Observation space bound

[Fatimah-Alahmed]

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]

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.