search

nicrusso7 / rex-gym

OpenAI Gym environments for an open-source quadruped robot (SpotMicro)
Apache License 2.0
973 stars 130 forks source link

General questions #17

Closed darshisen closed 3 years ago

darshisen commented 3 years ago

Just a few general questions:

  1. How do I run a policy from a trained model?
  2. How do I restart training from the same place I left off if I stop in the middle or the training crashes?
nicrusso7 commented 3 years ago

Hi, thank you for you interest in this project. For general questions/discussions there is a more appropriate Discussions panel here.

Regarding your questions:

  1. If you mean how to run a policy in a simulation, check out the policy command. With this command you can run any policy under the policies folder. If you want to run your own policy, just edit this map. Be sure that your policy match the environment (map key), e.g. if you trained a new policy for the walk env and you are using the open_loop controller, then you need to edit the value of walk_ol.

  2. Unfortunately this feature is not supported. Any PR is welcome!

Please feel free to open a new discussion if needed!