General Principles of Learning-Based Multi-Agent Systems

Simple item page
dc.creatorWolpert, David H.
dc.creatorWheeler, Kevin R.
dc.creatorTumer, Kagan
dc.date1999-05-10
dc.date.accessioned2026-07-07T03:24:06Z
dc.date.available2026-07-07T03:24:06Z
dc.descriptionWe consider the problem of how to design large decentralized multi-agent systems (MAS's) in an automated fashion, with little or no hand-tuning. Our approach has each agent run a reinforcement learning algorithm. This converts the problem into one of how to automatically set/update the reward functions for each of the agents so that the global goal is achieved. In particular we do not want the agents to ``work at cross-purposes'' as far as the global goal is concerned. We use the term artificial COllective INtelligence (COIN) to refer to systems that embody solutions to this problem. In this paper we present a summary of a mathematical framework for COINs. We then investigate the real-world applicability of the core concepts of that framework via two computer experiments: we show that our COINs perform near optimally in a difficult variant of Arthur's bar problem (and in particular avoid the tragedy of the commons for that problem), and we also illustrate optimal performance for our COINs in the leader-follower problem.
dc.description7 pages, 6 figures
dc.identifierhttps://arxiv.org/abs/cs/9905005
dc.identifierhttp://arxiv.org/abs/cs/9905005
dc.identifierProceedings of the Third International Conference on Autonomous Agents, Seatle, WA 1999
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/33196
dc.subjectMultiagent Systems
dc.subjectAdaptation and Self-Organizing Systems
dc.subjectStatistical Mechanics
dc.subjectDistributed, Parallel, and Cluster Computing
dc.subjectMachine Learning
dc.subjectI.2.6 ; I.2.11
dc.titleGeneral Principles of Learning-Based Multi-Agent Systems
dc.typetext

Files

Collections

arXiv