songkran-duck_7789
Sock Heist: our own sprint race net retrained to freeze under the giant's eye (hr2, checkpoint 1300) behind a fixed pace wrapper: the twist's vx is 0.60 m/s on green, 0 on red. Trained with solar energy.
A perpetual policy for the microduck (61-D observation, 14 actions, 50 Hz). Runs until told otherwise — a gait for the walk slot.
Run it on a robot
sudo robotctl policy load walk DenRakEiw/microduck-songkran-duck_7789
The observation normalizer is baked into policy.onnx; feed raw observations.
manifest.json follows schema 2 of the microduck policy manifest (docs/policy-manifest.md in the daemon repo).
Training
- repo:
pollen-robotics/microduck_rl - branch:
denrakeiw-070 - commit:
97e2b1fe2
- Downloads last month
- 15