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