Evidence Propagation and Consensus Formation in Noisy Environments: Extended Abstract

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

45 Downloads (Pure)

Abstract

We study the effectiveness of consensus formation in multi-agent systems where belief updating is an iterative two-part process, consisting of both belief updating based on direct evidence and also belief combination between agents, within the context of a best-of-n problem. Agents’ beliefs are represented within Dempster-Shafer theory by mass functions and we investigate the macro-level properties of four well-known belief combination operators: Dempster’s rule, Yager’s rule, Dubois & Prade’s operator and the averaging operator. Simulation experiments are conducted for different evidence rates and noise levels. Broadly, Dubois & Prade’s operator results in better convergence to the best state, and is more robust to noisy evidence.
Original languageEnglish
Title of host publicationthe Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems
PublisherInternational Foundation for Autonomous Agents and MultiAgent Systems
Pages1904-1906
Number of pages3
ISBN (Print)978-1-4503-6309-9
Publication statusPublished - 13 May 2019
EventInternational Conference on Autonomous Agents and Multiagent Systems - Montreal, Canada
Duration: 5 May 201917 May 2019
http://aamas2019.encs.concordia.ca/

Publication series

NameAAMAS Conference proceedings
PublisherInternational Foundation for Autonomous Agents and MultiAgent Systems
ISSN (Print)2523-5699

Conference

ConferenceInternational Conference on Autonomous Agents and Multiagent Systems
Abbreviated titleAAMAS 2019
CountryCanada
CityMontreal
Period5/05/1917/05/19
Internet address

Keywords

  • Consensus formation
  • evidence propagation
  • noisy decision-making
  • emergent behaviour
  • distributed problem solving

Fingerprint Dive into the research topics of 'Evidence Propagation and Consensus Formation in Noisy Environments: Extended Abstract'. Together they form a unique fingerprint.

Cite this