Instructions to use GinDuck/microduck-gin-sock-s5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Microduck
How to use GinDuck/microduck-gin-sock-s5 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 GinDuck/microduck-gin-sock-s5
- Notebooks
- Google Colab
- Kaggle
gin-sock-s5
Simulation only. Seeds 1 to 4 replay jrubiosainz's 'Microduck Sock Heist - P1 s4 1f0fc5ae' and the runs it builds on. Seed 5 is GinDuck's own run: seed 5 follows the motion of seed 2 from the start, found by search in the Arena's physics. 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-s5
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
- 20