Zero-Sum Ergodic Stochastic Games with Feller Transition Probabilities.
Anna JaskiewiczAndrzej S. NowakPublished in: SIAM J. Control. Optim. (2006)
Keyphrases
- stochastic games
- transition probabilities
- markov chain
- average reward
- nash equilibria
- random walk
- games with incomplete information
- state space
- markov decision processes
- markov model
- reinforcement learning algorithms
- multiagent reinforcement learning
- repeated games
- markov models
- reward function
- multi agent
- learning automata
- imperfect information
- nash equilibrium
- robust optimization
- learning agent
- markov decision process
- incomplete information
- hidden markov models
- pairwise
- cooperative
- random variables