Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Observation space bound #246

Open
Fatimah-Alahmed opened this issue Nov 17, 2024 · 1 comment
Open

Observation space bound #246

Fatimah-Alahmed opened this issue Nov 17, 2024 · 1 comment
Labels
question Further information is requested

Comments

@Fatimah-Alahmed
Copy link

I would like to ask about the upper and lower bounds of the obs space in BaseRLAviary.py, I. noticed that the bounds are - and + infinity, does not that make the state space very huge to be explored? I noticed in the paper version it is different. so is it okay to keep the bounds like this? or better to restrict them to like the max drone velocity and so on...

@JacopoPan JacopoPan added the question Further information is requested label Nov 26, 2024
@JacopoPan
Copy link
Member

The simulation is intended mostly for deep RL and you can let the MLP representation of the policy and value networks deal with that. If you have a problem where the state space boundaries are know, it can help the learning but it is not imperative.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested
Projects
None yet
Development

No branches or pull requests

2 participants