"DAI meets ML" by G. Weiss (LNAI-1221)

Book Announcement:

DISTRIBUTED ARTIFICIAL INTELLIGENCE
MEETS MACHINE LEARNING

- Learning in multi-agent environments -

ed. by Gerhard Weiss
Springer-Verlag
Lecture Notes in Artificial Intelligence, Volume 1221
ISBN 3-540-62934-3, 294 pp., softcover, price DM 68 / US$ 44.95
Available around May 10, 1997

Below You Find:

General Information
Book Structure
Table of Contents
Ordering Information

klick for high resolution (186K)

General Information (from the Preface)

The intersection of distributed artificial intelligence and machine learning constitutes a relatively young but important area of research that has received steadily increasing attention in the past years. The reason for this attention is largely based on the insight that the complexity of the systems studied in distributed artificial intelligence often makes it extremely difficult or even impossible to correctly and completely specify their behavioral repertoires and their dynamics. It is therefore broadly agreed that these systems should be equipped with the ability to learn, that is, to improve their future performance on their own. This book documents current and ongoing developments in the area of learning in distributed artificial intelligence systems.

The book contains selected, revised, and extended versions of sixteen papers that were first presented at two related workshops held at the Twelfth European Conference on Artificial Intelligence (ECAI-96, Budapest, Hungary, August 11--16, 1996) and the Second International Conference on Multiagent Systems (ICMAS-96, Kyoto, Japan, December 9--13, 1996). These were the ECAI-96 workshop on ``Learning in Distributed Artificial Intelligence Systems'' (LDAIS) and the ICMAS-96 workshop on ``Learning, Interaction, and Organization in Multiagent Environments'' (LIOME). Additionally, the book contains the invited talk by Munindar Singh and Michael Huhns presented at the LDAIS workshop and an extensive Reader's Guide. The papers included in this book reflect the broad spectrum of learning in distributed artificial intelligence systems and the progress made in this area.

This book may be viewed as the successor of Weiss & Sen, eds., 1996, Adaption and Learning in Multi-Agent Systems, Lecture Notes in Artificial Intelligence Volume 1042, Springer-Verlag.

Structure of the Book (from the Reader's Guide)

The book is structured as follows:

Introduction.
This part contains an extensive reader's guide by the editor, and a valuable overview of major challenges for machine learning in cooperative information systems by Munindar Singh and Michael Huhns.
Part I: Learning, cooperation and competition.
This part includes work whose main focus is on the question how multiple agents can learn cooperative and/or competitive behavior (e.g., in order to optimally share resources or to maximize one own's profit). This work is much concerned with the development and adaptation of data-flow and control patterns that improve the interactions among several agents.
Part II: Learning about/from other agents and the world.
The main focus of the papers included in this part is on the question how learning conducted by an agent can be influenced (e.g., initiated, accelerated, re-directed, made possible at all, and so forth) by other agents. This work is much concerned with the prediction of the behavior of other agents (including their preferences, strategies, intentions, goals, etc), with the improvement and refinement of an agent's behavior by interacting with and observing other agents, and with the development of a common view of the world.
Part III: Learning, communication and understanding.
Here the papers' main focus is on the question how learning on the one hand and communication and mutual understanding on the other hand are related to each other. The work described in these papers is much concerned with the requirements on the agents' ability to effectively exchange useful information and to develop a shared meaning of the information exchanged.

(It is important to see that these parts are not orthogonal, but complement one another. For instance, agents may learn to cooperate by learning about each other's abilities, and in order to learn from one another the agents typically have to communicate.)

----- Introduction

"Reader's Guide", Gerhard Weiss, 1--10

"Challenges for Machine Learning in Cooperative Information Systems",
M. Singh and M. Huhns, 11--24

----- Part I: Learning, Cooperation and Competition

"A Modular Approach to Multi-Agent Reinforcement Learning"
N. Ono and K. Fukumoto, 25--39

" Learning Real Team Solutions",
C. Versino and L.M. Gambardella, 40--61

"Learning by Linear Anticipation in Multi-Agent Systems",
P. Davidsson, 62--72

"Learning Coordinated Behavior in a Continuous Environment",
N. Ono and Y. Fukuta, 73--81

"Multi-Agent Learning with the Success-Story Algorithm",
J. Schmidhuber and J. Zhao, 82--93

"On the Collaborative Object Search Team: A Formulation",
Y. Ye and J. Tsotsos, 94--116

"Evolution of Coordination as a Metaphor for Learning in
Multi-Agent Systems", A. Bazzan, 117--136

----- Part II: Learning About/From Other Agents and the World

"Correlating Internal Parameters and External Performance:
Learning Soccer Agents", R. Nadella and S. Sen, 137--150

"Learning Agents' Reliability Through Bayesian Conditioning:
A Simulation Experiment", A. Dragoni and Paolo Giorgini, 151--167

"A Study of Organizational Learning in Multi-Agent Systems",
M. Terabe, T. Washio, O. Katai, and T. Sawaragi, 168--179

"Cooperative Case-Based Reasoning",
E. Plaza, J. Arcos, and F. Martin, 180--201

"Contract-Net-Based Learning in a User-Adaptive Interface Agency",
B. Lenzmann and Ipke Wachsmuth, 202--222

----- Part III: Learning, Communication and Understanding

"The Communication of Inductive Inferences",
W. Davies and P. Edwards, 223--241

"Addressee Learning and Message Interception for Communication
Load Reduction in Multiple Robot Environments",
T. Ohko, K. Hiraki, and Y. Anzai, 242--258

"Learning and Communication in Multi-Agent Systems",
H. Friedrich, M. Kaiser, O. Rogalla, and R. Dillmann, 259--275

"Investigating the Effects of Explicit Epistemology on a Distributed
Learning System", N. Lacey, K. Nakata, and M. Lee, 276--292

----- Subject Index, 293--294

Ordering Information

 
Please send me [__] copies of "DISTRIBUTED ARTIFICIAL INTELLIGENCE 
MEETS MACHINE LEARNING. Learning in Multi-Agent Environments",  
edited by Gerhard Weiss, and published by Springer-Verlag as 
Lecture Notes in Artificial Intelligence Volume 1221.  
ISBN 3-540-62934-3, 294 pp., softcover, price DM 68 / US$ 44.95.  
Available around May 10, 1997. 
 
Please charge my credit card 
 
    [_] Eurocard    [_] American Express    [_] Visa    [_] Diners  
 
    Number      __ __ __ __ __  __ __ __ __  __ __ __ __  __ __ __ __  
 
 
    Valid until _____________  Signature ____________________________ 
 
 
    Title      Prof/Dr/Mr/Mrs/Ms  Surname ___________________________ 
 
    First name ______________________________________________________ 
 
    Address    ______________________________________________________ 
 
               ______________________________________________________ 
 
 
Give the completed form to your bookseller, or send to one of: 
 
    Springer-Verlag, Vertrieb   |  Springer-Verlag New York, Inc. 
    Postfach 31 13 40,          |  PO Box 2485 
    D-10643 Berlin, Germany     |  Secaucus, NJ 07096-2485, USA 
                                | 
    FAX:   (+49) 30 8207 301    |  FAX: (+1) 201 348 4033 
    EMAIL: orders@springer.de   |  TEL: 1 800 SPRINGER (Toll free in USA)

Book Announcement:

DISTRIBUTED ARTIFICIAL INTELLIGENCE MEETS MACHINE LEARNING

- Learning in multi-agent environments -

Below You Find: General Information Book Structure Table of Contents Ordering Information

General Information (from the Preface)

Structure of the Book (from the Reader's Guide)

Table of Contents

Ordering Information

DISTRIBUTED ARTIFICIAL INTELLIGENCE
MEETS MACHINE LEARNING

Below You Find:

General Information
Book Structure
Table of Contents
Ordering Information