Limit Optimal Trajectories in Zero-Sum Stochastic Games.
Sylvain SorinGuillaume VigeralPublished in: Dyn. Games Appl. (2020)
Keyphrases
- stochastic games
- average reward
- nash equilibria
- games with incomplete information
- markov decision processes
- multiagent reinforcement learning
- nash equilibrium
- multi agent
- dynamic programming
- reinforcement learning algorithms
- learning automata
- worst case
- long run
- single agent
- linear programming
- incomplete information
- optimal control
- robust optimization
- optimal strategy
- imperfect information
- dynamical systems
- optimal policy
- np hard