rl-baselines3-zoo icon indicating copy to clipboard operation
rl-baselines3-zoo copied to clipboard

Published 20 hours ago • verified publisher icon DLR-RM

panda-gym v2

Open qgallouedec opened this issue 2 years ago • 6 comments

Description

Update benchmark for latest version of panda-gym.

Motivation and Context

  • [ ] I have raised an issue to propose this change (required for new features and bug fixes)

Types of changes

  • [ ] Bug fix (non-breaking change which fixes an issue)
  • [ ] New feature (non-breaking change which adds functionality)
  • [x] Breaking change (fix or feature that would cause existing functionality to change)
  • [ ] Documentation (update in the documentation)

Checklist:

  • [ ] I've read the CONTRIBUTION guide (required)
  • [x] I have updated the changelog accordingly (required).
  • [x] My change requires a change to the documentation.
  • [ ] I have updated the tests accordingly (required for a bug fix or a new feature).
  • [x] I have updated the documentation accordingly.
  • [x] I have reformatted the code using make format (required)
  • [x] I have checked the codestyle using make check-codestyle and make lint (required)
  • [x] I have ensured make pytest and make type both pass. (required)

Note: we are using a maximum length of 127 characters per line

qgallouedec avatar May 13 '22 11:05 qgallouedec

Hey,

thanks for the PR =) I might wait until Huggingface PR is merged https://github.com/DLR-RM/rl-baselines3-zoo/pull/198 I will help @simoninithomas in the coming days.

araffin avatar May 16 '22 15:05 araffin

Quickly looking at it, no additional tuning was in fact required?

araffin avatar May 16 '22 15:05 araffin

no additional tuning was in fact required?

No tuning has been done. It might be possible to find better hyperparameters. I leave this for a future PR. One exception: I had to decrease the learning for PickAndPlace with SAC. Otherwise, the loss was diverging.

qgallouedec avatar May 16 '22 15:05 qgallouedec

Basic version is ready to review ;) https://github.com/DLR-RM/rl-baselines3-zoo/pull/250

An example: https://huggingface.co/sb3/ppo-MountainCarContinuous-v0

araffin avatar May 20 '22 07:05 araffin

btw, this requires gym > 0.21, right?

araffin avatar Jun 02 '22 22:06 araffin

btw, this requires gym > 0.21, right?

Yes, so it can't be merged before #256 I think

qgallouedec avatar Jun 03 '22 06:06 qgallouedec

What's the status with this PR?

fikricanozgur avatar Sep 26 '22 13:09 fikricanozgur

panda-gym v2 requires gym==0.24. But, for the moment, SB3 requires gym==0.21. So the status is "waiting for SB3 to be compatible with gym>=0.24"

qgallouedec avatar Sep 26 '22 13:09 qgallouedec