Zero-Sum Stochastic Games in Borel Spaces: Average Payoff Criteria.
Onésimo Hernández-LermaJean B. LasserrePublished in: SIAM J. Control. Optim. (2000)
Keyphrases
- stochastic games
- markov decision processes
- repeated games
- nash equilibrium
- average cost
- nash equilibria
- games with incomplete information
- average reward
- game theory
- reinforcement learning algorithms
- multi agent
- multiagent reinforcement learning
- finite state
- learning automata
- incomplete information
- policy iteration
- state space
- reinforcement learning
- single agent
- dynamic programming
- robust optimization
- markov decision process
- optimal policy
- learning agent
- upper bound
- imperfect information