On a new class of nonzero-sum discounted stochastic games having stationary Nash equilibrium points.
Andrzej S. NowakPublished in: Int. J. Game Theory (2003)
Keyphrases
- stochastic games
- nash equilibrium
- markov decision processes
- nash equilibria
- average reward
- game theory
- infinite horizon
- multiagent reinforcement learning
- repeated games
- game theoretic
- multi agent reinforcement learning
- optimal policy
- congestion games
- reinforcement learning
- long run
- mixed strategy
- state space
- multi agent
- cooperative
- finite state
- learning automata
- worst case
- reinforcement learning algorithms
- imperfect information
- single agent
- average cost
- objective function
- convergence rate
- pure strategy
- genetic algorithm