A decomposition approach for undiscounted two-person zero-sum stochastic games.
Zeynep Müge AvsarMelike Baykal-GürsoyPublished in: Math. Methods Oper. Res. (1999)
Keyphrases
- stochastic games
- nash equilibria
- games with incomplete information
- markov decision processes
- multi agent
- multiagent reinforcement learning
- learning automata
- average reward
- reinforcement learning algorithms
- nash equilibrium
- robust optimization
- game theory
- repeated games
- cooperative
- solving problems
- infinite horizon
- single agent
- learning agent
- learning algorithm