Train in Simulation, Deploy on a Real Robot: Microduck with Isaac Lab 3.0

This tutorial details training and evaluating Microduck using Isaac Lab and Newton, then exporting the policy for real-world deployment. Users can share their models on the Hugging Face Hub, test compatibility in Microduck Arena, or deploy them on their own Microduck hardware. This workflow leverages Pollen Robotics' Microduck, the original Microduck reinforcement-learning project, BAM actuator modeling, and Isaac Lab 3.0 and Newton integrations, with walking as a starting point.