<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="static/style.xsl"?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-04-05T12:38:25Z</responseDate><request verb="GetRecord" identifier="oai:www.recercat.cat:10230/46270" metadataPrefix="rdf">https://recercat.cat/oai/request</request><GetRecord><record><header><identifier>oai:recercat.cat:10230/46270</identifier><datestamp>2025-12-20T20:24:24Z</datestamp><setSpec>com_2072_6</setSpec><setSpec>col_2072_452954</setSpec></header><metadata><rdf:RDF xmlns:rdf="http://www.openarchives.org/OAI/2.0/rdf/" xmlns:ow="http://www.ontoweb.org/ontology/1#" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:ds="http://dspace.org/ds/elements/1.1/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:doc="http://www.lyncode.com/xoai" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/rdf/ http://www.openarchives.org/OAI/2.0/rdf.xsd">
   <ow:Publication rdf:about="oai:recercat.cat:10230/46270">
      <dc:title>Study of turn-taking coordination for nagents in game-theoretic scenarios, with reinforcement learning: Proposal of an evaluation framework of Perfect Alternation Equilibria for multi-agent environments</dc:title>
      <dc:creator>Papadopoulos, Nikolaos</dc:creator>
      <dc:subject>Conventionalization</dc:subject>
      <dc:subject>Game Theory</dc:subject>
      <dc:subject>Battle of the Exes</dc:subject>
      <dc:subject>Battle of the Sexes</dc:subject>
      <dc:subject>Multi-agent Battle of the Exes</dc:subject>
      <dc:subject>MBoE</dc:subject>
      <dc:subject>Repeated Games</dc:subject>
      <dc:subject>Repeated Games</dc:subject>
      <dc:subject>Stochastic Games</dc:subject>
      <dc:subject>Alternation Equilibrium</dc:subject>
      <dc:subject>n-agents</dc:subject>
      <dc:subject>Multi-Agent Reinforcement Learning</dc:subject>
      <dc:subject>Q-learning</dc:subject>
      <dc:subject>Perfect Alternation Equilibrium</dc:subject>
      <dc:subject>Perfect Alternation</dc:subject>
      <dc:subject>Fairness</dc:subject>
      <dc:subject>Efficiency</dc:subject>
      <dc:subject>Reward Fairness</dc:subject>
      <dc:subject>Multi-agent Fairness</dc:subject>
      <dc:subject>Rotation</dc:subject>
      <dc:subject>Metric</dc:subject>
      <dc:subject>Alternation Metric</dc:subject>
      <dc:subject>ALT</dc:subject>
      <dc:description>Treball fi de màster de: Master in Cognitive Systems and Interactive Media</dc:description>
      <dc:description>Directos: Martí Sànchez-Fibla, Ismael Tito Freire Gonzalez</dc:description>
      <dc:description>In this thesis, a novel performance evaluation framework is introduced for several&#xd;
dynamic multi-agent interpretations of the Battle of the Exes scenario, which are also&#xd;
proposed for the first time. The Multi-Agent BoE scenario (MBoE) was modeled as a&#xd;
Markov Game and was computationally examined in 7 branches of 2-6 and 2-10 agents’&#xd;
experiments (43 experiments) for two types of state-representations, two numbers of&#xd;
episodes and various reward systems. New variations of Fairness (Multi-agent Fairness&#xd;
&amp;amp; Reward Fairness) were proposed, with the latter being used to measure the systems’&#xd;
performance, as literature’s 2-agents metrics were found insufficient for n-agents&#xd;
games. Furthermore, a Perfect Alternation equilibrium was introduced, defined and&#xd;
evaluated, as an ideal equilibrium, robust to the number of agents and episodes of a&#xd;
system. For the purposes of this thesis, it was hypothesized and eventually shown, that a&#xd;
Fair and Efficient equilibrium in multi-agent dynamic environments such as MBoE does&#xd;
not necessarily signify Perfect Alternation. Furthermore, new types of metrics and&#xd;
indicators for measuring and evaluating the performance of a system towards Perfect&#xd;
Alternation were introduced and tested: Rotation (RT, with 2 sub-metrics and 2 forms),&#xd;
Alternation (ALT, 6 versions) and Proportional Individual Performance. ALT metrics&#xd;
definitions were found sufficient for evaluating of Perfect Alternation, thus they was&#xd;
benchmarked and tested through the series of experiments, aspiring to initiate this&#xd;
branch of studies and contribute novel tools for deeper understanding of complexsystems, such as the social behavior of cognitive systems.</dc:description>
      <dc:date>2021-01-26T11:39:23Z</dc:date>
      <dc:date>2021-01-26T11:39:23Z</dc:date>
      <dc:date>2020-07</dc:date>
      <dc:type>info:eu-repo/semantics/masterThesis</dc:type>
      <dc:rights>This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License</dc:rights>
      <dc:rights>http://creativecommons.org/licenses/by-nc-nd/4.0</dc:rights>
      <dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
   </ow:Publication>
</rdf:RDF></metadata></record></GetRecord></OAI-PMH>