Switching dynamics of multi-agent learning

P. Vrancx, K.P. Tuyls, R. Westra

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

    24 Citations (Scopus)

    Abstract

    This paper presents the dynamics of multi-agent reinforcement learning in multiple state problems. We extend previous work that formally modelled the relation between reinforcement learning agents and replicator dynamics in stateless multi-agent games. More precisely, in this work we use a combination of replicator dynamics and switching dynamics to model multi-agent learning automata in multi-state games. This is the first time that the dynamics of problems with more than one state is considered with replicator equations. Previously, it was unclear how the replicator dynamics of stateless games had to be extended to account for multiple states. We use our model to visualize the basin of attraction of the learning agents and the boundaries of switching dynamics at which an agent possibly arrives in a new dynamical system. Our model allows to analyze and predict the behavior of the different learning agents in a wide variety of multi-state problems. In our experiments we illustrate this powerful method in two games with two agents and two states.
    Original languageEnglish
    Title of host publicationProceedings of the Seventh International Conference on Autonomous Agents and Multi-Agent Systems, AAMAS'08, Estoril, Portugal.
    Place of PublicationNew York
    PublisherAssociation for Computing Machinery, Inc
    Pages307-314
    Volume1
    ISBN (Print)978-0-9817381-0-9
    Publication statusPublished - 2008
    Event7th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2008), May 12-16, 2008, Estoril, Portugal - Estoril, Portugal
    Duration: 12 May 200816 May 2008

    Conference

    Conference7th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2008), May 12-16, 2008, Estoril, Portugal
    Abbreviated titleAAMAS 2008
    Country/TerritoryPortugal
    CityEstoril
    Period12/05/0816/05/08
    Other

    Fingerprint

    Dive into the research topics of 'Switching dynamics of multi-agent learning'. Together they form a unique fingerprint.

    Cite this