tug-competitive-v2
Microduck Tug of War competitive policy with anti-fall and recovery
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> RSanchez996/microduck-tug-competitive-v2
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:
ft_competitive_multiopponent - commit:
b8328925e - exported from a checkout with uncommitted changes
- Downloads last month
- 23