gin-sock-c19

Lookup-table remix for the 6 m Sock Heist. Seeds 2-5 replay rumezhak's sock-heist-composite-v13 (thanks!). Seed 1 starts from rumezhak's seed 1 and its last 25 steps are GinDuck's own hill-climb search in the Arena physics (4.615 -> 4.610 s). The network behind the table is GinDuck's.

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> GinDuck/microduck-gin-sock-c19

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: talent-3
  • commit: debcfcae0
Downloads last month
7
Video Preview
loading