Multi-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-Solvers.
Luke MarrisPaul MullerMarc LanctotKarl TuylsThore GraepelPublished in: CoRR (2021)
Keyphrases
- multi agent
- nash equilibria
- cooperative
- stochastic games
- nash equilibrium
- incomplete information
- multi agent systems
- single agent
- training examples
- intelligent agents
- game theory
- training set
- reinforcement learning
- supervised learning
- training samples
- breast cancer
- state space
- training phase
- meta level
- multiple agents