I trained some MPE environments (simpe_tag,...) in MALlib to see how well it trains.... but I came to a slight problem viewing the results I made and those they uploaded. I am realtivly new to MARL and have no idea if the are good or not.
I tried looking up in the documentation on Rllib and Marllib bur couldn't find anything and because I have no experience regarding the results I have no idea what to read.
My question: Did somebody already worked with MARLlib an can confirm that it trains well?
Is it normal for simple_spread (from MPE Pettingzoo) to get reward results like -20 after 8000 epochs (started with -40)?
It would be great if sombody could help me.
Thank you