{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T01:54:13Z","timestamp":1787968453277,"version":"build-2784847793"},"reference-count":112,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,4,3]],"date-time":"2024-04-03T00:00:00Z","timestamp":1712102400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004189","name":"Max Planck Society","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004189","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100005156","name":"Alexander von Humboldt Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100005156","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001711","name":"Swiss National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006447","name":"University of Zurich","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006447","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurobiology of Learning and Memory"],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1016\/j.nlm.2024.107924","type":"journal-article","created":{"date-parts":[[2024,4,3]],"date-time":"2024-04-03T23:40:57Z","timestamp":1712187657000},"page":"107924","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":28,"special_numbering":"C","title":["Bayesian reinforcement learning: A basic overview"],"prefix":"10.1016","volume":"211","author":[{"given":"Pyungwon","family":"Kang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philippe N.","family":"Tobler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Dayan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"3","key":"10.1016\/j.nlm.2024.107924_b0005","doi-asserted-by":"crossref","first-page":"614","DOI":"10.1038\/s41386-020-00881-8","article-title":"Attention-deficit\/hyperactivity disorder and the explore\/exploit trade-off","volume":"46","author":"Addicott","year":"2021","journal-title":"Neuropsychopharmacology"},{"key":"10.1016\/j.nlm.2024.107924_b0010","unstructured":"Ahmadi, M. (2020). Normative Hidden Variable Models of Learning and Decision Making Under Uncertainty. UCL (University College London)."},{"key":"10.1016\/j.nlm.2024.107924_b0015","doi-asserted-by":"crossref","first-page":"147","DOI":"10.3758\/BF03196059","article-title":"Simulations of a modified SOP model applied to retrospective revaluation of human causal learning","volume":"33","author":"Aitken","year":"2005","journal-title":"Learning & Behavior"},{"key":"10.1016\/j.nlm.2024.107924_bib522","series-title":"The Cambridge handbook of artificial intelligence","first-page":"232","article-title":"Actions and agents","author":"Alonso","year":"2014"},{"key":"10.1016\/j.nlm.2024.107924_bib523","first-page":"548","article-title":"Quantum Probability in Operant Conditioning-Behavioral Uncertainty in Reinforcement Learning","volume":"2","author":"Alonso","year":"2014","journal-title":"International Conference on Agents and Artificial Intelligence"},{"issue":"12","key":"10.1016\/j.nlm.2024.107924_b0020","doi-asserted-by":"crossref","first-page":"5458","DOI":"10.1109\/TIE.2012.2236994","article-title":"Industrial applications of the Kalman filter: A review","volume":"60","author":"Auger","year":"2013","journal-title":"IEEE Transactions on Industrial Electronics"},{"issue":"3","key":"10.1016\/j.nlm.2024.107924_b0025","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1016\/0023-9690(91)90008-V","article-title":"Simultaneous conditioning demonstrated in second-order conditioning: Evidence for similar associative structure in forward and simultaneous conditioning","volume":"22","author":"Barnet","year":"1991","journal-title":"Learning and Motivation"},{"key":"10.1016\/j.nlm.2024.107924_bib524","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1007\/BF00453370","article-title":"Associative search network: A reinforcement learning associative memory","volume":"40","author":"Barto","year":"1981","journal-title":"Biological cybernetics"},{"issue":"2","key":"10.1016\/j.nlm.2024.107924_b0030","doi-asserted-by":"crossref","first-page":"490","DOI":"10.1016\/j.neuron.2018.10.002","article-title":"What is a cognitive map? Organizing knowledge for flexible behavior","volume":"100","author":"Behrens","year":"2018","journal-title":"Neuron"},{"issue":"9","key":"10.1016\/j.nlm.2024.107924_b0035","doi-asserted-by":"crossref","first-page":"1214","DOI":"10.1038\/nn1954","article-title":"Learning the value of information in an uncertain world","volume":"10","author":"Behrens","year":"2007","journal-title":"Nature Neuroscience"},{"key":"10.1016\/j.nlm.2024.107924_b0040","unstructured":"Bishop, C. M., & Nasrabadi, N. M. (2006). Pattern recognition and machine learning (Vol. 4, Issue 4). Springer."},{"issue":"1","key":"10.1016\/j.nlm.2024.107924_b0045","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1016\/j.beproc.2012.03.004","article-title":"Relapse processes after the extinction of instrumental learning: Renewal, resurgence, and reacquisition","volume":"90","author":"Bouton","year":"2012","journal-title":"Behavioural Processes"},{"issue":"2","key":"10.1016\/j.nlm.2024.107924_b0050","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1016\/j.bbr.2009.08.031","article-title":"Structure learning in action","volume":"206","author":"Braun","year":"2010","journal-title":"In Behavioural Brain Research"},{"issue":"1","key":"10.1016\/j.nlm.2024.107924_b0055","doi-asserted-by":"crossref","first-page":"e8973","DOI":"10.1371\/journal.pone.0008973","article-title":"Structure learning in a sensorimotor association task","volume":"5","author":"Braun","year":"2010","journal-title":"PLoS One1"},{"issue":"4","key":"10.1016\/j.nlm.2024.107924_b0060","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1037\/h0058944","article-title":"Sensory pre-conditioning","volume":"25","author":"Brogden","year":"1939","journal-title":"Journal of Experimental Psychology"},{"key":"10.1016\/j.nlm.2024.107924_b0065","doi-asserted-by":"crossref","first-page":"e51260","DOI":"10.7554\/eLife.51260","article-title":"Dopaminergic modulation of the exploration\/exploitation trade-off in human decision-making","volume":"9","author":"Chakroun","year":"2020","journal-title":"eLife"},{"issue":"4","key":"10.1016\/j.nlm.2024.107924_b0070","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1037\/bne0000461","article-title":"Orbitofrontal cortex and learning predictions of state transitions","volume":"135","author":"Chan","year":"2021","journal-title":"Behavioral Neuroscience"},{"issue":"1","key":"10.1016\/j.nlm.2024.107924_b0075","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1037\/a0030852","article-title":"Cognitive control over learning: Creating, clustering, and generalizing task-set structure","volume":"120","author":"Collins","year":"2013","journal-title":"Psychological Review"},{"issue":"3","key":"10.1016\/j.nlm.2024.107924_b0080","doi-asserted-by":"crossref","first-page":"e1001293","DOI":"10.1371\/journal.pbio.1001293","article-title":"Reasoning, learning, and creativity: Frontal lobe function and human decision-making","volume":"10","author":"Collins","year":"2012","journal-title":"PLoS Biology"},{"issue":"7","key":"10.1016\/j.nlm.2024.107924_b0085","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1016\/j.tics.2006.05.004","article-title":"Bayesian theories of conditioning in a changing world","volume":"10","author":"Courville","year":"2006","journal-title":"Trends in Cognitive Sciences"},{"key":"10.1016\/j.nlm.2024.107924_b0090","unstructured":"Courville, A. C., Daw, N., & Touretzky, D. (2004). Similarity and discrimination in classical conditioning: A latent variable account. Advances in Neural Information Processing Systems, 17."},{"key":"10.1016\/j.nlm.2024.107924_b0095","first-page":"369","article-title":"The pigeon as particle filter","volume":"20","author":"Daw","year":"2008","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"7095","key":"10.1016\/j.nlm.2024.107924_b0100","doi-asserted-by":"crossref","first-page":"876","DOI":"10.1038\/nature04766","article-title":"Cortical substrates for exploratory decisions in humans","volume":"441","author":"Daw","year":"2006","journal-title":"Nature"},{"key":"10.1016\/j.nlm.2024.107924_b9005","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1093\/acprof:oso\/9780199216093.003.0019","article-title":"Semi-rational models of conditioning: The case of trial order","author":"Daw","year":"2008","journal-title":"The probabilistic mind"},{"key":"10.1016\/j.nlm.2024.107924_b0105","unstructured":"Dayan, P., & Kakade, S. (2000). Explaining away in weight space. Advances in Neural Information Processing Systems."},{"key":"10.1016\/j.nlm.2024.107924_b0110","doi-asserted-by":"crossref","unstructured":"Dayan, P., Kakade, S., & Read Montague, P. (2000). Learning and selective attention. http:\/\/neurosci.nature.com.","DOI":"10.1038\/81504"},{"key":"10.1016\/j.nlm.2024.107924_b0115","first-page":"117","article-title":"Statistical models of conditioning","author":"Dayan","year":"1998","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"1","key":"10.1016\/j.nlm.2024.107924_b0120","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","article-title":"Maximum likelihood from incomplete data via the EM algorithm","volume":"39","author":"Dempster","year":"1977","journal-title":"Journal of the Royal Statistical Society: Series B (Methodological)"},{"issue":"9","key":"10.1016\/j.nlm.2024.107924_b0125","doi-asserted-by":"crossref","first-page":"e1003810","DOI":"10.1371\/journal.pcbi.1003810","article-title":"Inferring on the intentions of others by hierarchical Bayesian learning","volume":"10","author":"Diaconescu","year":"2014","journal-title":"PLoS Computational Biology"},{"issue":"1","key":"10.1016\/j.nlm.2024.107924_b0130","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1080\/713932614","article-title":"Within compound associations mediate the retrospective revaluation of causality judgements","volume":"49","author":"Dickinson","year":"1996","journal-title":"The Quarterly Journal of Experimental Psychology: Section B"},{"issue":"2","key":"10.1016\/j.nlm.2024.107924_b0135","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1037\/0096-3445.127.2.107","article-title":"Rules and exemplars in category learning","volume":"127","author":"Erickson","year":"1998","journal-title":"Journal of Experimental Psychology: General"},{"issue":"1718","key":"10.1016\/j.nlm.2024.107924_b0140","doi-asserted-by":"crossref","first-page":"2553","DOI":"10.1098\/rspb.2011.0836","article-title":"Reconciling the influence of predictiveness and uncertainty on stimulus salience: A model of attention in associative learning","volume":"278","author":"Esber","year":"2011","journal-title":"Proceedings of the Royal Society B: Biological Sciences"},{"key":"10.1016\/j.nlm.2024.107924_b0145","volume":"Vol. 1","author":"Ferguson","year":"2014"},{"issue":"2","key":"10.1016\/j.nlm.2024.107924_b0150","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1037\/bne0000306","article-title":"Occasion setting","volume":"133","author":"Fraser","year":"2019","journal-title":"Behavioral Neuroscience"},{"issue":"2","key":"10.1016\/j.nlm.2024.107924_b0155","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1037\/0033-295X.107.2.289","article-title":"Time, rate, and conditioning","volume":"107","author":"Gallistel","year":"2000","journal-title":"Psychological Review"},{"key":"10.1016\/j.nlm.2024.107924_b0160","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.17086","article-title":"A map of abstract relational knowledge in the human hippocampal-entorhinal cortex","volume":"6","author":"Garvert","year":"2017","journal-title":"eLife"},{"key":"10.1016\/j.nlm.2024.107924_b0165","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1613\/jair.3077","article-title":"Kalman temporal differences","volume":"39","author":"Geist","year":"2010","journal-title":"Journal of Artificial Intelligence Research"},{"issue":"11","key":"10.1016\/j.nlm.2024.107924_b0170","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1371\/journal.pcbi.1004567","article-title":"A Unifying Probabilistic View of Associative Learning","volume":"11","author":"Gershman","year":"2015","journal-title":"PLoS Computational Biology"},{"key":"10.1016\/j.nlm.2024.107924_b0175","doi-asserted-by":"crossref","first-page":"e23763","DOI":"10.7554\/eLife.23763","article-title":"The computational nature of memory modification","volume":"6","author":"Gershman","year":"2017","journal-title":"eLife"},{"key":"10.1016\/j.nlm.2024.107924_b0180","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/j.conb.2010.02.008","article-title":"Learning latent structure: Carving nature at its joints. In","volume":"Vol. 20(2","author":"Gershman","year":"2010","journal-title":"Current Opinion in Neurobiology"},{"issue":"3","key":"10.1016\/j.nlm.2024.107924_b0185","doi-asserted-by":"crossref","first-page":"255","DOI":"10.3758\/s13420-012-0080-8","article-title":"Exploring a latent cause theory of classical conditioning","volume":"40","author":"Gershman","year":"2012","journal-title":"Learning and Behavior"},{"key":"10.1016\/j.nlm.2024.107924_b0190","first-page":"43","article-title":"Discovering latent causes in reinforcement learning","volume":"5","author":"Gershman","year":"2015"},{"key":"10.1016\/j.nlm.2024.107924_b0195","doi-asserted-by":"crossref","first-page":"45","DOI":"10.3758\/BF03209729","article-title":"Partial reinforcement in autoshaping with pigeons","volume":"8","author":"Gibbon","year":"1980","journal-title":"Animal Learning & Behavior"},{"key":"10.1016\/j.nlm.2024.107924_b0200","series-title":"Proceedings of the Fourteenth Annual Meeting of the Cognitive Science Society Bloomington","article-title":"Adaptation of cue-specific learning rates in network models of human category learning","author":"Gluck","year":"1992"},{"issue":"2","key":"10.1016\/j.nlm.2024.107924_b0205","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1049\/ip-f-2.1993.0015","article-title":"Novel approach to nonlinear\/non-Gaussian Bayesian state estimation","volume":"140","author":"Gordon","year":"1993","journal-title":"IEE Proceedings F (Radar and Signal Processing)"},{"key":"10.1016\/j.nlm.2024.107924_b0210","article-title":"Hierarchical topic models and the nested Chinese restaurant process","volume":"16","author":"Griffiths","year":"2003","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"5","key":"10.1016\/j.nlm.2024.107924_b0215","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1037\/0033-295X.89.5.529","article-title":"Processing of expected and unexpected events during conditioning and attention: A psychophysiological theory","volume":"89","author":"Grossberg","year":"1982","journal-title":"Psychological Review"},{"issue":"3","key":"10.1016\/j.nlm.2024.107924_b0220","first-page":"240","article-title":"A partial reinforcement extinction effect despite equal rates of reinforcement during Pavlovian conditioning","volume":"30","author":"Haselgrove","year":"2004","journal-title":"Journal of Experimental Psychology: Animal Behavior Processes"},{"issue":"2","key":"10.1016\/j.nlm.2024.107924_b0225","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1037\/0097-7403.31.2.155","article-title":"Variations in unconditioned stimulus processing in unblocking","volume":"31","author":"Holland","year":"2005","journal-title":"Journal of Experimental Psychology. Animal Behavior Processes"},{"key":"10.1016\/j.nlm.2024.107924_b0230","doi-asserted-by":"crossref","DOI":"10.1016\/j.neuroimage.2020.117590","article-title":"Cholinergic and dopaminergic effects on prediction error and uncertainty responses during sensory associative learning","volume":"226","author":"Iglesias","year":"2021","journal-title":"NeuroImage"},{"issue":"2","key":"10.1016\/j.nlm.2024.107924_b0235","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1207\/s15516709cog1502_2","article-title":"Task decomposition through competition in a modular connectionist architecture: The what and where vision tasks","volume":"15","author":"Jacobs","year":"1991","journal-title":"Cognitive Science"},{"issue":"1","key":"10.1016\/j.nlm.2024.107924_b0240","first-page":"8","article-title":"Bayesian learning theory applied to human cognition","volume":"2","author":"Jacobs","year":"2011","journal-title":"Wiley Interdisciplinary Reviews: Cognitive Science"},{"issue":"11","key":"10.1016\/j.nlm.2024.107924_b0245","doi-asserted-by":"crossref","first-page":"838","DOI":"10.1038\/s41562-018-0455-8","article-title":"Behavioural and neural evidence for self-reinforcing expectancy effects on pain","volume":"2","author":"Jepma","year":"2018","journal-title":"Nature Human Behaviour"},{"issue":"9","key":"10.1016\/j.nlm.2024.107924_b0250","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1371\/journal.pcbi.1008276","article-title":"Uncertainty-driven regulation of learning and exploration in adolescents: A computational account","volume":"16","author":"Jepma","year":"2020","journal-title":"PLoS Computational Biology"},{"issue":"1","key":"10.1016\/j.nlm.2024.107924_b0255","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1115\/1.3662552","article-title":"A New Approach to Linear Filtering and Prediction Problems","volume":"82","author":"Kalman","year":"1960","journal-title":"Journal of Basic Engineering"},{"issue":"4","key":"10.1016\/j.nlm.2024.107924_b0260","doi-asserted-by":"crossref","first-page":"677","DOI":"10.1037\/0033-295X.113.4.677","article-title":"Locally Bayesian learning with applications to retrospective revaluation and highlighting","volume":"113","author":"Kruschke","year":"2006","journal-title":"Psychological Review"},{"issue":"3","key":"10.1016\/j.nlm.2024.107924_b0265","doi-asserted-by":"crossref","first-page":"210","DOI":"10.3758\/LB.36.3.210","article-title":"Bayesian approaches to associative learning: From passive to active learning","volume":"36","author":"Kruschke","year":"2008","journal-title":"Learning and Behavior"},{"key":"10.1016\/j.nlm.2024.107924_b0270","doi-asserted-by":"crossref","unstructured":"Kruschke, John. (2011). Chapter 2. Doing Bayesian Data Analysis. Doing Bayesian Data Analysis, 673. doi: 10.1016\/B978-0-12-405888-0.00001-5.","DOI":"10.1016\/B978-0-12-405888-0.00001-5"},{"issue":"3b","key":"10.1016\/j.nlm.2024.107924_b0275","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1080\/02724990344000141","article-title":"The role of associative history in models of associative learning: A selective review and a hybrid model","volume":"57","author":"Le Pelley","year":"2004","journal-title":"The Quarterly Journal of Experimental Psychology Section B"},{"issue":"4b","key":"10.1016\/j.nlm.2024.107924_b0280","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1080\/02724990143000072","article-title":"Retrospective revaluation in humans: Learning or memory?","volume":"54","author":"Le Pelley","year":"2001","journal-title":"The Quarterly Journal of Experimental Psychology Section B"},{"issue":"10","key":"10.1016\/j.nlm.2024.107924_bib525","doi-asserted-by":"crossref","first-page":"1111","DOI":"10.1037\/bul0000064","article-title":"Attention and associative learning in humans: An integrative review","volume":"142","author":"Le Pelley","year":"2016","journal-title":"Psychological bulletin"},{"issue":"82","key":"10.1016\/j.nlm.2024.107924_b0285","doi-asserted-by":"crossref","first-page":"20130069","DOI":"10.1098\/rsif.2013.0069","article-title":"Context-dependent decision-making: A simple Bayesian model","volume":"10","author":"Lloyd","year":"2013","journal-title":"Journal of The Royal Society Interface"},{"key":"10.1016\/j.nlm.2024.107924_b0290","series-title":"Information theory, inference and learning algorithms","author":"MacKay","year":"2003"},{"issue":"4","key":"10.1016\/j.nlm.2024.107924_b0295","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1037\/h0076778","article-title":"A theory of attention: Variations in the associability of stimuli with reinforcement","volume":"82","author":"Mackintosh","year":"1975","journal-title":"Psychological Review"},{"key":"10.1016\/j.nlm.2024.107924_bib526","series-title":"Vision: A computational investigation into the human representation and processing of visual information","author":"Marr","year":"1982"},{"issue":"MAY","key":"10.1016\/j.nlm.2024.107924_b0300","first-page":"39","article-title":"A bayesian foundation for individual learning under uncertainty","volume":"5","author":"Mathys","year":"2011","journal-title":"Frontiers in Human Neuroscience"},{"issue":"1","key":"10.1016\/j.nlm.2024.107924_b0305","first-page":"202","article-title":"Hippocampal Representation of Related and Opposing Memories Develop within Distinct","volume":"83","author":"McKenzie","year":"2014","journal-title":"Hierarchically Organized Neural Schemas. Neuron"},{"issue":"3","key":"10.1016\/j.nlm.2024.107924_b0310","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1037\/0033-2909.117.3.363","article-title":"Assessment of the Rescorla-Wagner model","volume":"117","author":"Miller","year":"1995","journal-title":"Psychological Bulletin"},{"issue":"4","key":"10.1016\/j.nlm.2024.107924_b0315","doi-asserted-by":"crossref","first-page":"370","DOI":"10.1037\/0096-3445.125.4.370","article-title":"Biological significance in forward and backward blocking: Resolution of a discrepancy between animal conditioning and human causal judgment","volume":"125","author":"Miller","year":"1996","journal-title":"Journal of Experimental Psychology: General"},{"key":"10.1016\/j.nlm.2024.107924_b0320","first-page":"51","article-title":"The comparator hypothesis: A response rule for the expression of associations","volume":"Vol. 22","author":"Miller","year":"1988"},{"issue":"5","key":"10.1016\/j.nlm.2024.107924_b0325","doi-asserted-by":"crossref","first-page":"1936","DOI":"10.1523\/JNEUROSCI.16-05-01936.1996","article-title":"A framework for mesencephalic dopamine systems based on predictive Hebbian learning","volume":"16","author":"Montague","year":"1996","journal-title":"Journal of Neuroscience"},{"issue":"4","key":"10.1016\/j.nlm.2024.107924_b0330","doi-asserted-by":"crossref","first-page":"e1003015","DOI":"10.1371\/journal.pcbi.1003015","article-title":"A healthy fear of the unknown: Perspectives on the interpretation of parameter fits from computational models in neuroscience","volume":"9","author":"Nassar","year":"2013","journal-title":"PLoS Computational Biology"},{"key":"10.1016\/j.nlm.2024.107924_b0340","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1007\/978-94-011-5014-9_12","article-title":"A view of the EM algorithm that justifies incremental, sparse, and other variants","author":"Neal","year":"1998","journal-title":"Learning in Graphical Models"},{"issue":"7","key":"10.1016\/j.nlm.2024.107924_b0345","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1016\/j.tics.2008.03.006","article-title":"Dialogues on prediction errors","volume":"12","author":"Niv","year":"2008","journal-title":"Trends in Cognitive Sciences"},{"issue":"4","key":"10.1016\/j.nlm.2024.107924_b0350","doi-asserted-by":"crossref","first-page":"587","DOI":"10.1037\/0033-295X.101.4.587","article-title":"Similarity and discrimination: A selective review and a connectionist model","volume":"101","author":"Pearce","year":"1994","journal-title":"Psychological Review"},{"key":"10.1016\/j.nlm.2024.107924_b0355","series-title":"Animal learning and cognition: An introduction","author":"Pearce","year":"2013"},{"issue":"6","key":"10.1016\/j.nlm.2024.107924_b0360","doi-asserted-by":"crossref","first-page":"532","DOI":"10.1037\/0033-295X.87.6.532","article-title":"A model for Pavlovian learning: Variations in the effectiveness of conditioned but not of unconditioned stimuli","volume":"87","author":"Pearce","year":"1980","journal-title":"Psychological Review"},{"issue":"4","key":"10.1016\/j.nlm.2024.107924_bib527","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1016\/j.tics.2011.02.002","article-title":"Posterior cingulate cortex: adapting behavior to a changing world","volume":"15","author":"Pearson","year":"2011","journal-title":"Trends in cognitive sciences"},{"issue":"39","key":"10.1016\/j.nlm.2024.107924_b0365","doi-asserted-by":"crossref","first-page":"13829","DOI":"10.1523\/JNEUROSCI.1704-11.2011","article-title":"Protection and expression of human motor memories","volume":"31","author":"Pekny","year":"2011","journal-title":"Journal of Neuroscience"},{"issue":"7","key":"10.1016\/j.nlm.2024.107924_b0370","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1007963","article-title":"A simple model for learning in volatile environments","volume":"16","author":"Piray","year":"2020","journal-title":"PLoS Computational Biology"},{"issue":"1","key":"10.1016\/j.nlm.2024.107924_b0375","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-021-26731-9","article-title":"A model for learning based on the joint estimation of stochasticity and volatility","volume":"12","author":"Piray","year":"2021","journal-title":"Nature Communications"},{"issue":"6351","key":"10.1016\/j.nlm.2024.107924_b0380","doi-asserted-by":"crossref","first-page":"596","DOI":"10.1126\/science.aan3458","article-title":"Pavlovian conditioning\u2013induced hallucinations result from overweighting of perceptual priors","volume":"357","author":"Powers","year":"2017","journal-title":"Science"},{"issue":"13","key":"10.1016\/j.nlm.2024.107924_b0385","doi-asserted-by":"crossref","first-page":"5371","DOI":"10.1073\/pnas.0802111106","article-title":"Mapping dynamic memories of gradually changing objects","volume":"106","author":"Preminger","year":"2009","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"7","key":"10.1016\/j.nlm.2024.107924_b0390","doi-asserted-by":"crossref","first-page":"965","DOI":"10.1016\/j.visres.2007.01.003","article-title":"The effects of perceptual history on memory of visual objects","volume":"47","author":"Preminger","year":"2007","journal-title":"Vision Research"},{"issue":"1","key":"10.1016\/j.nlm.2024.107924_b0395","doi-asserted-by":"crossref","first-page":"25","DOI":"10.3758\/BF03209127","article-title":"Second-order conditioning of the pigeon\u2019s keypeck","volume":"5","author":"Rashotte","year":"1977","journal-title":"Animal Learning & Behavior"},{"issue":"3","key":"10.1016\/j.nlm.2024.107924_b0400","doi-asserted-by":"crossref","first-page":"784","DOI":"10.1037\/0033-295X.114.3.784","article-title":"Reconciling reinforcement learning models with behavioral extinction and renewal: Implications for addiction, relapse, and problem gambling","volume":"114","author":"Redish","year":"2007","journal-title":"Psychological Review"},{"issue":"1","key":"10.1016\/j.nlm.2024.107924_b0405","first-page":"23","article-title":"Simultaneous second-order conditioning produces S\u00df learning in conditioned suppression","volume":"8","author":"Rescorla","year":"1982","journal-title":"Journal of Experimental Psychology: Animal Behavior Processes"},{"issue":"1b","key":"10.1016\/j.nlm.2024.107924_b0410","first-page":"75","article-title":"Within-subject partial reinforcement extinction effect in autoshaping","volume":"52","author":"Rescorla","year":"1999","journal-title":"The Quarterly Journal of Experimental Psychology Section B"},{"issue":"6","key":"10.1016\/j.nlm.2024.107924_b0415","first-page":"64","article-title":"A theory of Pavlovian conditioning: Variations in the effectiveness of reinforcement and nonreinforcement","volume":"21","author":"Rescorla","year":"1972","journal-title":"Classical Conditioning II Current Research and Theory"},{"issue":"1","key":"10.1016\/j.nlm.2024.107924_b0420","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1037\/h0033333","article-title":"Associations in second-order conditioning and sensory preconditioning","volume":"81","author":"Rizley","year":"1972","journal-title":"Journal of Comparative and Physiological Psychology"},{"issue":"3","key":"10.1016\/j.nlm.2024.107924_b0425","first-page":"235","article-title":"Mechanisms underlying spontaneous recovery in autoshaping","volume":"16","author":"Robbins","year":"1990","journal-title":"Journal of Experimental Psychology: Animal Behavior Processes"},{"issue":"10","key":"10.1016\/j.nlm.2024.107924_b0430","doi-asserted-by":"crossref","first-page":"1314","DOI":"10.1038\/s41593-022-01149-8","article-title":"Complementary task representations in hippocampus and prefrontal cortex for generalizing the structure of problems","volume":"25","author":"Samborska","year":"2022","journal-title":"Nature Neuroscience"},{"issue":"6","key":"10.1016\/j.nlm.2024.107924_b0435","doi-asserted-by":"crossref","first-page":"1402","DOI":"10.1016\/j.neuron.2016.08.019","article-title":"Human Orbitofrontal Cortex Represents a Cognitive Map of State Space","volume":"91","author":"Schuck","year":"2016","journal-title":"Neuron"},{"issue":"1b","key":"10.1016\/j.nlm.2024.107924_b0440","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/14640748508402082","article-title":"Forward and backward blocking in human contingency judgement","volume":"37","author":"Shanks","year":"1985","journal-title":"The Quarterly Journal of Experimental Psychology Section B"},{"issue":"3","key":"10.1016\/j.nlm.2024.107924_b0445","doi-asserted-by":"crossref","first-page":"526","DOI":"10.1037\/a0037018","article-title":"Explaining compound generalization in associative and causal learning through rational principles of dimensional generalization","volume":"121","author":"Soto","year":"2014","journal-title":"Psychological Review"},{"key":"10.1016\/j.nlm.2024.107924_b0450","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.conb.2013.12.007","article-title":"Computational approaches to psychiatry","volume":"25","author":"Stephan","year":"2014","journal-title":"Current Opinion in Neurobiology"},{"key":"10.1016\/j.nlm.2024.107924_b0455","doi-asserted-by":"crossref","unstructured":"Sutton, R. S. (1988). Learning to Predict by the Methods of Temporal Differences. 9\u201344.","DOI":"10.1007\/BF00115009"},{"key":"10.1016\/j.nlm.2024.107924_b0460","unstructured":"Sutton, R. S. (1992). Gain adaptation beats least squares. Proceedings of the 7th Yale Workshop on Adaptive and Learning Systems, 161, 166."},{"key":"10.1016\/j.nlm.2024.107924_b0465","unstructured":"Sutton, R. S., & Barto, A. G. (1990). Time-derivative models of pavlovian reinforcement."},{"issue":"6","key":"10.1016\/j.nlm.2024.107924_b0470","doi-asserted-by":"crossref","first-page":"3157","DOI":"10.1152\/jn.01008.2010","article-title":"Trial-by-trial analysis of intermanual transfer during visuomotor adaptation","volume":"106","author":"Taylor","year":"2011","journal-title":"Journal of Neurophysiology"},{"key":"10.1016\/j.nlm.2024.107924_b0475","first-page":"556","article-title":"Stick-breaking construction for the Indian buffet process","author":"Teh","year":"2007","journal-title":"Artificial Intelligence and Statistics"},{"issue":"3","key":"10.1016\/j.nlm.2024.107924_b0480","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1037\/h0055304","article-title":"There is more than one kind of learning","volume":"56","author":"Tolman","year":"1949","journal-title":"Psychological Review"},{"issue":"1","key":"10.1016\/j.nlm.2024.107924_bib529","doi-asserted-by":"crossref","first-page":"2371","DOI":"10.1038\/s41467-020-15766-z","article-title":"Dissociable neural correlates of uncertainty underlie different exploration strategies","volume":"11","author":"Tomov","year":"2020","journal-title":"Nature communications"},{"issue":"2","key":"10.1016\/j.nlm.2024.107924_b0485","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1006\/lmot.1994.1008","article-title":"Cue competition in causality judgments: The role of nonpresentation of compound stimulus elements","volume":"25","author":"Van Hamme","year":"1994","journal-title":"Learning and Motivation"},{"key":"10.1016\/j.nlm.2024.107924_b0490","unstructured":"Wagner A.R. (1981) SOP. A model of automatic memory processing in animal behavior N.E. Spear, R.R. Miller (Eds.), Information processing in animals: Memory mechanisms, Erlbaum, Hillsdale, NJ, pp. 5-47."},{"issue":"10","key":"10.1016\/j.nlm.2024.107924_b0495","doi-asserted-by":"crossref","first-page":"1257","DOI":"10.1038\/s41593-022-01153-y","article-title":"How to build a cognitive map","volume":"25","author":"Whittington","year":"2022","journal-title":"Nature Neuroscience"},{"issue":"1","key":"10.1016\/j.nlm.2024.107924_bib528","first-page":"96","article-title":"Adaptive switching circuits. In IRE WESCON convention","volume":"4","author":"Widrow","year":"1960","journal-title":"record"},{"issue":"11","key":"10.1016\/j.nlm.2024.107924_b0500","doi-asserted-by":"crossref","first-page":"2512","DOI":"10.1523\/JNEUROSCI.1607-20.2021","article-title":"Attenuated directed exploration during reinforcement learning in gambling disorder","volume":"41","author":"Wiehler","year":"2021","journal-title":"Journal of Neuroscience"},{"issue":"8","key":"10.1016\/j.nlm.2024.107924_b0505","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1038\/nrn.2016.56","article-title":"Over the river, through the woods: Cognitive maps in the hippocampus and orbitofrontal cortex","volume":"17","author":"Wikenheiser","year":"2016","journal-title":"Nature Reviews Neuroscience"},{"issue":"2","key":"10.1016\/j.nlm.2024.107924_b0510","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1016\/j.neuron.2013.11.005","article-title":"Orbitofrontal cortex as a cognitive map of task space","volume":"81","author":"Wilson","year":"2014","journal-title":"Neuron"},{"issue":"4","key":"10.1016\/j.nlm.2024.107924_b0515","doi-asserted-by":"crossref","first-page":"681","DOI":"10.1016\/j.neuron.2005.04.026","article-title":"Uncertainty, neuromodulation, and attention","volume":"46","author":"Yu","year":"2005","journal-title":"Neuron"},{"issue":"20","key":"10.1016\/j.nlm.2024.107924_b0520","doi-asserted-by":"crossref","first-page":"3402","DOI":"10.1016\/j.cub.2019.08.040","article-title":"Complementary Task Structure Representations in Hippocampus and Orbitofrontal Cortex during an Odor Sequence Task","volume":"29","author":"Zhou","year":"2019","journal-title":"Current Biology"}],"container-title":["Neurobiology of Learning and Memory"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1074742724000352?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1074742724000352?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,5,5]],"date-time":"2024-05-05T06:14:12Z","timestamp":1714889652000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1074742724000352"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":112,"alternative-id":["S1074742724000352"],"URL":"https:\/\/doi.org\/10.1016\/j.nlm.2024.107924","relation":{},"ISSN":["1074-7427"],"issn-type":[{"value":"1074-7427","type":"print"}],"subject":[],"published":{"date-parts":[[2024,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Bayesian reinforcement learning: A basic overview","name":"articletitle","label":"Article Title"},{"value":"Neurobiology of Learning and Memory","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.nlm.2024.107924","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 The Authors. Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"107924"}}