Transfer Learning Heuristically Accelerated Algorithm: A Case Study with Real Robots
Nenhuma Miniatura disponível
Citações na Scopus
5
Tipo de produção
Artigo de evento
Data
2016-10-12
Autores
CELIBERTO, L. A.
Reinaldo Bianchi
SANTOS, P. E.
Reinaldo Bianchi
SANTOS, P. E.
Orientador
Periódico
Proceedings - 13th Latin American Robotics Symposium and 4th Brazilian Symposium on Robotics, LARS/SBR 2016
Título da Revista
ISSN da Revista
Título de Volume
Citação
CELIBERTO, 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.
Texto completo (DOI)
Palavras-chave
Resumo
© 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.