Accelerating autonomous learning by using heuristic selection of actions

Página do item simplificado
dc.contributor.authorBianchi R.A.C.
dc.contributor.authorRibeiro C.H.C.
dc.contributor.authorCosta A.H.R.
dc.date.accessioned2019-08-19T23:45:21Z
dc.date.available2019-08-19T23:45:21Z
dc.date.issued2008
dc.description.abstractThis paper investigates how to make improved action selection for online policy learning in robotic scenarios using reinforcement learning (RL) algorithms. Since finding control policies using any RL algorithm can be very time consuming, we propose to combine RL algorithms with heuristic functions for selecting promising actions during the learning process. With this aim, we investigate the use of heuristics for increasing the rate of convergence of RL algorithms and contribute with a new learning algorithm, Heuristically Accelerated Q-learning (HAQL), which incorporates heuristics for action selection to the Q-Learning algorithm. Experimental results on robot navigation show that the use of even very simple heuristic functions results in significant performance enhancement of the learning rate. © 2007 Springer Science+Business Media, LLC.
dc.description.firstpage135
dc.description.issuenumber2
dc.description.lastpage168
dc.description.volume14
dc.identifier.citationBIANCHI, R. A. C.; Ribeiro, Carlos H. C.; COSTA, Anna Helena Reali. Accelerating autonomous learning by using heuristic selection of actions. Journal of Heuristics, v. 14, p. 135-168, 2008.
dc.identifier.doi10.1007/s10732-007-9031-5
dc.identifier.issn1381-1231
dc.identifier.urihttps://repositorio.fei.edu.br/handle/FEI/1232
dc.relation.ispartofJournal of Heuristics
dc.rightsAcesso Restrito
dc.subject.otherlanguageAction selection
dc.subject.otherlanguageHeuristic function
dc.subject.otherlanguageReinforcement learning
dc.subject.otherlanguageRobot navigation
dc.titleAccelerating autonomous learning by using heuristic selection of actions
dc.typeArtigo
fei.scopus.citations65
fei.scopus.eid2-s2.0-41249102188
fei.scopus.subjectControl policies
fei.scopus.subjectHeuristic selection
fei.scopus.subjectLearning processes
fei.scopus.subjectRobot navigation
fei.scopus.updated2024-03-04
fei.scopus.urlhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=41249102188&origin=inward
Arquivos
Coleções
Artigos