juicenv/microduck-hill-es1

hill-es1

1.5 m Hill Climb runner: our 2 m Sprint winner (HannesVonEssen/microduck-running, Apache-2.0, fine-tuned) further tuned by evolution strategies on the Arena's own hill scorer.

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-hill-es1

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 HannesVonEssen/microduck-running.

Training

• repo: pollen-robotics/microduck_rl
• branch: lean
• commit: 5a3636302