Benjamin Etheredge

I manage to get the wrapping code working. It was more elegant than I thought. My issue was it didn't play nicely in a jupyter notebook. The example code would...

Yes, I have gotten it working. I still think it would be helpful to have the gym-compatible environment available outside the wrapper. Is it possible to handle the wrapping logic...

So the work going on to rework the gym wrapper would make this environment work with any other algorithms. I've got it working with the PPO example from pytorch lightning...

I have a fix for it. I'm trying to get it pushed to a new branch now.

I don't have a code snippet to reproduce it. I noticed it when trying to run the same code twice in two shells.

There may also be an issue with passing specific player configurations through extended PlayerEnvs. I'm still investigating that one as it could be an issue with my code. It was...

I'm not sold on uuid either. It is ugly and hard to track. I had to start logging player names to follow what was going on. I like the more...

Is there a way to store player names as a side effect? Or maybe to catch the "Someone is already using that name" in the default configuration and keep incrementing...

An additional note for why this needs updating: I'm exploring using openai baselines (and other forks). One key element for algorithms is parallel environments. I'm able to get parallel environments...

I think going more synchronous is probably the way to go. Maybe just throw things on other processes? I'm not super familair with python multi-threading/processing. I sorta did something similar....