Sim2Real Transfer for Reinforcement Learning without Dynamics Randomization
Manuel Kaspar,Juan D. Muñoz Osorio,Juergen Bock,Manuel Kaspar,Juan D. Muñoz Osorio,Juergen Bock
We show how to use the Operational Space Control framework (OSC) under joint and Cartesian constraints for reinforcement learning in Cartesian space. Our method is able to learn fast and with adjustable degrees of freedom, while we are able to transfer policies without additional dynamics randomizations on a KUKA LBR iiwa peg-in-hole task. Before learning in simulation starts, we perform a system ...
