Instructions to use heyskylark/microduck-sprint-w2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Microduck
How to use heyskylark/microduck-sprint-w2 with Microduck:
# Replace SLOT with the slot specified in the model card (walk, stand, sitstand, ground_pick, kick_left, kick_right, roulade). sudo robotctl policy load SLOT heyskylark/microduck-sprint-w2
- Notebooks
- Google Colab
- Kaggle
sprint-w2
Mjlab-Sprint2m-MicroDuck
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> heyskylark/microduck-sprint-w2
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-Sprint2m-MicroDuck - repo:
git@github.com:heyskylark/microduck-challenges.git - branch:
main - commit:
0b7f5c1bf - checkpoint:
2700 - seed:
1 - base:
mjlab-microduck 0.1.0 @ 1efd853be - started:
2026-11-02T20:53:00Z
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 git@github.com:heyskylark/microduck-challenges.git
cd microduck-challenges
git checkout 0b7f5c1bf
uv sync
uv run train Mjlab-Sprint2m-MicroDuck --env.scene.num-envs 4096 --agent.max-iterations 3000 --agent.seed 1 --agent.logger tensorboard --agent.run-name W2-angvel001-s1
- Downloads last month
- 30