| Texto completo | |
| Autor(es): |
Bianchi, Reinaldo A. C.
;
Santos, Paulo E.
;
da Silva, Isaac J.
;
Celiberto, Luiz A., Jr.
;
de Mantaras, Ramon Lopez
Número total de Autores: 5
|
| Tipo de documento: | Artigo Científico |
| Fonte: | JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS; v. 91, n. 2, p. 12-pg., 2018-08-01. |
| Resumo | |
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(lambda) 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. (AU) | |
| Processo FAPESP: | 16/21047-3 - ALIS: Aprendizado Autônomo em Sistemas Inteligentes |
| Beneficiário: | Anna Helena Reali Costa |
| Modalidade de apoio: | Auxílio à Pesquisa - Regular |
| Processo FAPESP: | 16/18792-9 - Descrição, representação e solução de jogos espaciais |
| Beneficiário: | Paulo Eduardo Santos |
| Modalidade de apoio: | Auxílio à Pesquisa - Parceria para Inovação Tecnológica - PITE |