Tim Baarslag

Exploring the Strategy Space of Negotiating Agents

A Framework for Bidding, Learning and Accepting in Automated Negotiation

• Broschiertes Buch

Produktbeschreibung

This book reports on an outstanding thesis that has significantlyadvanced the state-of-the-art in the area of automated negotiation. It givesnew practical and theoretical insights into the design and evaluation ofautomated negotiators. It describes an innovative negotiating agent frameworkthat enables systematic exploration of the space of possible negotiationstrategies by recombining different agent components. Using this framework, newand effective ways are formulated for an agent to learn, bid, and accept duringa negotiation. The findings have been evaluated in four annual instantiationsof the International Automated Negotiating Agents Competition (ANAC), theresults of which are also outlined here. The book also describes severalmethodologies for evaluating and comparing negotiation strategies andcomponents, with a special emphasis on performance and accuracy measures.

Produktdetails

• Springer Theses
• Verlag: Springer / Springer International Publishing / Springer, Berlin
• Artikelnr. des Verlages: 978-3-319-80305-0
• Softcover reprint of the original 1st ed. 2016
• Seitenzahl: 300
• Erscheinungstermin: 30. März 2018
• Englisch
• Abmessung: 235mm x 155mm x 17mm
• Gewicht: 462g
• ISBN-13: 9783319803050
• ISBN-10: 3319803050
• Artikelnr.: 53583351

Inhaltsangabe

Introduction.- Background.- A Component-based Architecture to Explore the Space of Negotiation Strategies.- Effective Acceptance Conditions.- Accepting Optimally with Incomplete Information.- Measuring the Performance of Online Opponent Models.- Predicting the Performance of Opponent Models.- A Quantitative Concession-Based Classification Method of Bidding Strategies.- Optimal Non-adaptive Concession Strategies.- Putting the Pieces Together.- Conclusion.