Towards social complexity reduction in multiagent learning: the adhoc approach

Michael Rovatsos, Marco Wolf

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper presents a novel method for classifying adversaries that is designed to achieve social complexity reduction in large-scale, open multiagent systems. In contrast to previous work on opponent modelling, we seek to generalise from individuals and to identify suitable opponent classes. To validate the adequacy of our approach, we present initial experiments ina multiagent Iterated Prisoner’s Dilemma seenario and we discuss directions for future work on the subject
Original languageEnglish
Title of host publicationCollaborative Learning Agents. Papers from 2002 AAAI Spring Symposium on
PublisherAAAI Press
Pages90-97
Number of pages8
Publication statusPublished - 2002

Publication series

Name AAAI Technical Report
PublisherAAAI Press
NumberSS-02-02

Fingerprint Dive into the research topics of 'Towards social complexity reduction in multiagent learning: the adhoc approach'. Together they form a unique fingerprint.

Cite this