trackmania-rl / tmrl

Reinforcement Learning for real-time applications - host of the TrackMania Roborace League
https://pypi.org/project/tmrl
MIT License
500 stars 68 forks source link

Feature Request: migrate from gym to gymnasium #40

Closed elliottower closed 1 year ago

elliottower commented 1 year ago

Hi, very cool repo. Would it be possible for it 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. The main difference is the API has switched to returning truncated and terminated, rather than done, in order to give more information and mitigate edge case issues.

yannbouteiller commented 1 year ago

Hi, we will migrate to gymnasium shortly alongside rtgym, some people have already requested we do :)

yannbouteiller commented 1 year ago

tmrl and rtgym now support gymnasium instead of gym since version 0.5.0

Note that tmrl had already migrated to the truncated / terminated signature when gym did. Our SAC implementation has always used the difference between these two signals and used the info dictionary for that purpose when the change was not yet introduced in the newer versions of gym.

elliottower commented 1 year ago

tmrl and rtgym now support gymnasium instead of gym since version 0.5.0

Note that tmrl had already migrated to the truncated / terminated signature when gym did. Our SAC implementation has always used the difference between these two signals and used the info dictionary for that purpose when the change was not yet introduced in the newer versions of gym.

Thanks! My bad, I didn’t see the truncated and terminated changes were already switched. Excited to play around with training agents:)