Training signal from environments in RLlib

[jcallaham]

Training a basic PPO agent using RLlib and the script here this is what I'm getting for the "episode reward mean". Somehow it doesn't really seem to be learning anything, although I haven't actually run the learned model forward yet.

[jcallaham]

Seems like the problem might be that the flow config and solver both need to be able to reset with the environment.

[jcallaham]

Now the signal is changing (though performance doesn't look great)