Cantitate/Preț
Produs

Adaptation and Learning in Multi-Agent Systems: IJCAI' 95 Workshop, Montreal, Canada, August 21, 1995. Proceedings.: Lecture Notes in Computer Science, cartea 1042

Editat de Gerhard Weiß, Sandip Sen
en Limba Engleză Paperback – 27 feb 1996
This book is based on the workshop on Adaptation and Learning in Multi-Agent Systems, held in conjunction with the International Joint Conference on Artificial Intelligence, IJCAI'95, in Montreal, Canada in August 1995.
The 14 thoroughly reviewed revised papers reflect the whole scope of current aspects in the field: they describe and analyze, both experimentally and theoretically, new learning and adaption approaches for situations in which several agents have to cooperate or compete. Also included, and aimed at the novice reader, are a comprehensive introductory survey on the area with 154 references listed and a subject index. As the first book solely devoted to this area, this volume documents the state of the art and is thus indispensable for anyone active or interested in the field.
Citește tot Restrânge

Din seria Lecture Notes in Computer Science

Preț: 39394 lei

Preț vechi: 49242 lei
-20% Nou

Puncte Express: 591

Preț estimativ în valută:
7542 8171$ 6298£

Carte tipărită la comandă

Livrare economică 12-26 decembrie

Preluare comenzi: 021 569.72.76

Specificații

ISBN-13: 9783540609230
ISBN-10: 3540609237
Pagini: 256
Ilustrații: XII, 568 p.
Dimensiuni: 155 x 235 x 13 mm
Greutate: 0.36 kg
Ediția:1996
Editura: Springer Berlin, Heidelberg
Colecția Springer
Seriile Lecture Notes in Computer Science, Lecture Notes in Artificial Intelligence

Locul publicării:Berlin, Heidelberg, Germany

Public țintă

Research

Cuprins

Adaptation and learning in multi-agent systems: Some remarks and a bibliography.- Refinement in agent groups.- Opponent modeling in multi-agent systems.- A multi-agent environment for department of defense distribution.- Mutually supervised learning in multiagent systems.- A framework for distributed reinforcement learning.- Evolving behavioral strategies in predators and prey.- To learn or not to learn .......- A user-adaptive interface agency for interaction with a virtual environment.- Learning in multi-robot systems.- Learn your opponent's strategy (in polynomial time)!.- Learning to reduce communication cost on task negotiation among multiple autonomous mobile robots.- On multiagent Q-learning in a semi-competitive domain.- Using reciprocity to adapt to others.- Multiagent coordination with learning classifier systems.