Advice Taking in Multiagent Reinforcement Learning

Michael Rovatsos, Alexandros Belesiotis

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

Abstract

This paper proposes the β-WoLF algorithm for multiagent reinforcement learning (MARL) that uses an additional "advice" signal to inform agents about mutually beneficial forms of behaviour. β-WoLF is an extension of the WoLF-PHC algorithm that allows agents to assess whether the advice obtained through this additional reward signal is (i) useful for the learning agent itself and (ii) currently being followed by other agents in the system. We report on experimental results obtained with this novel algorithm which indicate that it enables cooperation in scenarios in which the need to defend oneself against exploitation results in poor coordination using existing MARL algorithms.
Original languageEnglish
Title of host publicationAAMAS '07 Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems
Place of PublicationNew York, NY, USA
PublisherACM
Pages1342-1344
Number of pages3
ISBN (Print)978-81-904262-7-5
DOIs
Publication statusPublished - May 2007

Keywords

  • communication, multiagent reinforcement learning

Fingerprint Dive into the research topics of 'Advice Taking in Multiagent Reinforcement Learning'. Together they form a unique fingerprint.

Cite this