pollen-robotics/microduck_rl

RL training environments for Microduck — a 800 g, 25 cm tall bipedal robot — built on mjlab (MuJoCo Warp) with PPO. Policies are trained here at 50 Hz, exported to ONNX, and deployed on the real robot by the runtime in pollen-robotics/microduck. https://github.com/user-attachments/assets/50c3d537-8db2-4005-9d9c-3472faeec4d0 The repo encodes the full sim2real recipe: BAM actuator physics, domain randomization, backlash simulation, and the reward-design lessons that made it work (see AGENTS.md for the distilled playbook). Requires a CUDA GPU (training runs through MuJoCo Warp) and uv. Resume from a checkpoint: No GPU? Add --hf-jobs to any train command to run it on Hugging Face Jobs instead of locally (see scripts/hf/README.md). uv run list-envs prints the live registry. Flat/Rough variants exist where noted. At deployment the runtime hot-swaps these policies (walk / recover / trick) behind a shared 61-dimensional observation contract, so any of them can take over the robot at any moment. scripts/inferpolicy.py…