Analysing Congestion Problems in Multi-agent Reinforcement Learning

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

8 Citations (Scopus)
48 Downloads (Pure)

Abstract

We extend the study of congestion problems to a more realistic scenario, the Road Network Domain (RND), where the resources are no longer independent, but rather part of a network, thus choosing one path will also impact the load of another one having common road segments. We demonstrate the application of state-of-the-art multi-agent reinforcement learning methods for this new congestion model and analyse their performance. RND allows us to highlight an important limitation of resource abstraction and show that the difference rewards approach manages to better capture and inform the agents about the dynamics of the environment.

Original languageEnglish
Title of host publication16th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2017
EditorsEdmund Durfee, Michael Winikoff, Kate Larson, Sanmay Das
Pages1705-1707
Number of pages3
Volume3
ISBN (Electronic)9781510855076
Publication statusPublished - 8 May 2017
Event16th International Conference on Autonomous Agents and Multiagent Systems: AAMAS 2017 - WTC Sao Paulo, Sao Paolo, Brazil
Duration: 8 May 201712 May 2017
http://www.aamas2017.org

Conference

Conference16th International Conference on Autonomous Agents and Multiagent Systems
Abbreviated titleAAMAS 2017
Country/TerritoryBrazil
CitySao Paolo
Period8/05/1712/05/17
Internet address

Keywords

  • Congestion problems
  • Multi-agent reinforcement learning
  • Resource abstraction

Fingerprint

Dive into the research topics of 'Analysing Congestion Problems in Multi-agent Reinforcement Learning'. Together they form a unique fingerprint.

Cite this