Complementarity and Diagonal Dominance in Discounted Stochastic Games.
Rabah AmirPublished in: Ann. Oper. Res. (2002)
Keyphrases
- stochastic games
- markov decision processes
- average reward
- infinite horizon
- optimal policy
- long run
- incomplete information
- multiagent reinforcement learning
- nash equilibria
- reinforcement learning algorithms
- reinforcement learning
- finite state
- finite horizon
- state space
- policy iteration
- dynamic programming
- average cost
- repeated games
- nash equilibrium
- partially observable
- model free
- cooperative
- markov chain
- expert systems
- markov decision process
- optimal control
- learning automata
- decision problems
- genetic algorithm