Simplifying optimal strategies in limsup and liminf stochastic games.
János FleschArkadi PredtetchinskiWilliam D. SudderthPublished in: Discret. Appl. Math. (2018)
Keyphrases
- optimal strategy
- stochastic games
- decision problems
- nash equilibria
- monte carlo
- markov decision processes
- single agent
- multiagent reinforcement learning
- mathematical models
- learning automata
- repeated games
- imperfect information
- multi agent
- nash equilibrium
- expected utility
- reinforcement learning algorithms
- average reward
- infinite horizon
- robust optimization
- game tree
- machine learning
- learning agent
- utility function
- mathematical model
- state space
- cooperative
- artificial intelligence