microduck-tug-p10
reinforcement learning policy for robot
1 min readupdated
The microduck-tug-p10 model is a perpetual policy (behavior algorithm) for the microduck robot platform, built for tug-of-war tasks. It processes 61-dimensional observations and outputs 14 control actions at 50 Hz, enabling the robot to hold its position or pull until a stop command is issued. Trained via Reinforcement Learning in the Mjlab environment using mjlab-microduck 0.1.0, it is useful for robotics researchers.
Key features
- Perpetual movement policy running at 50 Hz until a stop command is received.
- Built-in observation normalizer right inside the policy.onnx file for working with raw data.
- Trained via reinforcement learning using the mjlab-microduck 0.1.0 environment (checkpoint 1840).
What you can do
- Upload the policy to a compatible microduck robot using the robotctl utility to participate in a competition.
- Reproduce model training locally using the microduck-challenges repository and the uv package manager.
Example
sudo robotctl policy load SSH111111/microduck-tug-p10Read more
DetailsTask ID: Mjlab-TugOfWar-MicroDuck
Architecture: 61-D observation, 14 actions, 50 Hz
Base: mjlab-microduck 0.1.0
Training: seed 42, checkpoint 1840










Comments