Microduck Robot Open Sources RL Stack for Sim2real Training Loop

victormustar · x · 2026-08-28

Pollen Robotics' Microduck robot demonstrates a complete sim2real loop, training in simulation and running in reality. The project's reinforcement learning (RL) stack is fully open source, allowing the robot to learn new tricks through this workflow.

Related event: Pollen Robotics Open-Sources RL Training Stack for Microduck Robot(3 posts)→

Original post →

More from Embodied

Embodied channel →