tug-mild
Mild reward-restructure Tug of War policy: 149.9 cm rating; 8-1 vs Nico/reference; 0-10 vs the #1 wrapper.
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> Supreme-Ed/microduck-tug-mild
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:
main - commit:
4b675ebf4 - exported from a checkout with uncommitted changes
- Downloads last month
- 28