The folk theorem for irreducible stochastic games with imperfect public monitoring.
Drew FudenbergYuichi YamamotoPublished in: J. Econ. Theory (2011)
Keyphrases
- stochastic games
- imperfect information
- nash equilibria
- games with incomplete information
- learning automata
- multiagent reinforcement learning
- repeated games
- markov decision processes
- nash equilibrium
- reinforcement learning algorithms
- average reward
- expert systems
- multi agent
- single agent
- knowledge base
- infinite horizon
- dynamic programming
- lower bound
- optimal solution