Farama-Foundation / Miniworld

Simple and easily configurable 3D FPS-game-like environments for reinforcement learning

http://miniworld.farama.org/

Apache License 2.0

694 stars 129 forks source link

Added `EzPickle` to the environments #76

Closed BolunDai0216 closed 1 year ago

BolunDai0216 commented 1 year ago

Description

All of the environments now also inherit from gymnasium.utils.EzPickle. Included a test for pickling.

Type of change

New feature (non-breaking change which adds functionality)

Checklist:

[x] I have run the pre-commit checks with pre-commit run --all-files (see CONTRIBUTING.md instructions to set it up)
[x] I have commented my code, particularly in hard-to-understand areas
[x] I have made corresponding changes to the documentation
[x] My changes generate no new warnings
[x] I have added tests that prove my fix is effective or that my feature works
[x] New and existing unit tests pass locally with my changes

BolunDai0216 commented 1 year ago

Looks good, could you add a test that for each environment, you try to pickle and unpickle the object. This is an example from Gymnasium. https://github.com/Farama-Foundation/Gymnasium/blob/33e32178ffdf040a095bd2c856f6410bc7ec1306/tests/envs/test_envs.py#L197

An interesting addition, in comparison to the gymnasium is to pass a keyword to check that works

I added the test and passed a keyword using gym.make(env_id, max_episode_steps=100).unwrapped, is that what you had in mind?