Value-free reinforcement learning: policy optimization as a minimal model of operant behavior. | Curr Opin Behav Sci;41: 114-121, 2021 Oct. | MEDLINE

Main content 1 Search 2 Footer 3

+A A -A High contrast

VHL Regional Portal

Information and Knowledge for Health

Subject descriptor lookup Advanced Search EVID@Easy

Value-free reinforcement learning: policy optimization as a minimal model of operant behavior.

Bennett, Daniel; Niv, Yael; Langdon, Angela J.

Affiliation

Bennett D; Princeton Neuroscience Institute, Princeton University, USA.
Niv Y; Department of Psychiatry, Monash University, Australia.
Langdon AJ; Princeton Neuroscience Institute, Princeton University, USA.

Curr Opin Behav Sci ; 41: 114-121, 2021 Oct.

Article in En | MEDLINE | ID: mdl-36341023

Key words

computational modelling; decision-making; policy gradient; reinforcement learning; value

Search on Google

Full text: 1 Collection: 01-internacional Database: MEDLINE Type of study: Prognostic_studies Language: En Journal: Curr Opin Behav Sci Year: 2021 Document type: Article Affiliation country: United States Country of publication: Netherlands

Search on Google

Full text: 1 Collection: 01-internacional Database: MEDLINE Type of study: Prognostic_studies Language: En Journal: Curr Opin Behav Sci Year: 2021 Document type: Article Affiliation country: United States Country of publication: Netherlands