Llwytho...

States versus Rewards: Dissociable neural prediction error signals underlying model-based and model-free reinforcement learning

Reinforcement learning (RL) uses sequential experience with situations (“states”) and outcomes to assess actions. Whereas model-free RL uses this experience directly, in the form of a reward prediction error (RPE), model-based RL uses it indirectly, building a model of the state transition and outco...

Disgrifiad llawn

Wedi'i Gadw mewn:
Manylion Llyfryddiaeth
Prif Awduron: Gläscher, Jan, Daw, Nathaniel, Dayan, Peter, O’Doherty, John P.
Fformat: Artigo
Iaith:Inglês
Cyhoeddwyd: 2010
Pynciau:
Mynediad Ar-lein:https://ncbi.nlm.nih.gov/pmc/articles/PMC2895323/
https://ncbi.nlm.nih.gov/pubmed/20510862
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1016/j.neuron.2010.04.016
Tagiau: Ychwanegu Tag
Dim Tagiau, Byddwch y cyntaf i dagio'r cofnod hwn!