Title: | General Principles of Learning-Based Multi-Agent Systems |

Author: | David Wolpert, Kevin Wheeler, and Kagan Tumer |

Book Tittle: | Proceedings of the Third International Conference on Automomous Agents |

Pages: | 77--83 |

Year: | 1999 |

Abstract: | We 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. |

Cited by 43

@InProceedings{wolpert99b, author = {David Wolpert and Kevin Wheeler and Kagan Tumer}, title = {General Principles of Learning-Based Multi-Agent Systems}, googleid = {PG9fDQwTqX0J:scholar.google.com/}, booktitle = {Proceedings of the Third International Conference on Automomous Agents}, year = 1999, pages = {77--83}, address = {Seattle, WA}, abstract = {We 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. }, keywords = {multiagent learning}, url = {http://jmvidal.cse.sc.edu/library/wolpert99b.pdf}, cluster = {9054789468289986364} }Last modified: Wed Mar 9 10:14:41 EST 2011