An Evolutionary Game Theoretic Perspective on Learning in Multi-Agent Systems

Abstract

In this paper we revise Reinforcement Learning andadaptiveness in Multi-Agent Systems from an EvolutionaryGame Theoretic perspective. More precisely we show thereis a triangular relation between the fields of Multi-AgentSystems, Reinforcement Learning and Evolutionary Game Theory.We illustrate how these new insights can contribute to a betterunderstanding of learning in MAS and to new improved learningalgorithms. All three fields are introduced in a self- containedmanner. Each relation is discussed in detail with thenecessary background information to understand it, alongwith major references to relevant work