Reinforcement learning with case-based heuristics for RoboCup soccer keepaway

dc.contributor.authorCELIBERTO JUNIOR, L. A.
dc.contributor.authorMATSUURA, J. P.
dc.contributor.authorMANTARA, R. L. D.
dc.contributor.authorReinaldo Bianchi
dc.contributor.authorOrcidhttps://orcid.org/0000-0001-9097-827X
dc.date.accessioned2022-01-12T22:02:04Z
dc.date.available2022-01-12T22:02:04Z
dc.date.issued2012-10-19
dc.description.abstractIn this paper we propose to combine Case-based Reasoning and Heuristically Accelerated Reinforcement Learning to speed up a Reinforcement Learning algorithm in a Transfer Learning problem. To do so, we propose a new algorithm called SARSA Accelerated by Transfer Learning - SATL, which uses Reinforcement Learning to learn how to perform one task, stores the policy for this problem as a case-base and then uses the learned case-base as heuristics to speed up the learning performance in a related, but different, task. A set of empirical evaluations were conducted in transferring the learning between two domains with multiple agents: an expanded version of Littman's simulated robot soccer and the RoboCup Soccer Keep away. A policy learned by one agent in the Littman's soccer is used to speed up the agent learning in the Keep away soccer. The results show that the use of this new algorithm can lead to a significant improvement in the performance of the learning agents. © 2012 IEEE.
dc.description.firstpage7
dc.description.lastpage13
dc.identifier.citationCELIBERTO JUNIOR, L. A.; MATSUURA, J. P.; MANTARA, R. L. D.; BIANCHI, R. Reinforcement learning with case-based heuristics for RoboCup soccer keepaway. Proceedings - 2012 Brazilian Robotics Symposium and Latin American Robotics Symposium, SBR-LARS 2012, p. 7-13, Oct. 2012.
dc.identifier.doi10.1109/SBR-LARS.2012.9
dc.identifier.urihttps://repositorio.fei.edu.br/handle/FEI/4110
dc.relation.ispartofProceedings - 2012 Brazilian Robotics Symposium and Latin American Robotics Symposium, SBR-LARS 2012
dc.rightsAcesso Restrito
dc.subject.otherlanguageArtificial Intelligence
dc.subject.otherlanguageKnowledge based systems
dc.subject.otherlanguageMachine Learning
dc.subject.otherlanguageTransfer Learning
dc.titleReinforcement learning with case-based heuristics for RoboCup soccer keepaway
dc.typeArtigo de evento
fei.scopus.citations5
fei.scopus.eid2-s2.0-84871533285
fei.scopus.subjectAgent learning
fei.scopus.subjectEmpirical evaluations
fei.scopus.subjectKeepaway
fei.scopus.subjectLearning agents
fei.scopus.subjectLearning performance
fei.scopus.subjectMultiple agents
fei.scopus.subjectRoboCup soccer
fei.scopus.subjectSimulated robot
fei.scopus.subjectTransfer learning
fei.scopus.subjectTwo domains
fei.scopus.updated2024-05-01
fei.scopus.urlhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84871533285&origin=inward
Arquivos
Coleções