Computing Equilibria with Two-Player Zero-Sum Continuous Stochastic Games with Switching Controller.
Guido BonomiNicola GattiFabio PanozzoMarcello RestelliPublished in: AAAI (2012)
Keyphrases
- stochastic games
- nash equilibria
- games with incomplete information
- repeated games
- nash equilibrium
- incomplete information
- game theory
- game theoretic
- multiagent reinforcement learning
- control system
- markov decision processes
- long run
- average reward
- learning automata
- reinforcement learning algorithms
- infinite horizon
- imperfect information
- initial state
- control strategy
- search algorithm
- state space
- lower bound