A Potential Reduction Algorithm for Ergodic Two-Person Zero-Sum Limiting Average Payoff Stochastic Games.
Endre BorosKhaled M. ElbassioniVladimir GurvichKazuhisa MakinoPublished in: COCOA (2014)
Keyphrases
- stochastic games
- repeated games
- nash equilibrium
- nash equilibria
- markov decision processes
- game theory
- multiagent reinforcement learning
- games with incomplete information
- multi agent
- markov chain
- learning automata
- reinforcement learning algorithms
- incomplete information
- robust optimization
- average reward
- imperfect information
- single agent
- infinite horizon