Journal article Open Access

# Stochastic Stability of Perturbed Learning Automata in Positive-Utility Games

Chasparis, Georgios

### DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<identifier identifierType="DOI">10.5281/zenodo.1186647</identifier>
<creators>
<creator>
<creatorName>Chasparis, Georgios</creatorName>
<givenName>Georgios</givenName>
<familyName>Chasparis</familyName>
<nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0003-3059-3575</nameIdentifier>
<affiliation>Software Competence Center Hagenberg GmbH</affiliation>
</creator>
</creators>
<titles>
<title>Stochastic Stability of Perturbed Learning Automata in Positive-Utility Games</title>
</titles>
<publisher>Zenodo</publisher>
<publicationYear>2018</publicationYear>
<subjects>
<subject>Learning automata, distributed optimization, stochastic stability</subject>
</subjects>
<dates>
<date dateType="Issued">2018-02-21</date>
</dates>
<resourceType resourceTypeGeneral="Text">Journal article</resourceType>
<alternateIdentifiers>
<alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/1186647</alternateIdentifier>
</alternateIdentifiers>
<relatedIdentifiers>
<relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.1186646</relatedIdentifier>
</relatedIdentifiers>
<rightsList>
<rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
</rightsList>
<descriptions>
<description descriptionType="Abstract">&lt;p&gt;This paper considers a class of reinforcement-based learning (namely, perturbed learning automata) and provides a&lt;br&gt;
stochastic-stability analysis in repeatedly-played, positive-utility, strategic-form games. Prior work in this class of learning dynamics primarily analyzes asymptotic convergence through stochastic approximations, where convergence can be associated with the limit points of an ordinary-differential equation (ODE). However, analyzing global convergence through an ODE-approximation requires the existence of a Lyapunov or a potential function, which naturally restricts the analysis to a fine class of games. To overcome these limitations, this paper introduces an alternative framework for analyzing asymptotic convergence that is based upon an explicit characterization of the invariant probability measure of the induced Markov chain. We further provide a methodology for computing the invariant probability measure in&lt;br&gt;
positive-utility games, together with an illustration in the context of coordination games.&lt;/p&gt;</description>
</descriptions>
<fundingReferences>
<fundingReference>
<funderName>European Commission</funderName>
<funderIdentifier funderIdentifierType="Crossref Funder ID">10.13039/501100000780</funderIdentifier>
<awardNumber awardURI="info:eu-repo/grantAgreement/EC/H2020/644235/">644235</awardNumber>
<awardTitle>REfactoring Parallel Heterogeneous Resource-Aware Applications  - a Software Engineering Approach</awardTitle>
</fundingReference>
</fundingReferences>
</resource>

4
15
views