Reinforcement learning: The Good, The Bad and The Ugly

Peter Dayan; Yael Niv

doi:10.1016/j.conb.2008.08.003

Reinforcement learning: The Good, The Bad and The Ugly

Peter Dayan, Yael Niv

Research output: Contribution to journal › Review article › peer-review

389 Scopus citations

Abstract

Reinforcement learning provides both qualitative and quantitative frameworks for understanding and modeling adaptive decision-making in the face of rewards and punishments. Here we review the latest dispatches from the forefront of this field, and map out some of the territories where lie monsters.

Original language	English (US)
Pages (from-to)	185-196
Number of pages	12
Journal	Current Opinion in Neurobiology
Volume	18
Issue number	2
DOIs	https://doi.org/10.1016/j.conb.2008.08.003
State	Published - Apr 2008

All Science Journal Classification (ASJC) codes

Neuroscience(all)

Access to Document

10.1016/j.conb.2008.08.003

Cite this

@article{b7b6d2d37a504ce7aecdf51c3159aa10,

title = "Reinforcement learning: The Good, The Bad and The Ugly",

abstract = "Reinforcement learning provides both qualitative and quantitative frameworks for understanding and modeling adaptive decision-making in the face of rewards and punishments. Here we review the latest dispatches from the forefront of this field, and map out some of the territories where lie monsters.",

author = "Peter Dayan and Yael Niv",

note = "Funding Information: We are very grateful to Peter Bossaerts, Nathaniel Daw, Michael Frank, Russell Poldrack, Daniel Salzman, Ben Seymour and Wako Yoshida for their helpful comments on a previous version of this manuscript. PD is funded by the Gatsby Charitable Foundation; YN is funded by the Human Frontiers Science Program.",

year = "2008",

month = apr,

doi = "10.1016/j.conb.2008.08.003",

language = "English (US)",

volume = "18",

pages = "185--196",

journal = "Current Opinion in Neurobiology",

issn = "0959-4388",

publisher = "Elsevier Limited",

number = "2",

}

TY - JOUR

T1 - Reinforcement learning

T2 - The Good, The Bad and The Ugly

AU - Dayan, Peter

AU - Niv, Yael

N1 - Funding Information: We are very grateful to Peter Bossaerts, Nathaniel Daw, Michael Frank, Russell Poldrack, Daniel Salzman, Ben Seymour and Wako Yoshida for their helpful comments on a previous version of this manuscript. PD is funded by the Gatsby Charitable Foundation; YN is funded by the Human Frontiers Science Program.

PY - 2008/4

Y1 - 2008/4

N2 - Reinforcement learning provides both qualitative and quantitative frameworks for understanding and modeling adaptive decision-making in the face of rewards and punishments. Here we review the latest dispatches from the forefront of this field, and map out some of the territories where lie monsters.

AB - Reinforcement learning provides both qualitative and quantitative frameworks for understanding and modeling adaptive decision-making in the face of rewards and punishments. Here we review the latest dispatches from the forefront of this field, and map out some of the territories where lie monsters.

UR - http://www.scopus.com/inward/record.url?scp=52049107354&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=52049107354&partnerID=8YFLogxK

U2 - 10.1016/j.conb.2008.08.003

DO - 10.1016/j.conb.2008.08.003

M3 - Review article

C2 - 18708140

AN - SCOPUS:52049107354

SN - 0959-4388

VL - 18

SP - 185

EP - 196

JO - Current Opinion in Neurobiology

JF - Current Opinion in Neurobiology

IS - 2

ER -

Reinforcement learning: The Good, The Bad and The Ugly

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this