Optimal Strategies in Perfect-Information Stochastic Games with Tail Winning Conditions
Florian HornHugo GimbertPublished in: CoRR (2008)
Keyphrases
- optimal strategy
- stochastic games
- subgame perfect equilibrium
- perfect information
- imperfect information
- game tree
- decision problems
- game theoretic
- human players
- nash equilibria
- monte carlo
- markov decision processes
- mathematical models
- expected utility
- nash equilibrium
- average reward
- reinforcement learning algorithms
- single agent
- infinite horizon
- learning automata
- state space
- board game
- computational complexity
- multi agent
- learning algorithm
- robust optimization
- game playing