huggingface / huggingface/simulate
Question about n_show and n_maps in ParallelRLEnv
Open
- Dominant language
- Python
- Stars
- 195
- Forks
- 13
- Avg merge
- 58m
- Merged PRs (30d)
- 1
Description
In the `ParallelRLEnv` class, I am having a doubt if the environment instances above the number set for n_show perform a function? Because in the class when you inherit from VecEnv of stable-baselines3 you set the num_envs to n_show. So an agent from SB3 will be able to interact only with those agents that are in n_show. Even in the step function of ParallelRLEnv, there is a check that the actions are given only for n_show envs.
So if n_maps is 20 and n_show is 12, is there any reason to have the extra 8 env instances since you can neither interact with them nor get observations from them.
Contributor guide
Assessment
This issue has not been assessed yet.