Transfer Learning Heuristically Accelerated Algorithm: A Case Study with Real Robots

dc.contributor.authorCELIBERTO, L. A.
dc.contributor.authorReinaldo Bianchi
dc.contributor.authorSANTOS, P. E.
dc.contributor.authorOrcidhttps://orcid.org/0000-0001-9097-827X
dc.date.accessioned2022-01-12T21:58:34Z
dc.date.available2022-01-12T21:58:34Z
dc.date.issued2016-10-12
dc.description.abstract© 2016 IEEE.Reinforcement Learning (RL) is a successful technique for learning the solutions of control problems from an agent's interaction in its domain. However, RL is known to be inefficient for real-world applications. In this paper we propose to use a combination of case-based reasoning (CBR) and heuristically accelerated reinforcement learning methods aiming to speed up a Reinforcement Learning algorithm in a transfer learning problem. We show results of applying this method on a robot soccer domain, where the use of the proposed method led to a significant improvement in the learning rate.
dc.description.firstpage311
dc.description.lastpage316
dc.identifier.citationCELIBERTO, L. A.; BIANCHI, R.; SANTOS, P. E.; Transfer Learning Heuristically Accelerated Algorithm: A Case Study with Real Robots. Proceedings - 13th Latin American Robotics Symposium and 4th Brazilian Symposium on Robotics, LARS/SBR 2016, p. 311-316, Oct. 2016.
dc.identifier.doi10.1109/LARS-SBR.2016.59
dc.identifier.urihttps://repositorio.fei.edu.br/handle/FEI/3870
dc.relation.ispartofProceedings - 13th Latin American Robotics Symposium and 4th Brazilian Symposium on Robotics, LARS/SBR 2016
dc.rightsAcesso Restrito
dc.subject.otherlanguageHeuristically Accelerated
dc.subject.otherlanguageReinforcement Learning
dc.subject.otherlanguageTransfer Learning
dc.titleTransfer Learning Heuristically Accelerated Algorithm: A Case Study with Real Robots
dc.typeArtigo de evento
fei.scopus.citations5
fei.scopus.eid2-s2.0-85010425300
fei.scopus.subjectCasebased reasonings (CBR)
fei.scopus.subjectControl problems
fei.scopus.subjectHeuristically Accelerated
fei.scopus.subjectLearning rates
fei.scopus.subjectReal robot
fei.scopus.subjectReinforcement learning method
fei.scopus.subjectRobot soccer
fei.scopus.subjectTransfer learning
fei.scopus.updated2024-05-01
fei.scopus.urlhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85010425300&origin=inward
Arquivos
Coleções