Pure and Stationary Optimal Strategies in Perfect-Information Stochastic Games with Global Preferences.
Hugo GimbertWieslaw ZielonkaPublished in: CoRR (2016)
Keyphrases
- stochastic games
- optimal strategy
- subgame perfect equilibrium
- perfect information
- imperfect information
- game tree
- decision problems
- game theoretic
- monte carlo
- nash equilibria
- markov decision processes
- multi agent
- average reward
- game playing
- board game
- reinforcement learning algorithms
- learning automata
- mathematical models
- expected utility
- np hard
- search algorithm
- nash equilibrium
- incomplete information