Can this algorithm be generalised to work with multiple (60) agents competing against eachother?

openai / maddpg

Code for the MADDPG algorithm from the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

https://arxiv.org/pdf/1706.02275.pdf

MIT License

1.6k stars 484 forks source link

Can this algorithm be generalised to work with multiple (60) agents competing against eachother? #27

Closed alexanderkell closed 3 years ago

alexanderkell commented 5 years ago

The examples seem to show two teams, however I was wondering whether it was possible to generalise this reinforcement algorithm to a "free-for-all" model, where multiple agents all compete amongst themselves.

silkyrose commented 4 years ago

I have the same problem. Do you address it ?

alexanderkell commented 4 years ago

It is possible to use other, non-multi-agent specific algorithms, such as PPO, DQN or DDPG. They can sometimes generalise well.