Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Feature Request: migrate from gym to gymnasium #125

Open
elliottower opened this issue Mar 17, 2023 · 5 comments
Open

Feature Request: migrate from gym to gymnasium #125

elliottower opened this issue Mar 17, 2023 · 5 comments
Labels
enhancement New feature or request

Comments

@elliottower
Copy link

Hi, would it be possible for safe-control-gym to be upgraded from gym to gymnasium? Gymnasium is the maintained version of openai gym and is compatible with current RL training libraries (rllib and tianshou have already migrated, and stable-baselines3 will soon).

This repository is currently listed in the gymnasium third party environments but we are cleaning the list up to only include maintained gymnasium-compatible repositories.

For information about upgrading and compatibility, see migration guide and gym compatibility.

@JacopoPan
Copy link
Member

Hello @elliottower
yes, I will attend to this as soon as we have fully migrated utiasDSL/gym-pybullet-dones (which I foresee to be a bit simpler).

@JacopoPan JacopoPan added the enhancement New feature or request label Mar 20, 2023
@elliottower
Copy link
Author

Hello @elliottower
yes, I will attend to this as soon as we have fully migrated utiasDSL/gym-pybullet-dones (which I foresee to be a bit simpler).

Sounds good, thanks! Just wanted to make sure you you were aware of the deprecation/new maintenance on gymnasium but my fault if you saw it twice cause of the other repo.

@jkterry1
Copy link

@JacopoPan Hey, just wanted to follow up on this :)

@JacopoPan
Copy link
Member

Hi Jordan, the main branch's dependencies have all been changed from gym to gymnasium.
We still need to work on changing the .step() API to account for terminated and truncated returns (it should be easy on the environments' side but will require some due diligence on the controllers/experiments side, can we talk about this with the precommit hooks next week, @Federico-PizarroBejarano?)

@Federico-PizarroBejarano
Copy link
Contributor

@JacopoPan yes happy to talk about this and do the update this week.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

4 participants