Influence-optimistic local values for multiagent planning

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

2 Citations (Scopus)

Abstract

Over the last decade, methods for multiagent planning under uncertainty have increased in scalability. However, many methods assume value factorization or are not able to provide quality guarantees. We propose a novel family of influence-optimistic upper bounds on the optimal value for problems with lOOs of agents that do not exhibit value fec-torization.

Original languageEnglish
Title of host publicationAAMAS 2015 - Proceedings of the 2015 International Conference on Autonomous Agents and Multiagent Systems
PublisherInternational Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
Pages1703-1704
Number of pages2
Volume3
ISBN (Electronic)9781450337717
Publication statusPublished - 1 Jan 2015
EventAAMAS 2015: 14th International Conference on Autonomous Agents and Multiagent Systems - Istanbul, Turkey
Duration: 4 May 20158 May 2015
Conference number: 14

Conference

ConferenceAAMAS 2015: 14th International Conference on Autonomous Agents and Multiagent Systems
Abbreviated titleAAMAS 2015
CountryTurkey
CityIstanbul
Period4/05/158/05/15

Keywords

  • Factored Dec-POMDPs
  • Multi-agent planning

Fingerprint Dive into the research topics of 'Influence-optimistic local values for multiagent planning'. Together they form a unique fingerprint.

Cite this