Beyond dichotomies in reinforcement learning
Open accessThe DOI matches its Crossref record; 59 of the 59 references it cites were found in a registry or an index.
Abstract
Reinforcement learning (RL) is a framework of particular importance to psychology, neuroscience and machine learning. Interactions between these fields, as promoted through the common hub of RL, has facilitated paradigm shifts that relate multiple levels of analysis in a singular framework (for example, relating dopamine function to a computationally defined RL signal). Recently, more sophisticated RL algorithms have been proposed to better account for human learning, and in particular its oft-documented reliance on two separable systems: a model-based (MB) system and a model-free (MF) system. However, along with many benefits, this dichotomous lens can distort questions, and may contribute to an unnecessarily narrow perspective on learning and decision-making. Here, we outline some of the consequences that come from overconfidently mapping algorithms, such as MB versus MF RL, with putative cognitive processes. We argue that the field is well positioned to move beyond simplistic dichotomies, and we propose a means of refocusing research questions towards the rich and complex components that comprise learning and decision-making. Reinforcement learning has been suggested to come in two flavours: model-free and model-based. In this Perspective, Collins and Cockburn explain why viewing reinforcement learning through this dichotomous lens is not always accurate or helpful, and suggest paths forward.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Cognitive maps in rats and men
Tolman, E. C. (1948) · Psychological Review · doi:10.1037/h0061626 · Cited by 6,641
Representativeness revisited: Attribute substitution in intuitive judgment.
Kahneman, D., & Frederick, S. (2002) · Heuristics and Biases · doi:10.1017/cbo9780511808098.004 · Cited by 3,476
Pearce, J. M., & Hall, G. (1980) · Psychological Review · doi:10.1037/0033-295x.87.6.532 · Cited by 3,023
The debate over dopamine’s role in reward: the case for incentive salience
Berridge, K. C. (2007) · Psychopharmacology · doi:10.1007/s00213-006-0578-x · Cited by 2,347
Dissociable Roles of Ventral and Dorsal Striatum in Instrumental Conditioning
O'Doherty, J., Dayan, P., Schultz, J., Deichmann, R., Friston, K., & Dolan, R. J. (2004) · Science · doi:10.1126/science.1094285 · Cited by 2,088
A framework for mesencephalic dopamine systems based on predictive Hebbian learning
Montague, P., Dayan, P., & Sejnowski, T. (1996) · The Journal of Neuroscience · doi:10.1523/jneurosci.16-05-01936.1996 · Cited by 2,066
Learning the value of information in an uncertain world
Behrens, T. E. J., Woolrich, M. W., Walton, M. E., & Rushworth, M. F. S. (2007) · Nature Neuroscience · doi:10.1038/nn1954 · Cited by 2,053
By Carrot or by Stick: Cognitive Reinforcement Learning in Parkinsonism
Frank, M. J., Seeberger, L. C., & O'Reilly, R. C. (2004) · Science · doi:10.1126/science.1102941 · Cited by 1,964
Context and Behavioral Processes in Extinction: Table 1.
Bouton, M. E. (2004) · Learning & Memory · doi:10.1101/lm.78804 · Cited by 1,808
A neostriatal habit learning system in humans
Knowlton, B. J., Mangels, J. A., & Squire, L. R. (1996) · Science · doi:10.1126/science.273.5280.1399 · Cited by 1,777
Cited by
Himeur, Y., Elnour, M., Fadli, F., Meskin, N., Petri, I., Rezgui, Y., Bensaali, F., & Amira, A. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-022-10286-2 · Cited by 541
Computational processes of simultaneous learning of stochasticity and volatility in humans
Piray, P., & Daw, N. D. (2024) · Nature Communications · doi:10.1038/s41467-024-53459-z · Cited by 45
“These additional issues include attention 2 , decision noise and the explore-exploit tradeoff 47,59 , social cause inference 27,60,61 , the organization of experiences into latent causes or contexts 5,62,63 , and planning 64 – 67 .”
Addressing altered anticipation as a transdiagnostic target through computational psychiatry
Sepúlveda, P., Aitsahalia, I., Kumar, K., Atkin, T., & Iigaya, K. (2025) · Biological Psychiatry Cognitive Neuroscience and Neuroimaging · doi:10.1016/j.bpsc.2025.02.014 · Cited by 3
Environmental dynamics shape human learning: change points versus random walks
Foucault, C., Weber, L. A., & Hunt, L. (2025) · doi:10.1101/2025.11.26.690700 · Cited by 2
Metadata
- Authors
- Collins, A. G. E., & Cockburn, J.
- Venue
- Nature Reviews Neuroscience
- Published
- 2020-09-01
- Volume
- 21
- Issue
- 10
- Pages
- 576-586
- ISSN
- 1471-003X (ISSN-L)
- 1471-0048
- OpenAlex
- W3082381308
- Cited by
- 125
- References
- 59
- FWCI
- 1.95
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Beyond dichotomies in reinforcement learning. https://app.cochat.ai/papers/10.1038/s41583-020-0355-6
- The paper
- Collins, A. G. E., & Cockburn, J. (2020). Beyond dichotomies in reinforcement learning. Nature Reviews Neuroscience. https://doi.org/10.1038/s41583-020-0355-6
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.