Three Perspectives on Multi-Agent Reinforcement Learning
暂无分享,去创建一个
This chapter concludes three perspectives on multi-agent reinforcement learning (MARL): (1) cooperative MARL, which performs mutual interaction between cooperative agents; (2) equilibrium-based MARL, which focuses on equilibrium solutions among gaming agents; and (3) best-response MARL, which suggests a no-regret policy against other competitive agents. Then the authors present a general framework of MARL, which combines all the three perspectives in order to assist readers in understanding the intricate relationships between different perspectives. Furthermore, a negotiation-based MARL algorithm based on meta-equilibrium is presented, which can interact with cooperative agents, games with gaming agents, and provides the best response to other competitive agents.
[1] Goran Trajkovski. On a Robotic Platform for MASIVE-Like Experiments , 2007 .
[2] Raman Paranjape,et al. Multi-Agent Systems for Healthcare Simulation and Modeling: Applications for System Improvement , 2009 .
[3] Goran Trajkovski. An Imitation-based Approach to Modeling Homogenous Agents Societies (Computational Intelligence and Its Applications Series) (Computational Intelligence and Its Applications Series) , 2006 .