Optimality in different strategy classes in zero-sum stochastic games.
János FleschFrank ThuijsmanO. J. VriezePublished in: Math. Methods Oper. Res. (2002)
Keyphrases
- stochastic games
- average reward
- games with incomplete information
- nash equilibria
- markov decision processes
- multiagent reinforcement learning
- nash equilibrium
- learning automata
- multi agent
- optimal policy
- imperfect information
- repeated games
- long run
- infinite horizon
- single agent
- reinforcement learning algorithms
- robust optimization
- genetic algorithm
- optimal strategy
- reinforcement learning
- average cost
- game playing
- game theory
- multi agent systems