A reinforcement learning algorithm acquires demonstration from the training agent by dividing the task space.

Zu, Lipeng; He, Xiao; Yang, Jia; Liu, Lianqing; Wang, Wenxue

Zu, Lipeng; He, Xiao; Yang, Jia; Liu, Lianqing; Wang, Wenxue.

Afiliação

Zu L; State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, 110016, China; Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, 110169, China; University of Chinese Academy of Sciences, Beijing, 100049, China.
He X; State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, 110016, China; Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, 110169, China; University of Chinese Academy of Sciences, Beijing, 100049, China.
Yang J; State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, 110016, China; Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, 110169, China; University of Chinese Academy of Sciences, Beijing, 100049, China.
Liu L; State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, 110016, China; Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, 110169, China.
Wang W; State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, 110016, China; Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, 110169, China. Electronic address: wangwenxue@sia.cn.

Neural Netw ; 164: 419-427, 2023 Jul.

Article em En | MEDLINE | ID: mdl-37187108

Assuntos

Algoritmos; Inteligência Artificial; Reforço Psicológico; Recompensa

Palavras-chave

Reinforcement learning; Robotic grasping; Self-imitation learning; Sparse reward function; Task space division

Texto completo

Adicionar na Minha BVS

Imprimir

XML

PubMed Links

Buscar no Google

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Algoritmos / Inteligência Artificial Tipo de estudo: Prognostic_studies Idioma: En Revista: Neural Netw Assunto da revista: NEUROLOGIA Ano de publicação: 2023 Tipo de documento: Article País de afiliação: China País de publicação: Estados Unidos

Texto completo

Adicionar na Minha BVS

Imprimir

XML

PubMed Links

Buscar no Google