A carregar...

Human Reinforcement Learning Subdivides Structured Action Spaces by Learning Effector-Specific Values

Humans and animals are endowed with a large number of effectors. Although this enables great behavioral flexibility, it presents an equally formidable reinforcement learning problem of discovering which actions are most valuable because of the high dimensionality of the action space. An unresolved q...

ver descrição completa

Na minha lista:
Detalhes bibliográficos
Main Authors: Gershman, Samuel J., Pesaran, Bijan, Daw, Nathaniel D.
Formato: Artigo
Idioma:Inglês
Publicado em: Society for Neuroscience 2009
Assuntos:
Acesso em linha:https://ncbi.nlm.nih.gov/pmc/articles/PMC2796632/
https://ncbi.nlm.nih.gov/pubmed/19864565
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1523/JNEUROSCI.2469-09.2009
Tags: Adicionar Tag
Sem tags, seja o primeiro a adicionar uma tag!