MADRL project solving chess environment using PPO with two different methods: 2 agents/networks and a single agent/network.
Why do you think that https://github.com/Stanford-ILIAD/PantheonRL is a good alternative to Simple-MADRL-Chess
MADRL project solving chess environment using PPO with two different methods: 2 agents/networks and a single agent/network.
Why do you think that https://github.com/Stanford-ILIAD/PantheonRL is a good alternative to Simple-MADRL-Chess