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: | , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
Cell Press
2020
|
| _version_ | 1797072219583545344 |
|---|---|
| author | Bakermans, JJW Muller, TH Behrens, TEJ |
| author_facet | Bakermans, JJW Muller, TH Behrens, TEJ |
| author_sort | Bakermans, JJW |
| collection | OXFORD |
| description | 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.
|
| first_indexed | 2024-03-06T23:04:34Z |
| format | Journal article |
| id | oxford-uuid:6356a7a1-bca5-4b66-afda-32bbdc4ca6fe |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-06T23:04:34Z |
| publishDate | 2020 |
| publisher | Cell Press |
| record_format | dspace |
| spelling | oxford-uuid:6356a7a1-bca5-4b66-afda-32bbdc4ca6fe2022-03-26T18:12:18ZReinforcement learning: full glass or empty - depends who you askJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:6356a7a1-bca5-4b66-afda-32bbdc4ca6feEnglishSymplectic ElementsCell Press 2020Bakermans, JJWMuller, THBehrens, TEJAn 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. |
| spellingShingle | Bakermans, JJW Muller, TH Behrens, TEJ Reinforcement learning: full glass or empty - depends who you ask |
| title | Reinforcement learning: full glass or empty - depends who you ask |
| title_full | Reinforcement learning: full glass or empty - depends who you ask |
| title_fullStr | Reinforcement learning: full glass or empty - depends who you ask |
| title_full_unstemmed | Reinforcement learning: full glass or empty - depends who you ask |
| title_short | Reinforcement learning: full glass or empty - depends who you ask |
| title_sort | reinforcement learning full glass or empty depends who you ask |
| work_keys_str_mv | AT bakermansjjw reinforcementlearningfullglassoremptydependswhoyouask AT mullerth reinforcementlearningfullglassoremptydependswhoyouask AT behrenstej reinforcementlearningfullglassoremptydependswhoyouask |