Cargando…

Model-based learning retrospectively updates model-free values

Reinforcement learning (RL) is widely regarded as divisible into two distinct computational strategies. Model-free learning is a simple RL process in which a value is associated with actions, whereas model-based learning relies on the formation of internal models of the environment to maximise rewar...

Descripción completa

Detalles Bibliográficos
Autores principales: Doody, Max, Van Swieten, Maaike M. H., Manohar, Sanjay G.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8837618/
https://www.ncbi.nlm.nih.gov/pubmed/35149713
http://dx.doi.org/10.1038/s41598-022-05567-3