A nonlinear hidden layer enables actor-critic agents to learn multiple paired association navigation.

Kumar, M Ganesh; Tan, Cheston; Libedinsky, Camilo; Yen, Shih-Cheng; Tan, Andrew Y Y

Kumar, M Ganesh; Tan, Cheston; Libedinsky, Camilo; Yen, Shih-Cheng; Tan, Andrew Y Y.

Afiliação

Kumar MG; Integrative Sciences and Engineering Programme, NUS Graduate School, National University of Singapore, Singapore 119077, Singapore.
Tan C; The N.1 Institute for Health, National University of Singapore, Singapore 117456, Singapore.
Libedinsky C; Innovation and Design Programme, Faculty of Engineering, National University of Singapore, Singapore 117579, Singapore.
Yen SC; Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore 138632, Singapore.
Tan AYY; Integrative Sciences and Engineering Programme, NUS Graduate School, National University of Singapore, Singapore 119077, Singapore.

Cereb Cortex ; 32(18): 3917-3936, 2022 09 04.

Article em En | MEDLINE | ID: mdl-35034127

Assuntos

Aprendizagem; Modelos Neurológicos; Reforço Psicológico; Recompensa

Palavras-chave

Hebbian plasticity; reinforcement learning; temporal difference error

Texto completo

Imprimir

XML

PubMed Links

Buscar no Google

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Aprendizagem / Modelos Neurológicos Tipo de estudo: Risk_factors_studies Idioma: En Revista: Cereb Cortex Assunto da revista: CEREBRO Ano de publicação: 2022 Tipo de documento: Article País de afiliação: Singapura

Texto completo

Imprimir

XML

PubMed Links

Buscar no Google