Načítá se...
A normative account of confirmation bias during reinforcement learning
Reinforcement learning involves updating estimates of the value of states and actions on the basis of experience. Previous work has shown that in humans, reinforcement learning exhibits a confirmatory bias: when updating the value of a chosen option, estimates are revised more radically following po...
Uloženo v:
| Vydáno v: | Neural Comput |
|---|---|
| Hlavní autoři: | , , |
| Médium: | Artigo |
| Jazyk: | Inglês |
| Vydáno: |
2022
|
| Témata: | |
| On-line přístup: | https://ncbi.nlm.nih.gov/pmc/articles/PMC7612695/ https://ncbi.nlm.nih.gov/pubmed/34758486 https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1162/neco_a_01455 |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo otaguje tento záznam!
|