tug-puller3

Tug of War puller, fine-tuned from Nico-robot/microduck-tug-of-war (via our tug-puller1 and tug-puller2) against a league of frozen opponent ducks, each bout drawing one. Plain network, no seed tables.

A perpetual policy for the microduck (61-D observation, 14 actions, 50 Hz). Runs until told otherwise โ€” a gait, loaded into a policy slot.

Run it on a robot

sudo robotctl policy load <slot> juicenv/microduck-tug-puller3

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).

A remix of Nico-robot/microduck-tug-of-war.

Training

  • repo: pollen-robotics/microduck_rl
  • branch: main
  • commit: 4b675ebf4
Downloads last month
24
Video Preview
loading

Model tree for juicenv/microduck-tug-puller3

Finetuned
(7)
this model