A Zero-Sum Stochastic Game with Compact Action Sets and no Asymptotic Value.
Guillaume VigeralPublished in: Dyn. Games Appl. (2013)
Keyphrases
- action sets
- stochastic games
- markov decision processes
- game theory
- nash equilibria
- nash equilibrium
- boolean games
- reinforcement learning
- repeated games
- game theoretic
- finite state
- state space
- perfect information
- average reward
- reinforcement learning algorithms
- incomplete information
- monte carlo
- game playing
- optimal strategy
- cooperative
- optimal policy
- infinite horizon
- asymptotically optimal
- multi agent systems
- multi agent
- dynamic programming
- imperfect information
- average cost
- stochastic model