作者: Raymond Chiong , Sandeep Dhakal , Lubo Jankovic
DOI: 10.1007/978-3-540-77226-2_95
关键词:
摘要: In multi-agent systems, complex and dynamic interactions often emerge among individual agents. The ability of each agent to learn adaptively is therefore important for them survive in such changing environment. this paper, we consider the effects neighbourhood structure on evolution cooperative behaviour N-Player Iterated Prisoner's Dilemma (NIPD). We simulate NIPD as a bidding game two dimensional grid-world, where has bid against its neighbours based chosen strategy. conduct experiments with three different types structures, namely triangular structure, rectangular random pairing structure. Our results show that cooperation does under but defection prevails well