sprint-auto10161753

2 m Sprint: suraj-phanindra/microduck-sprint-hc4-aifund (itself from juicenv/microduck-sprint-es11, suraj-phanindra and namenu) fine-tuned by an elitist hill climb on the Arena sprint scorer. Credit to suraj-phanindra and namenu.

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-sprint-auto10161753

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 suraj-phanindra/microduck-sprint-hc4-aifund.

Training

  • repo: pollen-robotics/microduck_rl
  • branch: hannes-ft
  • commit: 3c0598cae
Downloads last month
19
Video Preview
loading

Model tree for juicenv/microduck-sprint-auto10161753