#python

Microduck RL gives training environments for a small biped robot, so you can teach it walking, standing up, sitting, tricks, and roller tasks in simulation, then export the learned policy to run on the real robot. It includes realistic motor physics, backlash, and random changes to help sim-to-real transfer. The benefit to you is faster robot training, easier testing, and safer deployment because one shared setup lets different skills swap on the robot without changing the runtime.

https://github.com/pollen-robotics/microduck_rl