DLR-RM / rl-baselines3-zoo

A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.
https://rl-baselines3-zoo.readthedocs.io
MIT License
1.9k stars 495 forks source link

Add `--eval-env-kwargs` to `train.py` #405

Closed Quentin18 closed 9 months ago

Quentin18 commented 9 months ago

Description

Motivation and Context

Types of changes

Checklist:

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

araffin commented 9 months ago

Hello, I somehow cannot push to your branch, so I pushed my edits to https://github.com/DLR-RM/rl-baselines3-zoo/pull/406 I mostly fixed a breaking change (by default, eval-env-kwargs should be the same as env-kwargs which was not the case here anymore) and simplify tests (and added a runtest for that feature).

Quentin18 commented 9 months ago

OK thanks :+1: