Sim2Real Transfer for Reinforcement Learning without Dynamics Randomization

Manuel Kaspar; Juan David Munoz Osorio; Jürgen Bock

Sim2Real Transfer for Reinforcement Learning without Dynamics Randomization

Artificial Intelligence 2020-02-27 v1 Machine Learning Robotics

Authors: Manuel Kaspar , Juan David Munoz Osorio , Jürgen Bock

Abstract

In this work 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 therefore 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 identification for aligning the simulation environment as far as possible with the dynamics of a real robot. Adding constraints to the OSC controller allows us to learn in a safe way on the real robot or to learn a flexible, goal conditioned policy that can be easily transferred from simulation to the real robot.

Keywords

sim-to-real transfer reinforcement learning

Cite

@article{arxiv.2002.11635,
  title  = {Sim2Real Transfer for Reinforcement Learning without Dynamics Randomization},
  author = {Manuel Kaspar and Juan David Munoz Osorio and Jürgen Bock},
  journal= {arXiv preprint arXiv:2002.11635},
  year   = {2020}
}

Related papers

View all related →

Computer Vision and Pattern Recognition · Computer Science

Meta Reinforcement Learning for Sim-to-real Domain Adaptation