Reinforcement Learning: Full Glass or Empty - Depends Who You Ask

Jacob J W Bakermans¹, Timothy H Muller², Timothy E J Behrens³

Affiliations

¹ Wellcome Centre for Integrative Neuroimaging, FMRIB, Nuffield Department of Clinical Neurosciences, University of Oxford, John Radcliffe Hospital, Oxford OX3 9DU, UK. Electronic address: Jacob.bakermans@ndcn.ox.ac.uk.
² Institute of Neurology, Department of Clinical and Movement Neurosciences, University College London, London WC1N 3BG, UK. Electronic address: timothymuller127@gmail.com.
³ Wellcome Centre for Integrative Neuroimaging, FMRIB, Nuffield Department of Clinical Neurosciences, University of Oxford, John Radcliffe Hospital, Oxford OX3 9DU, UK; Wellcome Centre for Human Neuroimaging, University College London, London WC1N 3AR, UK. Electronic address: behrens@fmrib.ox.ac.uk.

PMID: 32259508
DOI: 10.1016/j.cub.2020.02.062

Free article

Comment

Reinforcement Learning: Full Glass or Empty - Depends Who You Ask

Jacob J W Bakermans et al. Curr Biol. 2020.

Free article

. 2020 Apr 6;30(7):R321-R324.

doi: 10.1016/j.cub.2020.02.062.

Authors

Jacob J W Bakermans¹, Timothy H Muller², Timothy E J Behrens³

Affiliations

¹ Wellcome Centre for Integrative Neuroimaging, FMRIB, Nuffield Department of Clinical Neurosciences, University of Oxford, John Radcliffe Hospital, Oxford OX3 9DU, UK. Electronic address: Jacob.bakermans@ndcn.ox.ac.uk.
² Institute of Neurology, Department of Clinical and Movement Neurosciences, University College London, London WC1N 3BG, UK. Electronic address: timothymuller127@gmail.com.
³ Wellcome Centre for Integrative Neuroimaging, FMRIB, Nuffield Department of Clinical Neurosciences, University of Oxford, John Radcliffe Hospital, Oxford OX3 9DU, UK; Wellcome Centre for Human Neuroimaging, University College London, London WC1N 3AR, UK. Electronic address: behrens@fmrib.ox.ac.uk.

PMID: 32259508
DOI: 10.1016/j.cub.2020.02.062

Abstract

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.

PubMed Disclaimer

Comment on

A distributional code for value in dopamine-based reinforcement learning.
Dabney W, Kurth-Nelson Z, Uchida N, Starkweather CK, Hassabis D, Munos R, Botvinick M. Dabney W, et al. Nature. 2020 Jan;577(7792):671-675. doi: 10.1038/s41586-019-1924-6. Epub 2020 Jan 15. Nature. 2020. PMID: 31942076 Free PMC article.

Publication types

Actions

MeSH terms

Actions
Actions
Actions
Actions
Actions

Substances

Actions

LinkOut - more resources

Full Text Sources
- Elsevier Science

Save citation to file

Email citation

Add to Collections

Add to My Bibliography

Your saved search

Create a file for external citation management software

Your RSS Feed

Reinforcement Learning: Full Glass or Empty - Depends Who You Ask

Affiliations

Reinforcement Learning: Full Glass or Empty - Depends Who You Ask

Authors

Affiliations

Abstract

Comment on

Publication types

MeSH terms

Substances

LinkOut - more resources

Full Text Sources