On the optimality equation for zero-sum ergodic stochastic games.
Anna JaskiewiczAndrzej S. NowakPublished in: Math. Methods Oper. Res. (2001)
Keyphrases
- stochastic games
- average reward
- markov chain
- markov decision processes
- nash equilibria
- games with incomplete information
- optimal policy
- long run
- multiagent reinforcement learning
- multi agent
- repeated games
- reinforcement learning
- nash equilibrium
- average cost
- state space
- learning automata
- optimal solution
- incomplete information
- reinforcement learning algorithms
- policy iteration
- imperfect information
- linear programming
- dynamic programming
- np hard
- infinite horizon