A Potential Reduction Algorithm for Two-person Zero-sum Mean Payoff Stochastic Games.
Endre BorosKhaled M. ElbassioniVladimir GurvichKazuhisa MakinoPublished in: CoRR (2015)
Keyphrases
- stochastic games
- repeated games
- nash equilibrium
- nash equilibria
- games with incomplete information
- markov decision processes
- multiagent reinforcement learning
- multi agent
- game theory
- incomplete information
- imperfect information
- average reward
- reinforcement learning algorithms
- learning automata
- game theoretic
- monte carlo
- knowledge based systems