sock-heist5
6 m Sock Heist: the challenge recipe (warm start from the Arena reference walker) with progress_reward 12, seed 6, checkpoint 1300. Our own run, plain network, no seed tables.
A perpetual policy for the microduck (61-D observation, 14 actions, 50 Hz). Runs until told otherwise — a gait, loaded into a policy slot.
Run it on a robot
sudo robotctl policy load <slot> juicenv/microduck-sock-heist5
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:
HEAD - commit:
5cee942d8
- Downloads last month
- 13