A novel modular Q-learning architecture to improve performance under incomplete learning in a grid soccer game

Autoria(s): Araghi, Sahar; Khosravi, Abbas; Johnstone, Michael; Creighton, Douglas
Data(s)

01/01/2013
Identificador

http://hdl.handle.net/10536/DRO/DU:30055412
Idioma(s)

eng
Publicador

Elsevier
Relação

http://dro.deakin.edu.au/eserv/DU:30055412/araghi-anovelmodular-2013.pdf

http://dro.deakin.edu.au/eserv/DU:30055412/araghi-anovelmodular-inpress-2013.pdf

http://doi.org/10.1016/j.engappai.2013.05.003
Palavras-Chave #machine learning #modular reinforcement learning #multi-agent systems #Q-learning
Tipo

Journal Article
Acesso ao item digital