Edgar A. Duéñez-Guzmán

Results 16 comments of Edgar A. Duéñez-Guzmán

Closing. Feel free to re-open if you have more questions.

Unfortunately at the moment the stable baselines example is broken due to an inherent incompatibility between RLLib, Gym and Gymnasium. We are working in a way around this, but currently...

From setuptools: https://github.com/pypa/setuptools/issues/3801 pip3 install setuptools==65.5.0

We haven't experimented on scaling up much. There are some considerations about scaling: 1. The `GameMaster` currently calls on _all_ agents at every step. So, linearly scaling calls for agents...

At head, `clean_up_20` has been fixed. The tagged version 2.3.0 contains the mistake so it can be used to reproduce the state for the Melting Pot Competition 2023.

This is a bug. I'll see what we can do