Reinforcement learning: full glass or empty - depends who you ask
An extension of the prediction error theory of dopamine, imported from artificial intelligence, represents the full distribution over future rewards rather than only the average and better explains dopamine responses.
Main Authors: | Bakermans, JJW, Muller, TH, Behrens, TEJ |
---|---|
Format: | Journal article |
Language: | English |
Published: |
Cell Press
2020
|
Similar Items
-
What exactly is Product Modularity? The answer depends on who you ask
by: Fixson, Sebastian K.
Published: (2007) -
Relational representations for composition of knowledge and plans
by: Bakermans, JJW
Published: (2022) -
Unicompartmental knee arthroplasty: is the glass half full or half empty?
by: Murray, D, et al.
Published: (2015) -
The Portuguese Journal of Cardiology: Is the glass half full or half empty?
by: Helena Donato, et al.
Published: (2023-04-01) -
Entorhinal and ventromedial prefrontal cortices abstract and generalize the structure of reinforcement learning problems.
by: Baram, AB, et al.
Published: (2020)