A Potential Reduction Algorithm for Two-Person Zero-Sum Mean Payoff Stochastic Games.
Endre BorosKhaled M. ElbassioniVladimir GurvichKazuhisa MakinoPublished in: Dyn. Games Appl. (2018)
Keyphrases
- stochastic games
- repeated games
- nash equilibrium
- nash equilibria
- game theory
- multiagent reinforcement learning
- games with incomplete information
- markov decision processes
- incomplete information
- learning automata
- infinite horizon
- average reward
- game theoretic
- multi agent
- single agent
- reinforcement learning algorithms
- neural network
- imperfect information
- resource allocation
- cooperative
- genetic algorithm