improve docs adding "--gym-packages" argument

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

1.89k stars 494 forks source link

improve docs adding "--gym-packages" argument #445

Open turbotimon opened 2 months ago

turbotimon commented 2 months ago

Description

improve doc adding "--gym-packages" argument

source: https://github.com/DLR-RM/rl-baselines3-zoo/blob/e06914e9835b8f3233b18d59943b1464b89ddb90/rl_zoo3/train.py#L107-L112

Motivation and Context

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

Types of changes

[x] Documentation (update in the documentation)

Checklist:

[x] I've read the CONTRIBUTION guide (required)
[x] I have updated the documentation accordingly.

turbotimon commented 2 months ago

package:env_id is the first thing I tried, but unfortunately it does not work yet (v2.3.0)...

ENV_NAME = 'gym_environment:gym_environment/GridWorld-v0' # My custom environment

# Works
from gymnasium import make_vec
env = make_vec(ENV_NAME) 

# ValueError: gym_environment:gym_environment/GridWorld-v0 not found in gym registry ....
import sys
from rl_zoo3.train import train
sys.argv = ["python", "--algo", "ppo", "--env", ENV_NAME]
train()

(You could try using this template for custom env)