Posterior sampling for multi-agent reinforcement learning: solving extensive games with imperfect information.
Yichi ZhouJialian LiJun ZhuPublished in: ICLR (2020)
Keyphrases
- imperfect information
- multi agent reinforcement learning
- stochastic games
- game theoretic
- game theory
- game playing
- game tree search
- perfect information
- multi agent learning
- game tree
- nash equilibria
- imperfect information games
- monte carlo
- learning agents
- nash equilibrium
- multi agent systems
- multi agent
- card game
- probability distribution
- combinatorial optimization
- resource allocation
- finite automata
- decision makers
- lower bound
- human players
- cooperative
- learning algorithm