Chargement en cours...

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...

Description complète

Enregistré dans:
Détails bibliographiques
Auteurs principaux: Gershman, Samuel J., Pesaran, Bijan, Daw, Nathaniel D.
Format: Artigo
Langue:Inglês
Publié: Society for Neuroscience 2009
Sujets:
Accès en ligne: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: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!