Distributed Planning in Stochastic Games with Communication

This paper treats the problem of distributed planning in general-sum stochastic games with communication when the model is known. Our main contribution is a novel, game theoretic approach to the problem of distributed equilibrium computation and selection. We show theoretically and via experiments that our approach, when adopted by all agents, facilitates an efficient distributed equilibrium computation and leads to a unique equilibrium selection in general-sum stochastic games with communication.

• Type: Conference
• Year: 2008
• Where: ICMLA
• Authors: Andriy Burkov, Brahim Chaib-draa
• Keywords: Efficient Distributed Equilibrium, Equilibrium Computation, General-sum Stochastic Games, ICMLA 2008, Machine Learning