Stochastic games with non-observable actions.
János FleschFrank ThuijsmanO. J. VriezePublished in: Math. Methods Oper. Res. (2003)
Keyphrases
- worst case
- stochastic games
- multiagent reinforcement learning
- nash equilibrium
- repeated games
- state action
- nash equilibria
- upper bound
- learning agent
- multi agent
- markov decision processes
- multiagent systems
- reinforcement learning algorithms
- robust optimization
- learning automata
- state transitions
- game theoretic
- infinite horizon
- single agent
- incomplete information
- cooperative
- average reward
- game theory
- reinforcement learning