| Texto completo | |
| Autor(es): |
Bianchi, Reinaldo A. C.
[1]
;
Celiberto, Jr., Luiz A.
[2]
;
Santos, Paulo E.
[1]
;
Matsuura, Jackson P.
[3]
;
Lopez de Mantaras, Ramon
[4]
Número total de Autores: 5
|
| Afiliação do(s) autor(es): | [1] Ctr Univ FEI, BR-09850901 Sao Paulo - Brazil
[2] Univ Fed ABC UFABC, Ctr Engn Modelagem & Ciencias Sociais Aplicadas C, BR-09210580 Sao Paulo - Brazil
[3] Technol Inst Aeronaut ITA, BR-12228900 Sao Paulo - Brazil
[4] CSIC, IIIA Artificial Intelligence Res Inst, Spanish Natl Res Council, Bellaterra 08193, Catalonia - Spain
Número total de Afiliações: 4
|
| Tipo de documento: | Artigo Científico |
| Fonte: | ARTIFICIAL INTELLIGENCE; v. 226, p. 102-121, SEP 2015. |
| Citações Web of Science: | 24 |
| Resumo | |
The goal of this paper is to propose and analyse a transfer learning meta-algorithm that allows the implementation of distinct methods using heuristics to accelerate a Reinforcement Learning procedure in one domain (the target) that are obtained from another (simpler) domain (the source domain). This meta-algorithm works in three stages: first, it uses a Reinforcement Learning step to learn a task on the source domain, storing the knowledge thus obtained in a case base; second, it does an unsupervised mapping of the source-domain actions to the target-domain actions; and, third, the case base obtained in the first stage is used as heuristics to speed up the learning process in the target domain. A set of empirical evaluations were conducted in two target domains: the 3D mountain car (using a learned case base from a 2D simulation) and stability learning for a humanoid robot in the Robocup 3D Soccer Simulator (that uses knowledge learned from the Acrobot domain). The results attest that our transfer learning algorithm outperforms recent heuristically-accelerated reinforcement learning and transfer learning algorithms. (C) 2015 Elsevier B.V. All rights reserved. (AU) | |
| Processo FAPESP: | 11/19280-8 - CogBot: integrando informação perceptual e conhecimento semântico na robótica cognitiva |
| Beneficiário: | Anna Helena Reali Costa |
| Modalidade de apoio: | Auxílio à Pesquisa - Regular |
| Processo FAPESP: | 12/04089-3 - Raciocínio espacial colaborativo para múltiplos robôs |
| Beneficiário: | Paulo Eduardo Santos |
| Modalidade de apoio: | Auxílio à Pesquisa - Regular |
| Processo FAPESP: | 12/14010-5 - Transferência de Aprendizado para Robôs Heterogêneos |
| Beneficiário: | Luiz Antonio Celiberto Junior |
| Modalidade de apoio: | Bolsas no Brasil - Pós-Doutorado |