Definable Zero-Sum Stochastic Games.
Jérôme BolteStéphane GaubertGuillaume VigeralPublished in: Math. Oper. Res. (2015)
Keyphrases
- stochastic games
- games with incomplete information
- nash equilibria
- markov decision processes
- average reward
- reinforcement learning algorithms
- multiagent reinforcement learning
- multi agent
- first order logic
- repeated games
- learning automata
- nash equilibrium
- reinforcement learning
- imperfect information
- robust optimization
- expert systems
- learning algorithm
- infinite horizon
- long run
- situation calculus
- state space
- dynamic programming