hill-es2
1.5 m Hill Climb walker: our own 2 m Sprint policy (PPO with a linear forward-speed reward, then evolution strategies), fine-tuned by evolution strategies on the Arena's hill simulator (70 generations). Searched on start seeds 101-400, selected on 1001-1060, never on the board's seeds 1-5; 100/100 finishes on held-out seeds 2001-2100. Simulation only.
A perpetual policy for the microduck (61-D observation, 14 actions, 50 Hz). Runs until told otherwise — a gait for the walk slot.
Run it on a robot
sudo robotctl policy load walk linkTheWorld/microduck-hill-es2
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:
sprint-race - commit:
822c9db39
- Downloads last month
- -