Using cases as heuristics in reinforcement learning: A transfer learning application

Página do item simplificado
dc.contributor.authorCELIBERTO JUNIOR, L. A.
dc.contributor.authorMATSUURA, J. P.
dc.contributor.authorDE MANTARAS, R. L.
dc.contributor.authorReinaldo Bianchi
dc.contributor.authorOrcidhttps://orcid.org/0000-0001-9097-827X
dc.date.accessioned2022-01-12T22:03:05Z
dc.date.available2022-01-12T22:03:05Z
dc.date.issued2011-07-02
dc.description.abstractIn this paper we propose to combine three AI techniques to speed up a Reinforcement Learning algorithm in a Transfer Learning problem: Case-based Reasoning, Heuristically Accelerated Reinforcement Learning and Neural Networks. To do so, we propose a new algorithm, called L3, which works in 3 stages: in the first stage, it uses Reinforcement Learning to learn how to perform one task, and stores the optimal policy for this problem as a case-base; in the second stage, it uses a Neural Network to map actions from one domain to actions in the other domain and; in the third stage, it uses the case-base learned in the first stage as heuristics to speed up the learning performance in a related, but different, task. The RL algorithm used in the first phase is the Q-learning and in the third phase is the recently proposed Case-based Heuristically Accelerated Q-learning. A set of empirical evaluations were conducted in transferring the learning between two domains, the Acrobot and the Robocup 3D: the policy learned during the solution of the Acrobot Problem is transferred and used to speed up the learning of stability policies for a humanoid robot in the Robocup 3D simulator. The results show that the use of this algorithm can lead to a significant improvement in the performance of the agent.
dc.description.firstpage1211
dc.description.lastpage1217
dc.identifier.citationCELIBERTO JUNIOR, L. A.; MATSUURA, J. P.; DE MANTARAS, R. L.; BIANCHI, R. Using cases as heuristics in reinforcement learning: A transfer learning application. IJCAI International Joint Conference on Artificial Intelligence. p. 1211-1217, July, 2011.
dc.identifier.doi10.5591/978-1-57735-516-8/IJCAI11-206
dc.identifier.issn1045-0823
dc.identifier.urihttps://repositorio.fei.edu.br/handle/FEI/4180
dc.relation.ispartofIJCAI International Joint Conference on Artificial Intelligence
dc.rightsAcesso Restrito
dc.titleUsing cases as heuristics in reinforcement learning: A transfer learning application
dc.typeArtigo de evento
fei.scopus.citations25
fei.scopus.eid2-s2.0-84871606206
fei.scopus.subjectAI techniques
fei.scopus.subjectEmpirical evaluations
fei.scopus.subjectHumanoid robot
fei.scopus.subjectLearning performance
fei.scopus.subjectOptimal policies
fei.scopus.subjectThird phase
fei.scopus.subjectTransfer learning
fei.scopus.subjectTwo domains
fei.scopus.updated2024-07-01
fei.scopus.urlhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84871606206&origin=inward
Arquivos
Coleções
Artigos