RL training environments for Microduck (mjlab)
microduck_rl provides reinforcement-learning environments for training walking and recovery policies for Microduck, an 800-gram, 25-centimetre bipedal robot, in MuJoCo through mjlab. It trains policies with PPO in simulation, including actuator and terrain variation, then exports them to ONNX for deployment on the physical robot.
These files are pollen-robotics/microduck_rl's own configuration. They tell Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.
AGENTS.md A 4,200 tok CLAUDE.md A 5 tok