Heuristically Accelerated Reinforcement Learning by Means of Case-Based Reasoning and Transfer Learning

Página do item simplificado
dc.contributor.authorBianchi R.A.C.
dc.contributor.authorSantos P.E.
dc.contributor.authorda Silva I.J.
dc.contributor.authorCeliberto L.A.
dc.contributor.authorLopez de Mantaras R.
dc.date.accessioned2019-08-19T23:45:19Z
dc.date.available2019-08-19T23:45:19Z
dc.date.issued2018
dc.description.abstract© 2017, Springer Science+Business Media B.V.Reinforcement Learning (RL) is a well-known technique for learning the solutions of control problems from the interactions of an agent in its domain. However, RL is known to be inefficient in problems of the real-world where the state space and the set of actions grow up fast. Recently, heuristics, case-based reasoning (CBR) and transfer learning have been used as tools to accelerate the RL process. This paper investigates a class of algorithms called Transfer Learning Heuristically Accelerated Reinforcement Learning (TLHARL) that uses CBR as heuristics within a transfer learning setting to accelerate RL. The main contributions of this work are the proposal of a new TLHARL algorithm based on the traditional RL algorithm Q(λ) and the application of TLHARL on two distinct real-robot domains: a robot soccer with small-scale robots and the humanoid-robot stability learning. Experimental results show that our proposed method led to a significant improvement of the learning rate in both domains.
dc.description.firstpage301
dc.description.issuenumber2
dc.description.lastpage312
dc.description.volume91
dc.identifier.citationBianchi, Reinaldo A. C.; Santos, Paulo E.; DA SILVA, ISAAC J.; CELIBERTO, LUIZ A.; LOPEZ DE MANTARAS, RAMON. Heuristically Accelerated Reinforcement Learning by Means of Case-Based Reasoning and Transfer Learning. JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS, v. 1, p. 1, 2017.
dc.identifier.doi10.1007/s10846-017-0731-2
dc.identifier.issn1573-0409
dc.identifier.urihttps://repositorio.fei.edu.br/handle/FEI/1211
dc.relation.ispartofJournal of Intelligent and Robotic Systems: Theory and Applications
dc.rightsAcesso Restrito
dc.subject.otherlanguageCase-based reasoning
dc.subject.otherlanguageReinforcement learning
dc.subject.otherlanguageRobotics
dc.subject.otherlanguageTransfer learning
dc.titleHeuristically Accelerated Reinforcement Learning by Means of Case-Based Reasoning and Transfer Learning
dc.typeArtigo
fei.scopus.citations14
fei.scopus.eid2-s2.0-85032696272
fei.scopus.subjectCasebased reasonings (CBR)
fei.scopus.subjectControl problems
fei.scopus.subjectHumanoid robot
fei.scopus.subjectLearning rates
fei.scopus.subjectReal robot
fei.scopus.subjectRobot soccer
fei.scopus.subjectSmall scale
fei.scopus.subjectTransfer learning
fei.scopus.updated2024-03-04
fei.scopus.urlhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85032696272&origin=inward
Arquivos
Coleções
Artigos