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)→
More from Embodied
- MIT's Loop Closure Grasping Balances Strength, Gentleness, and Versatility — lukas_m_ziegler · 2026-08-28
- Stewart Alsop to host in-person robotics workshop in Mendoza — StewartalsopIII · 2026-08-28
- Q-Planning enables recursive self-improvement for robot policies: 25% to 80% success — animesh_garg · 2026-08-28
- Open Source Animacy: Maps Any Human Video to Robot Motion Without Retraining — dee_hw · 2026-08-28
- Agent Body Protocol: Visualizing Coding Agent Status — dee_hw · 2026-08-28
- Autonomous Lamp: Open Source AI Companion with Physical Body — dee_hw · 2026-08-28