Learning to identify winning coalitions in the PAC model

Ariel D. Procaccia*, Jeffrey S. Rosenschein

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

We consider PAG learning of simple cooperative games, in which the coalitions are partitioned into "winning" and "losing" coalitions. We analyze the complexity of learning a suitable concept class via its Vapnik-Chervonenkis (VC) dimension, and provide an algorithm that learns this class. Furthermore, we study constrained simple games; we demonstrate that the VC dimension can be dramatically reduced when one allows only a single minimum winning coalition (even more so when this coalition has cardinality 1), whereas other interesting constraints do not significantly lower the dimension.

Original languageAmerican English
Title of host publicationProceedings of the Fifth International Joint Conference on Autonomous Agents and Multiagent Systems
Pages673-675
Number of pages3
DOIs
StatePublished - 2006
EventFifth International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS - Hakodate, Japan
Duration: 8 May 200612 May 2006

Publication series

NameProceedings of the International Conference on Autonomous Agents
Volume2006

Conference

ConferenceFifth International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
Country/TerritoryJapan
CityHakodate
Period8/05/0612/05/06

Keywords

  • Coalition formation
  • PAC learning

Fingerprint

Dive into the research topics of 'Learning to identify winning coalitions in the PAC model'. Together they form a unique fingerprint.

Cite this