I'm looking for a reinforcement learning library that can be used for real-time robot control. What I first had in mind was ROS to describe the robot, Mujoco to simulate physics, and OpenAI gym to encapsulate RL. However, to my knowledge, this stack is only suitable when the robot is in simulation. What is the best way to implement and benchmark RL algorithms independent of the underlying control mechanism? Meaning, I would like to write the same algorithms, and just swap out simulated and real robot as needed, but the algos shouldn't know the difference. Thanks.

  • $\begingroup$ Control algorithms must be the same $\endgroup$
    – Long Smith
    Apr 9, 2019 at 16:13
  • $\begingroup$ Yes, that's the reason why I'm looking for a way to decouple the algorithms from the running environment (simulation and real world). $\endgroup$
    – makons
    Apr 9, 2019 at 17:50


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.