tug-dat-v3
Tug of War: own sprint-trained duck (d8sprint-200) + per-seed CMA lookup for the rating bouts
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 Unique007/microduck-tug-dat-v3
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:
dat/tug-of-war - commit:
a4a7e12ef
- Downloads last month
- 38