", "| time_elapsed | 2094 |\n", "| total_timesteps | 902000 |\n", "| train/ | |\n", "| entropy_loss | 0.124 |\n", "| explained_variance | -0.156 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 45099 |\n", "| policy_loss | 0.00418 |\n", "| std | 0.291 |\n", "| value_loss | 0.0124 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.79 |\n", "| ep_rew_mean | -0.22 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 45200 |\n", "| time_elapsed | 2099 |\n", "| total_timesteps | 904000 |\n", "| train/ | |\n", "| entropy_loss | 0.107 |\n", "| explained_variance | 0.964 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 45199 |\n", "| policy_loss | 0.0138 |\n", "| std | 0.294 |\n", "| value_loss | 0.00118 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.76 |\n", "| ep_rew_mean | -0.223 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 45300 |\n", "| time_elapsed | 2103 |\n", "| total_timesteps | 906000 |\n", "| train/ | |\n", "| entropy_loss | 0.123 |\n", "| explained_variance | 0.94 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 45299 |\n", "| policy_loss | -0.00253 |\n", "| std | 0.293 |\n", "| value_loss | 0.000529 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.73 |\n", "| ep_rew_mean | -0.217 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 45400 |\n", "| time_elapsed | 2108 |\n", "| total_timesteps | 908000 |\n", "| train/ | |\n", "| entropy_loss | 0.13 |\n", "| explained_variance | 0.971 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 45399 |\n", "| policy_loss | 0.000636 |\n", "| std | 0.292 |\n", "| value_loss | 0.000271 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.85 |\n", "| ep_rew_mean | -0.224 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 45500 |\n", "| time_elapsed | 2112 |\n", "| total_timesteps | 910000 |\n", "| train/ | |\n", "| entropy_loss | 0.137 |\n", "| explained_variance | 0.821 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 45499 |\n", "| policy_loss | -0.0049 |\n", "| std | 0.291 |\n", "| value_loss | 0.000673 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.65 |\n", "| ep_rew_mean | -0.209 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 45600 |\n", "| time_elapsed | 2117 |\n", "| total_timesteps | 912000 |\n", "| train/ | |\n", "| entropy_loss | 0.135 |\n", "| explained_variance | 0.947 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 45599 |\n", "| policy_loss | -0.00691 |\n", "| std | 0.293 |\n", "| value_loss | 0.000382 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.9 |\n", "| ep_rew_mean | -0.23 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 45700 |\n", "| time_elapsed | 2122 |\n", "| total_timesteps | 914000 |\n", "| train/ | |\n", "| entropy_loss | 0.128 |\n", "| explained_variance | 0.843 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 45699 |\n", "| policy_loss | 0.00573 |\n", "| std | 0.295 |\n", "| value_loss | 0.0011 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 4.36 |\n", "| ep_rew_mean | -0.357 |\n", "| success_rate | 0.98 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 45800 |\n", "| time_elapsed | 2126 |\n", "| total_timesteps | 916000 |\n", "| train/ | |\n", "| entropy_loss | 0.11 |\n", "| explained_variance | 0.697 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 45799 |\n", "| policy_loss | 0.00483 |\n", "| std | 0.297 |\n", "| value_loss | 0.162 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.99 |\n", "| ep_rew_mean | -0.236 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 45900 |\n", "| time_elapsed | 2130 |\n", "| total_timesteps | 918000 |\n", "| train/ | |\n", "| entropy_loss | 0.126 |\n", "| explained_variance | 0.549 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 45899 |\n", "| policy_loss | 0.0494 |\n", "| std | 0.296 |\n", "| value_loss | 0.00966 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.76 |\n", "| ep_rew_mean | -0.217 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 46000 |\n", "| time_elapsed | 2136 |\n", "| total_timesteps | 920000 |\n", "| train/ | |\n", "| entropy_loss | 0.153 |\n", "| explained_variance | 0.359 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 45999 |\n", "| policy_loss | -0.0359 |\n", "| std | 0.291 |\n", "| value_loss | 0.0175 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.85 |\n", "| ep_rew_mean | -0.235 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 46100 |\n", "| time_elapsed | 2140 |\n", "| total_timesteps | 922000 |\n", "| train/ | |\n", "| entropy_loss | 0.174 |\n", "| explained_variance | 0.976 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 46099 |\n", "| policy_loss | 0.00131 |\n", "| std | 0.289 |\n", "| value_loss | 0.000308 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.9 |\n", "| ep_rew_mean | -0.231 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 46200 |\n", "| time_elapsed | 2145 |\n", "| total_timesteps | 924000 |\n", "| train/ | |\n", "| entropy_loss | 0.179 |\n", "| explained_variance | 0.98 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 46199 |\n", "| policy_loss | 0.0021 |\n", "| std | 0.289 |\n", "| value_loss | 0.000484 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.76 |\n", "| ep_rew_mean | -0.215 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 46300 |\n", "| time_elapsed | 2149 |\n", "| total_timesteps | 926000 |\n", "| train/ | |\n", "| entropy_loss | 0.171 |\n", "| explained_variance | 0.935 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 46299 |\n", "| policy_loss | -0.00663 |\n", "| std | 0.289 |\n", "| value_loss | 0.000502 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.95 |\n", "| ep_rew_mean | -0.226 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 46400 |\n", "| time_elapsed | 2153 |\n", "| total_timesteps | 928000 |\n", "| train/ | |\n", "| entropy_loss | 0.174 |\n", "| explained_variance | 0.88 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 46399 |\n", "| policy_loss | -0.00226 |\n", "| std | 0.289 |\n", "| value_loss | 0.000994 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.88 |\n", "| ep_rew_mean | -0.229 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 46500 |\n", "| time_elapsed | 2159 |\n", "| total_timesteps | 930000 |\n", "| train/ | |\n", "| entropy_loss | 0.189 |\n", "| explained_variance | 0.95 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 46499 |\n", "| policy_loss | 0.00652 |\n", "| std | 0.288 |\n", "| value_loss | 0.000753 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.82 |\n", "| ep_rew_mean | -0.222 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 46600 |\n", "| time_elapsed | 2163 |\n", "| total_timesteps | 932000 |\n", "| train/ | |\n", "| entropy_loss | 0.187 |\n", "| explained_variance | 0.973 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 46599 |\n", "| policy_loss | -0.000167 |\n", "| std | 0.288 |\n", "| value_loss | 0.000407 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.58 |\n", "| ep_rew_mean | -0.2 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 46700 |\n", "| time_elapsed | 2167 |\n", "| total_timesteps | 934000 |\n", "| train/ | |\n", "| entropy_loss | 0.197 |\n", "| explained_variance | 0.961 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 46699 |\n", "| policy_loss | 0.00134 |\n", "| std | 0.288 |\n", "| value_loss | 0.000247 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.65 |\n", "| ep_rew_mean | -0.203 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 46800 |\n", "| time_elapsed | 2172 |\n", "| total_timesteps | 936000 |\n", "| train/ | |\n", "| entropy_loss | 0.189 |\n", "| explained_variance | 0.981 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 46799 |\n", "| policy_loss | 0.00329 |\n", "| std | 0.287 |\n", "| value_loss | 0.000143 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.67 |\n", "| ep_rew_mean | -0.21 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 46900 |\n", "| time_elapsed | 2177 |\n", "| total_timesteps | 938000 |\n", "| train/ | |\n", "| entropy_loss | 0.162 |\n", "| explained_variance | 0.969 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 46899 |\n", "| policy_loss | 0.00736 |\n", "| std | 0.289 |\n", "| value_loss | 0.000403 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.9 |\n", "| ep_rew_mean | -0.235 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 47000 |\n", "| time_elapsed | 2181 |\n", "| total_timesteps | 940000 |\n", "| train/ | |\n", "| entropy_loss | 0.14 |\n", "| explained_variance | 0.979 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 46999 |\n", "| policy_loss | 0.00254 |\n", "| std | 0.291 |\n", "| value_loss | 0.000671 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.8 |\n", "| ep_rew_mean | -0.214 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 47100 |\n", "| time_elapsed | 2186 |\n", "| total_timesteps | 942000 |\n", "| train/ | |\n", "| entropy_loss | 0.134 |\n", "| explained_variance | 0.957 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 47099 |\n", "| policy_loss | 0.00529 |\n", "| std | 0.292 |\n", "| value_loss | 0.000521 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.69 |\n", "| ep_rew_mean | -0.21 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 47200 |\n", "| time_elapsed | 2190 |\n", "| total_timesteps | 944000 |\n", "| train/ | |\n", "| entropy_loss | 0.13 |\n", "| explained_variance | 0.981 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 47199 |\n", "| policy_loss | 0.00473 |\n", "| std | 0.293 |\n", "| value_loss | 0.000239 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.84 |\n", "| ep_rew_mean | -0.228 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 47300 |\n", "| time_elapsed | 2196 |\n", "| total_timesteps | 946000 |\n", "| train/ | |\n", "| entropy_loss | 0.133 |\n", "| explained_variance | 0.903 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 47299 |\n", "| policy_loss | 0.00475 |\n", "| std | 0.293 |\n", "| value_loss | 0.00113 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.75 |\n", "| ep_rew_mean | -0.223 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 47400 |\n", "| time_elapsed | 2200 |\n", "| total_timesteps | 948000 |\n", "| train/ | |\n", "| entropy_loss | 0.157 |\n", "| explained_variance | 0.981 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 47399 |\n", "| policy_loss | -0.00218 |\n", "| std | 0.292 |\n", "| value_loss | 0.000145 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.81 |\n", "| ep_rew_mean | -0.226 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 47500 |\n", "| time_elapsed | 2204 |\n", "| total_timesteps | 950000 |\n", "| train/ | |\n", "| entropy_loss | 0.148 |\n", "| explained_variance | 0.923 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 47499 |\n", "| policy_loss | -0.00192 |\n", "| std | 0.293 |\n", "| value_loss | 0.000924 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.67 |\n", "| ep_rew_mean | -0.214 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 47600 |\n", "| time_elapsed | 2209 |\n", "| total_timesteps | 952000 |\n", "| train/ | |\n", "| entropy_loss | 0.127 |\n", "| explained_variance | 0.93 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 47599 |\n", "| policy_loss | 0.00363 |\n", "| std | 0.293 |\n", "| value_loss | 0.000483 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.8 |\n", "| ep_rew_mean | -0.228 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 47700 |\n", "| time_elapsed | 2214 |\n", "| total_timesteps | 954000 |\n", "| train/ | |\n", "| entropy_loss | 0.139 |\n", "| explained_variance | 0.981 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 47699 |\n", "| policy_loss | 0.00182 |\n", "| std | 0.291 |\n", "| value_loss | 0.000306 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.67 |\n", "| ep_rew_mean | -0.198 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 47800 |\n", "| time_elapsed | 2218 |\n", "| total_timesteps | 956000 |\n", "| train/ | |\n", "| entropy_loss | 0.146 |\n", "| explained_variance | 0.989 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 47799 |\n", "| policy_loss | 0.00453 |\n", "| std | 0.291 |\n", "| value_loss | 0.000711 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.79 |\n", "| ep_rew_mean | -0.22 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 47900 |\n", "| time_elapsed | 2223 |\n", "| total_timesteps | 958000 |\n", "| train/ | |\n", "| entropy_loss | 0.161 |\n", "| explained_variance | 0.957 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 47899 |\n", "| policy_loss | 0.00263 |\n", "| std | 0.289 |\n", "| value_loss | 0.00046 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.76 |\n", "| ep_rew_mean | -0.214 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 48000 |\n", "| time_elapsed | 2227 |\n", "| total_timesteps | 960000 |\n", "| train/ | |\n", "| entropy_loss | 0.169 |\n", "| explained_variance | 0.993 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 47999 |\n", "| policy_loss | -0.00215 |\n", "| std | 0.288 |\n", "| value_loss | 0.000104 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.59 |\n", "| ep_rew_mean | -0.196 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 48100 |\n", "| time_elapsed | 2232 |\n", "| total_timesteps | 962000 |\n", "| train/ | |\n", "| entropy_loss | 0.175 |\n", "| explained_variance | 0.959 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 48099 |\n", "| policy_loss | 0.00838 |\n", "| std | 0.287 |\n", "| value_loss | 0.000503 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.62 |\n", "| ep_rew_mean | -0.201 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 48200 |\n", "| time_elapsed | 2237 |\n", "| total_timesteps | 964000 |\n", "| train/ | |\n", "| entropy_loss | 0.163 |\n", "| explained_variance | 0.986 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 48199 |\n", "| policy_loss | -0.0016 |\n", "| std | 0.289 |\n", "| value_loss | 0.000108 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.77 |\n", "| ep_rew_mean | -0.217 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 48300 |\n", "| time_elapsed | 2241 |\n", "| total_timesteps | 966000 |\n", "| train/ | |\n", "| entropy_loss | 0.167 |\n", "| explained_variance | 0.979 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 48299 |\n", "| policy_loss | -0.00101 |\n", "| std | 0.287 |\n", "| value_loss | 9.53e-05 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.86 |\n", "| ep_rew_mean | -0.233 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 48400 |\n", "| time_elapsed | 2246 |\n", "| total_timesteps | 968000 |\n", "| train/ | |\n", "| entropy_loss | 0.17 |\n", "| explained_variance | 0.992 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 48399 |\n", "| policy_loss | -0.000974 |\n", "| std | 0.286 |\n", "| value_loss | 0.000196 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.83 |\n", "| ep_rew_mean | -0.232 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 48500 |\n", "| time_elapsed | 2250 |\n", "| total_timesteps | 970000 |\n", "| train/ | |\n", "| entropy_loss | 0.177 |\n", "| explained_variance | 0.985 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 48499 |\n", "| policy_loss | -0.00477 |\n", "| std | 0.287 |\n", "| value_loss | 0.000108 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 4.04 |\n", "| ep_rew_mean | -0.345 |\n", "| success_rate | 0.98 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 48600 |\n", "| time_elapsed | 2255 |\n", "| total_timesteps | 972000 |\n", "| train/ | |\n", "| entropy_loss | 0.175 |\n", "| explained_variance | 0.568 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 48599 |\n", "| policy_loss | 0.137 |\n", "| std | 0.288 |\n", "| value_loss | 1.17 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.27 |\n", "| ep_rew_mean | -0.28 |\n", "| success_rate | 0.99 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 48700 |\n", "| time_elapsed | 2260 |\n", "| total_timesteps | 974000 |\n", "| train/ | |\n", "| entropy_loss | 0.181 |\n", "| explained_variance | 0.109 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 48699 |\n", "| policy_loss | 0.0737 |\n", "| std | 0.287 |\n", "| value_loss | 0.0206 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.81 |\n", "| ep_rew_mean | -0.217 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 48800 |\n", "| time_elapsed | 2264 |\n", "| total_timesteps | 976000 |\n", "| train/ | |\n", "| entropy_loss | 0.189 |\n", "| explained_variance | 0.938 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 48799 |\n", "| policy_loss | 0.0065 |\n", "| std | 0.286 |\n", "| value_loss | 0.000588 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.64 |\n", "| ep_rew_mean | -0.206 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 48900 |\n", "| time_elapsed | 2269 |\n", "| total_timesteps | 978000 |\n", "| train/ | |\n", "| entropy_loss | 0.196 |\n", "| explained_variance | 0.334 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 48899 |\n", "| policy_loss | -0.024 |\n", "| std | 0.286 |\n", "| value_loss | 0.0258 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.85 |\n", "| ep_rew_mean | -0.222 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 49000 |\n", "| time_elapsed | 2273 |\n", "| total_timesteps | 980000 |\n", "| train/ | |\n", "| entropy_loss | 0.229 |\n", "| explained_variance | 0.949 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 48999 |\n", "| policy_loss | 0.0027 |\n", "| std | 0.283 |\n", "| value_loss | 0.000349 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.88 |\n", "| ep_rew_mean | -0.227 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 49100 |\n", "| time_elapsed | 2278 |\n", "| total_timesteps | 982000 |\n", "| train/ | |\n", "| entropy_loss | 0.225 |\n", "| explained_variance | 0.88 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 49099 |\n", "| policy_loss | 0.00586 |\n", "| std | 0.282 |\n", "| value_loss | 0.00168 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.64 |\n", "| ep_rew_mean | -0.197 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 49200 |\n", "| time_elapsed | 2283 |\n", "| total_timesteps | 984000 |\n", "| train/ | |\n", "| entropy_loss | 0.251 |\n", "| explained_variance | 0.961 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 49199 |\n", "| policy_loss | -0.00708 |\n", "| std | 0.28 |\n", "| value_loss | 0.000401 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.55 |\n", "| ep_rew_mean | -0.197 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 49300 |\n", "| time_elapsed | 2287 |\n", "| total_timesteps | 986000 |\n", "| train/ | |\n", "| entropy_loss | 0.253 |\n", "| explained_variance | 0.965 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 49299 |\n", "| policy_loss | -0.0196 |\n", "| std | 0.279 |\n", "| value_loss | 0.000957 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.58 |\n", "| ep_rew_mean | -0.19 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 49400 |\n", "| time_elapsed | 2292 |\n", "| total_timesteps | 988000 |\n", "| train/ | |\n", "| entropy_loss | 0.229 |\n", "| explained_variance | 0.989 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 49399 |\n", "| policy_loss | 0.00202 |\n", "| std | 0.282 |\n", "| value_loss | 0.000158 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.75 |\n", "| ep_rew_mean | -0.219 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 49500 |\n", "| time_elapsed | 2297 |\n", "| total_timesteps | 990000 |\n", "| train/ | |\n", "| entropy_loss | 0.215 |\n", "| explained_variance | 0.969 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 49499 |\n", "| policy_loss | -0.00186 |\n", "| std | 0.283 |\n", "| value_loss | 0.000301 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.66 |\n", "| ep_rew_mean | -0.199 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 49600 |\n", "| time_elapsed | 2301 |\n", "| total_timesteps | 992000 |\n", "| train/ | |\n", "| entropy_loss | 0.235 |\n", "| explained_variance | 0.93 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 49599 |\n", "| policy_loss | -0.00325 |\n", "| std | 0.28 |\n", "| value_loss | 0.000914 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.62 |\n", "| ep_rew_mean | -0.198 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 49700 |\n", "| time_elapsed | 2305 |\n", "| total_timesteps | 994000 |\n", "| train/ | |\n", "| entropy_loss | 0.255 |\n", "| explained_variance | 0.985 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 49699 |\n", "| policy_loss | 0.000811 |\n", "| std | 0.278 |\n", "| value_loss | 0.000207 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.7 |\n", "| ep_rew_mean | -0.211 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 49800 |\n", "| time_elapsed | 2310 |\n", "| total_timesteps | 996000 |\n", "| train/ | |\n", "| entropy_loss | 0.269 |\n", "| explained_variance | 0.953 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 49799 |\n", "| policy_loss | -0.00972 |\n", "| std | 0.277 |\n", "| value_loss | 0.000671 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.84 |\n", "| ep_rew_mean | -0.225 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 431 |\n", "| iterations | 49900 |\n", "| time_elapsed | 2315 |\n", "| total_timesteps | 998000 |\n", "| train/ | |\n", "| entropy_loss | 0.283 |\n", "| explained_variance | 0.978 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 49899 |\n", "| policy_loss | 0.011 |\n", "| std | 0.275 |\n", "| value_loss | 0.000162 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 2.67 |\n", "| ep_rew_mean | -0.205 |\n", "| success_rate | 1 |\n", "| time/ | |\n", "| fps | 430 |\n", "| iterations | 50000 |\n", "| time_elapsed | 2320 |\n", "| total_timesteps | 1000000 |\n", "| train/ | |\n", "| entropy_loss | 0.29 |\n", "| explained_variance | 0.994 |\n", "| learning_rate | 0.0007 |\n", "| n_updates | 49999 |\n", "| policy_loss | -0.00885 |\n", "| std | 0.275 |\n", "| value_loss | 6.45e-05 |\n", "------------------------------------\n" ] }, { "output_type": "execute_result", "data": { "text/plain": [ "" ] }, "metadata": {}, "execution_count": 11 } ] }, { "cell_type": "code", "source": [ "# Save the model and VecNormalize statistics when saving the agent\n", "model.save(\"a2c-PandaReachDense-v3\")\n", "env.save(\"vec_normalize.pkl\")" ], "metadata": { "id": "MfYtjj19cKFr" }, "execution_count": 12, "outputs": [] }, { "cell_type": "markdown", "source": [ "### Evaluate the agent 📈\n", "- Now that's our agent is trained, we need to **check its performance**.\n", "- Stable-Baselines3 provides a method to do that: `evaluate_policy`" ], "metadata": { "id": "01M9GCd32Ig-" } }, { "cell_type": "code", "source": [ "from stable_baselines3.common.vec_env import DummyVecEnv, VecNormalize\n", "\n", "# Load the saved statistics\n", "eval_env = DummyVecEnv([lambda: gym.make(\"PandaReachDense-v3\")])\n", "eval_env = VecNormalize.load(\"vec_normalize.pkl\", eval_env)\n", "\n", "# We need to override the render_mode\n", "eval_env.render_mode = \"rgb_array\"\n", "\n", "# do not update them at test time\n", "eval_env.training = False\n", "# reward normalization is not needed at test time\n", "eval_env.norm_reward = False\n", "\n", "# Load the agent\n", "model = A2C.load(\"a2c-PandaReachDense-v3\")\n", "\n", "mean_reward, std_reward = evaluate_policy(model, eval_env)\n", "\n", "print(f\"Mean reward = {mean_reward:.2f} +/- {std_reward:.2f}\")" ], "metadata": { "id": "liirTVoDkHq3", "colab": { "base_uri": "https://localhost:8080/" }, "outputId": "da7abc18-3420-4fe8-9dbd-064ba8c1e179" }, "execution_count": 13, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Mean reward = -0.26 +/- 0.10\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "/usr/local/lib/python3.11/dist-packages/stable_baselines3/common/evaluation.py:67: UserWarning: Evaluation environment is not wrapped with a ``Monitor`` wrapper. This may result in reporting modified episode lengths and rewards, if other wrappers happen to modify these. Consider wrapping environment first with ``Monitor`` wrapper.\n", " warnings.warn(\n" ] } ] }, { "cell_type": "markdown", "source": [ "### Publish your trained model on the Hub 🔥\n", "Now that we saw we got good results after the training, we can publish our trained model on the Hub with one line of code.\n", "\n", "📚 The libraries documentation 👉 https://github.com/huggingface/huggingface_sb3/tree/main#hugging-face--x-stable-baselines3-v20\n" ], "metadata": { "id": "44L9LVQaavR8" } }, { "cell_type": "markdown", "source": [ "By using `package_to_hub`, as we already mentionned in the former units, **you evaluate, record a replay, generate a model card of your agent and push it to the hub**.\n", "\n", "This way:\n", "- You can **showcase our work** 🔥\n", "- You can **visualize your agent playing** 👀\n", "- You can **share with the community an agent that others can use** 💾\n", "- You can **access a leaderboard 🏆 to see how well your agent is performing compared to your classmates** 👉 https://huggingface.co/spaces/huggingface-projects/Deep-Reinforcement-Learning-Leaderboard\n" ], "metadata": { "id": "MkMk99m8bgaQ" } }, { "cell_type": "markdown", "metadata": { "id": "JquRrWytA6eo" }, "source": [ "To be able to share your model with the community there are three more steps to follow:\n", "\n", "1️⃣ (If it's not already done) create an account to HF ➡ https://huggingface.co/join\n", "\n", "2️⃣ Sign in and then, you need to store your authentication token from the Hugging Face website.\n", "- Create a new token (https://huggingface.co/settings/tokens) **with write role**\n", "\n", "\"Create\n", "\n", "- Copy the token\n", "- Run the cell below and paste the token" ] }, { "cell_type": "code", "execution_count": 14, "metadata": { "id": "GZiFBBlzxzxY", "colab": { "base_uri": "https://localhost:8080/", "height": 17, "referenced_widgets": [ "22b65f742f6f45a3ab528282d65986f7", "7d6994a82ca64dbeb50f4da1da4f91d5", "4b44bef636d04083bd1e74ec8a37abcf", "988419020b2c488ca01de9c855e3b871", "f74fcf731f004609b3030a645ce55e40", "31ade0b42e624c50a698df43c705306b", "4cfaa0dfe03d4bdda729589e726f9cfb", "201aaad9b1584ee9ab88ce4981e7bba5", "728faf318a614500b86307f8040feb72", "35b068cc0fd048fcb1fb5366086d1ac8", "4403d9ed2124488d87b99c40e8d15ea0", "63cfd7ef19cf47228ba195bf102d0bb3", "8c8a0d6c29b0419d884f33d7291dad03", "6175e78506e248adb108e2014565ef26", "9a3933af0ae34b07a3646f03a0cb16b6", "a4deebba544347dc8da3bc880d1c69e8", "4d5e7e271d7c4083a9c84d04a5e14d7e", "6f78103f996d4dcf81bfba72af2bfb86", "22d2466c15084c39a6a9af8dac759916", "3c9f1a666be240c3a68bd7d04b22ec34" ] }, "outputId": "302c1dd1-8456-4bd4-ecb3-7faa1ff3489d" }, "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "VBox(children=(HTML(value='