Sigmoid-weighted linear units for neural network function approximation in reinforcement learning.

Elfwing, Stefan; Uchibe, Eiji; Doya, Kenji

Elfwing, Stefan; Uchibe, Eiji; Doya, Kenji.

Afiliação

Elfwing S; Department of Brain Robot Interface, ATR Computational Neuroscience Laboratories, 2-2-2 Hikaridai, Seikacho, Soraku-gun, Kyoto 619-0288, Japan. Electronic address: elfwing@atr.jp.
Uchibe E; Department of Brain Robot Interface, ATR Computational Neuroscience Laboratories, 2-2-2 Hikaridai, Seikacho, Soraku-gun, Kyoto 619-0288, Japan; Okinawa Institute of Science and Technology Graduate University, 1919-1 Tancha, Onna-son, Okinawa 904-0495, Japan. Electronic address: uchibe@atr.jp.
Doya K; Okinawa Institute of Science and Technology Graduate University, 1919-1 Tancha, Onna-son, Okinawa 904-0495, Japan. Electronic address: doya@oist.jp.

Neural Netw ; 107: 3-11, 2018 Nov.

Article em En | MEDLINE | ID: mdl-29395652

Assuntos

Aprendizado Profundo; Redes Neurais de Computação

Palavras-chave

Atari 2600; Deep learning; Function approximation; Reinforcement learning; Sigmoid-weighted linear unit; Tetris

Texto completo

Imprimir

XML

PubMed Links

Buscar no Google

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Redes Neurais de Computação / Aprendizado Profundo Idioma: En Revista: Neural Netw Assunto da revista: NEUROLOGIA Ano de publicação: 2018 Tipo de documento: Article

Texto completo

Imprimir

XML

PubMed Links

Buscar no Google