cartwheel
Mjlab-GotATalent-MicroDuck
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> JacoCronje/microduck-cartwheel
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
- task_id:
Mjlab-GotATalent-MicroDuck - repo:
https://github.com/JacoCronje/microduck-challenges.git - branch:
cartwheel - commit:
7427cbc1b - checkpoint:
10750 - seed:
1 - base:
mjlab-microduck 0.1.0 @ 8d0dbc94c - started:
2026-10-23T20:34:36Z
Reproduce
Same code, same uv.lock, same command, same seed. Training it again yields a comparable policy, not the same weights: GPU reinforcement learning is not bit-reproducible across machines.
git clone https://github.com/JacoCronje/microduck-challenges.git
cd microduck-challenges
git checkout 7427cbc1b
uv sync
uv run train Mjlab-GotATalent-MicroDuck --env.scene.num-envs 1536 --agent.max-iterations 2000 --agent.seed 1 --agent.logger tensorboard --agent.run-name cart5 --agent.resume True --agent.load-run 2026-10-23_21-33-01_cart4 --agent.load-checkpoint model_8997.pt
- Downloads last month
- 17