Arena-Independent Finite-Memory Determinacy in Stochastic Games.
Patricia BouyerYoussouf OualhadjMickael RandourPierre VandenhovePublished in: Log. Methods Comput. Sci. (2023)
Keyphrases
- stochastic games
- nash equilibria
- multiagent reinforcement learning
- markov decision processes
- nash equilibrium
- games with incomplete information
- learning automata
- multi agent
- average reward
- imperfect information
- single agent
- robust optimization
- reinforcement learning algorithms
- repeated games
- finite number
- game theory
- cooperative
- neural network