Lecture Notes in Artificial Intelligence, Volume 1042
ISBN 3-540-60923-7, 238 pp., index, softcover, US$ 43.00 / DM 54.00
Available around March 15, 1996 (Europe) / March 25, 1996 (North America)
Adaption and learning in multi-agent systems establishes a relatively new but significant topic in Artificial Intelligence (AI). Multi-agent systems typically are very complex and hard to specify in their behavior. It is therefore broadly agreed in both the Distributed AI and the Machine Learning community that there is the need to endow these systems with the ability to adapt and learn, that is, to self-improve their future performance. Despite this agreement, however, adaption and learning in multi-agent systems has been widely neglected in AI until a few years ago. On the one hand, work in Distributed AI mainly concentrated on developing multi-agent systems whose activity repertoires and coordination mechanisms are more or less fixed and thus less robust and effective particularly in changing environments. On the other hand, work in Machine Learning mainly concentrated on learning techniques and methods in single-agent or isolated-system settings. Today this situation has changed considerably, and there is an increasing number of researchers focussing on the intersection of Distributed AI and Machine Learning.
This is the first available book on adaption and learning in multi-agent systems. It is intended to serve as a valuable reference for all researchers and practitioners interested in Distributed AI and/or Machine Learning, and to foster further investigations on this increasingly important topic. The book contains the revised and extended versions of fourteen papers that were first presented at the workshop on ``Adaptation and Learning in Multi-Agent Systems'' held August 21, 1995 in Montreal, Canada, as part of the 14th International Joint Conference on Artificial Intelligence (IJCAI-95). The papers reflect both the broad spectrum of and the progress made in the available work on learning and adaption in multi-agent systems. They address this topic from different points of view, and describe and experimentally and/or theoretically analyze new adaption and learning approaches for situations in which several agents have to cooperate or to compete with each other in order to solve a given task or set of tasks. Additionally, to assist the novice reader, an introductory and motivational article is included which provides a compact guide to this topic. This article takes a general look at multi-agent systems and at adaption and learning therein, and offers an extensive and interdisciplinary list of pointers to relevant and related work.
Table of Contents:
This and other information on this book is also available via ftp: klick here.
Updated information (May 1997): Those interested in multi-agent learning are also refered to G. Weiss, ed., 1997, Distributed Artificial Intelligence Meets Machine Learning, Lecture Notes in Artificial Intelligence Volume 1221, Springer-Verlag.
To order copies of this book, use this form:
Please send me [_] copies of ADAPTION AND LEARNING IN MULTI-AGENT SYSTEMS, edited by Gerhard Weiss and Sandip Sen, published by Springer-Verlag (Lecture Notes in Artificial Intelligence, Volume 1042), ISBN 3-540-60923-7, March 1996.
[_] Please bill me
[_] Please charge my credit card
[_] Euro/MasterCard [_] American Express [_] Visa [_] Diners
Postfach 31 13 40, D-10643
FAX: (+49) 30 8207 301
Springer-Verlag New York, Inc.
PO Box 2485
Secaucus, NJ 07096-2485, USA
FAX: (+1) 201 348 4033
TEL: 1 800 777 4647 (Toll free in USA)