{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T01:36:00Z","timestamp":1773797760704,"version":"3.50.1"},"reference-count":78,"publisher":"Springer Science and Business Media LLC","issue":"8068","license":[{"start":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T00:00:00Z","timestamp":1748995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T00:00:00Z","timestamp":1748995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nature"],"published-print":{"date-parts":[[2025,6,19]]},"DOI":"10.1038\/s41586-025-09089-6","type":"journal-article","created":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T15:02:33Z","timestamp":1749049353000},"page":"691-699","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["A multidimensional distributional map of future reward in dopamine neurons"],"prefix":"10.1038","volume":"642","author":[{"given":"Margarida","family":"Sousa","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6653-1996","authenticated-orcid":false,"given":"Pawel","family":"Bujalski","sequence":"additional","affiliation":[]},{"given":"Bruno F.","family":"Cruz","sequence":"additional","affiliation":[]},{"given":"Kenway","family":"Louie","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9928-4960","authenticated-orcid":false,"given":"Daniel C.","family":"McNamee","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1663-6455","authenticated-orcid":false,"given":"Joseph J.","family":"Paton","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,6,4]]},"reference":[{"key":"9089_CR1","doi-asserted-by":"publisher","first-page":"1593","DOI":"10.1126\/science.275.5306.1593","volume":"275","author":"W Schultz","year":"1997","unstructured":"Schultz, W., Dayan, P. & Montague, P. R. A neural substrate of prediction and reward. Science 275, 1593\u20131599 (1997).","journal-title":"Science"},{"key":"9089_CR2","volume-title":"Reinforcement Learning: An Introduction 2nd edn","author":"RS Sutton","year":"2018","unstructured":"Sutton, R. S. & Barto, A. G. Reinforcement Learning: An Introduction 2nd edn (MIT Press, 2018)."},{"key":"9089_CR3","doi-asserted-by":"publisher","first-page":"1936","DOI":"10.1523\/JNEUROSCI.16-05-01936.1996","volume":"16","author":"PR Montague","year":"1996","unstructured":"Montague, P. R., Dayan, P. & Sejnowski, T. J. A framework for mesencephalic dopamine systems based on predictive hebbian learning. J. Neurosci. 16, 1936\u20131947 (1996).","journal-title":"J. Neurosci."},{"key":"9089_CR4","doi-asserted-by":"crossref","unstructured":"Dabney, W., Rowland, M., Bellemare, M. & Munos, R. Distributional reinforcement learning with quantile regression. In Proc. 32nd AAAI Conference on Artificial Intelligence 2892\u20132901 (AAAI, 2018).","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"9089_CR5","doi-asserted-by":"crossref","unstructured":"Lyle, C., Bellemare, M. G. & Castro, P. S. A comparative analysis of expected and distributional reinforcement learning. In Proc. 33rd AAAI Conference on Artificial Intelligence 4504\u20134511 (AAAI, 2019).","DOI":"10.1609\/aaai.v33i01.33014504"},{"key":"9089_CR6","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/14207.001.0001","volume-title":"Distributional Reinforcement Learning","author":"MG Bellemare","year":"2023","unstructured":"Bellemare, M. G., Dabney, W. & Rowland, M. Distributional Reinforcement Learning (MIT Press, 2023)."},{"key":"9089_CR7","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1038\/s41593-023-01535-w","volume":"27","author":"TH Muller","year":"2024","unstructured":"Muller, T. H. et al. Distributional reinforcement learning in prefrontal cortex. Nat. Neurosci. 27, 403\u2013408 (2024).","journal-title":"Nat. Neurosci."},{"key":"9089_CR8","doi-asserted-by":"publisher","first-page":"114080","DOI":"10.1016\/j.celrep.2024.114080","volume":"43","author":"R Avvisati","year":"2024","unstructured":"Avvisati, R. et al. Distributional coding of associative learning in discrete populations of midbrain dopamine neurons. Cell Rep. 43, 114080 (2024).","journal-title":"Cell Rep."},{"key":"9089_CR9","doi-asserted-by":"publisher","first-page":"671","DOI":"10.1038\/s41586-019-1924-6","volume":"577","author":"W Dabney","year":"2020","unstructured":"Dabney, W. et al. A distributional code for value in dopamine-based reinforcement learning. Nature 577, 671\u2013675 (2020).","journal-title":"Nature"},{"key":"9089_CR10","first-page":"449","volume":"70","author":"MG Bellemare","year":"2017","unstructured":"Bellemare, M. G., Dabney, W. & Munos, R. A distributional perspective on reinforcement learning. Proc. Mach. Learn. Res. 70, 449\u2013458 (2017).","journal-title":"Proc. Mach. Learn. Res."},{"key":"9089_CR11","first-page":"6745","volume":"119","author":"J Martin","year":"2020","unstructured":"Martin, J., Lyskawinski, M., Li, X. & Englot, B. Stochastically dominant distributional reinforcement learning. Proc. Mach. Learn. Res. 119, 6745\u20136754 (2020).","journal-title":"Proc. Mach. Learn. Res."},{"key":"9089_CR12","doi-asserted-by":"publisher","first-page":"325","DOI":"10.3390\/a16070325","volume":"16","author":"T Th\u00e9ate","year":"2023","unstructured":"Th\u00e9ate, T. & Ernst, D. Risk-sensitive policy with distributional reinforcement learning. Algorithms 16, 325 (2023).","journal-title":"Algorithms"},{"key":"9089_CR13","unstructured":"Puterman, M. L. Markov Decision Processes: Discrete Stochastic Dynamic Programming (Wiley, 2014) ."},{"key":"9089_CR14","doi-asserted-by":"publisher","first-page":"e7362","DOI":"10.1371\/journal.pone.0007362","volume":"4","author":"Z Kurth-Nelson","year":"2009","unstructured":"Kurth-Nelson, Z. & Redish, A. D. Temporal-difference reinforcement learning with distributed representations. PLoS ONE 4, e7362 (2009).","journal-title":"PLoS ONE"},{"key":"9089_CR15","doi-asserted-by":"publisher","unstructured":"Fedus, W., Gelada, C., Bengio, Y., Bellemare, M. G. & Larochelle, H. Hyperbolic discounting and learning over multiple horizons. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1902.06865 (2019).","DOI":"10.48550\/arXiv.1902.06865"},{"key":"9089_CR16","unstructured":"Janner, M., Mordatch, I. & Levine, S. Gamma-models: generative temporal difference learning for infinite-horizon prediction. In Advances in Neural Information Processing Systems 33 (NeurIPS 2020) (eds Larochelle, H. et al.) 1724\u20131735 (Curran Associates, 2020)."},{"key":"9089_CR17","first-page":"21272","volume":"162","author":"S Thakoor","year":"2022","unstructured":"Thakoor, S. et al. Generalised policy improvement with geometric policy composition. Proc. Mach. Learn. Res. 162, 21272\u201321307 (2022).","journal-title":"Proc"},{"key":"9089_CR18","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1162\/NECO_a_00212","volume":"24","author":"KH Shankar","year":"2012","unstructured":"Shankar, K. H. & Howard, M. W. A scale-invariant internal representation of time. Neural Comput. 24, 134\u2013193 (2012).","journal-title":"Neural Comput."},{"key":"9089_CR19","unstructured":"Tano, P., Dayan, P. & Pouget, A. A local temporal difference code for distributional reinforcement learning. In Advances in Neural Information Processing Systems 33 (NeurIPS 2020) (eds Larochelle, H. et al.) 13662\u20131367 (Curran Associates, 2020)."},{"key":"9089_CR20","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1162\/neco_a_01171","volume":"31","author":"Z Tiganj","year":"2019","unstructured":"Tiganj, Z., Gershman, S. J., Sederberg, P. B. & Howard, M. W. Estimating scale-invariant future in continuous time. Neural Comput. 31, 681\u2013709 (2019).","journal-title":"Neural Comput."},{"key":"9089_CR21","unstructured":"Barlow, H. B & Rosenblith, W. A. in Sensory Communication (ed. Rosenblith, W. A.) 217\u2013234 (MIT Press, 1961)."},{"key":"9089_CR22","doi-asserted-by":"publisher","first-page":"910","DOI":"10.1515\/znc-1981-9-1040","volume":"36","author":"S Laughlin","year":"1981","unstructured":"Laughlin, S. A simple coding procedure enhances a neuron\u2019s information capacity. Z. Naturforsch. C 36, 910\u2013912 (1981).","journal-title":"Z. Naturforsch. C"},{"key":"9089_CR23","doi-asserted-by":"publisher","first-page":"1193","DOI":"10.1146\/annurev.neuro.24.1.1193","volume":"24","author":"EP Simoncelli","year":"2001","unstructured":"Simoncelli, E. P. & Olshausen, B. A. Natural image statistics and neural representation. Annu. Rev. Neurosci. 24, 1193\u20131216 (2001).","journal-title":"Annu. Rev. Neurosci."},{"key":"9089_CR24","doi-asserted-by":"publisher","first-page":"787","DOI":"10.1038\/35090500","volume":"412","author":"AL Fairhall","year":"2001","unstructured":"Fairhall, A. L., Lewen, G. D., Bialek, W. & de Ruyter Van Steveninck, R. R. Efficiency and ambiguity in an adaptive neural code. Nature 412, 787\u2013792 (2001).","journal-title":"Nature"},{"key":"9089_CR25","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1901\/jeab.2005.110-04","volume":"84","author":"B Lau","year":"2005","unstructured":"Lau, B. & Glimcher, P. W. Dynamic response-by-response models of matching behavior in rhesus monkeys. J. Exp. Anal. Behav. 84, 555\u2013579 (2005).","journal-title":"J. Exp. Anal. Behav."},{"key":"9089_CR26","doi-asserted-by":"publisher","first-page":"5391","DOI":"10.1073\/pnas.1317695111","volume":"111","author":"PH Rudebeck","year":"2014","unstructured":"Rudebeck, P. H. et al. A role for primate subgenual cingulate cortex in sustaining autonomic arousal. Proc. Natl Acad. Sci. USA 111, 5391\u20135396 (2014).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"9089_CR27","doi-asserted-by":"publisher","first-page":"671","DOI":"10.1007\/s10071-018-1202-2","volume":"21","author":"T Cash-Padgett","year":"2018","unstructured":"Cash-Padgett, T., Azab, H., Yoo, S. B. M. & Hayden, B. Y. Opposing pupil responses to offered and anticipated reward values. Anim. Cogn. 21, 671\u2013684 (2018).","journal-title":"Anim. Cogn."},{"key":"9089_CR28","doi-asserted-by":"publisher","first-page":"2103","DOI":"10.1162\/NECO_a_00638","volume":"26","author":"D Ganguli","year":"2014","unstructured":"Ganguli, D. & Simoncelli, E. P. Efficient sensory encoding and bayesian inference with heterogeneous neural populations. Neural Comput. 26, 2103\u20132134 (2014).","journal-title":"Neural Comput."},{"key":"9089_CR29","doi-asserted-by":"publisher","first-page":"e1010350","DOI":"10.1371\/journal.pcbi.1010350","volume":"18","author":"K Louie","year":"2022","unstructured":"Louie, K. Asymmetric and adaptive reward coding via normalized reinforcement learning. PLoS Comput. Biol. 18, e1010350 (2022).","journal-title":"PLoS Comput. Biol."},{"key":"9089_CR30","doi-asserted-by":"publisher","first-page":"1333","DOI":"10.1038\/s41593-024-01671-x","volume":"27","author":"HH Sch\u00fctt","year":"2024","unstructured":"Sch\u00fctt, H. H., Kim, D. & Ma, W. J. Reward prediction error neurons implement an efficient code for reward. Nat. Neurosci. 27, 1333\u20131339 (2024).","journal-title":"Nat. Neurosci."},{"key":"9089_CR31","doi-asserted-by":"publisher","first-page":"363","DOI":"10.2307\/1914185","volume":"47","author":"D Kahneman","year":"1979","unstructured":"Kahneman, D. & Tversky, A. Prospect theory: an analysis of decision under risk. Econometrica 47, 363\u2013391 (1979).","journal-title":"Econometrica"},{"key":"9089_CR32","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1162\/neco.1993.5.4.613","volume":"5","author":"P Dayan","year":"1993","unstructured":"Dayan, P. Improving generalization for temporal difference learning: the successor representation. Neural Comput. 5, 613\u2013624 (1993).","journal-title":"Neural Comput."},{"key":"9089_CR33","doi-asserted-by":"crossref","unstructured":"Brunec, I. K. & Momennejad, I. Predictive representations in hippocampal and prefrontal hierarchies. J. Neurosci. 42, 299\u2013312 (2022).","DOI":"10.1523\/JNEUROSCI.1327-21.2021"},{"key":"9089_CR34","doi-asserted-by":"publisher","first-page":"15788","DOI":"10.1073\/pnas.1308718110","volume":"110","author":"H Yamada","year":"2013","unstructured":"Yamada, H., Tymula, A., Louie, K. & Glimcher, P. W. Thirst-dependent risk preferences in monkeys identify a primitive form of wealth. Proc. Natl Acad. Sci. USA 110, 15788\u201315793 (2013).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"9089_CR35","doi-asserted-by":"publisher","first-page":"2491","DOI":"10.1016\/j.cub.2014.08.064","volume":"24","author":"WR Stauffer","year":"2014","unstructured":"Stauffer, W. R., Lak, A. & Schultz, W. Dopamine reward prediction error responses reflect marginal utility. Curr. Biol. 24, 2491\u20132500 (2014).","journal-title":"Curr. Biol."},{"key":"9089_CR36","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1093\/icb\/36.4.402","volume":"36","author":"A Kacelnik","year":"1996","unstructured":"Kacelnik, A. & Bateson, M. Risky theories\u2014the effects of variance on foraging decisions. Am. Zool. 36, 402\u2013434 (1996).","journal-title":"Am. Zool."},{"key":"9089_CR37","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1007\/s10164-013-0362-4","volume":"31","author":"J Yoshimura","year":"2013","unstructured":"Yoshimura, J., Ito, H., Miller III, D. G. & Tainaka, K.-I. Dynamic decision-making in uncertain environments: I. The principle of dynamic utility. J. Ethol. 31, 101\u2013105 (2013).","journal-title":"J. Ethol."},{"key":"9089_CR38","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1016\/0003-3472(86)90032-1","volume":"34","author":"JH Kagel","year":"1986","unstructured":"Kagel, J. H., Green, L. & Caraco, T. When foragers discount the future: constraint or adaptation? Anim. Behav. 34, 271\u2013283 (1986).","journal-title":"Anim. Behav."},{"key":"9089_CR39","doi-asserted-by":"publisher","first-page":"1273","DOI":"10.1126\/science.aah5234","volume":"354","author":"S Soares","year":"2016","unstructured":"Soares, S., Atallah, B. V. & Paton, J. J. Midbrain dopamine neurons control judgment of time. Science 354, 1273\u20131277 (2016).","journal-title":"Science"},{"key":"9089_CR40","doi-asserted-by":"publisher","first-page":"1214","DOI":"10.1038\/nn1954","volume":"10","author":"TEJ Behrens","year":"2007","unstructured":"Behrens, T. E. J., Woolrich, M. W., Walton, M. E. & Rushworth, M. F. S. Learning the value of information in an uncertain world. Nat. Neurosci. 10, 1214\u20131221 (2007).","journal-title":"Nat. Neurosci."},{"key":"9089_CR41","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1038\/s41583-019-0180-y","volume":"20","author":"A Soltani","year":"2019","unstructured":"Soltani, A. & Izquierdo, A. Adaptive learning under expected and unexpected uncertainty. Nat. Rev. Neurosci. 20, 635\u2013644 (2019).","journal-title":"Nat. Rev. Neurosci."},{"key":"9089_CR42","doi-asserted-by":"publisher","first-page":"1040","DOI":"10.1038\/nn.3130","volume":"15","author":"MR Nassar","year":"2012","unstructured":"Nassar, M. R. et al. Rational regulation of learning dynamics by pupil-linked arousal systems. Nat. Neurosci. 15, 1040\u20131046 (2012).","journal-title":"Nat. Neurosci."},{"key":"9089_CR43","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-13953-1","volume":"11","author":"MJ Sharpe","year":"2020","unstructured":"Sharpe, M. J. et al. Dopamine transients do not act as model-free prediction errors during associative learning. Nat. Commun. 11, 106 (2020).","journal-title":"Nat. Commun."},{"key":"9089_CR44","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1038\/s41586-019-1261-9","volume":"570","author":"B Engelhard","year":"2019","unstructured":"Engelhard, B. et al. Specialized coding of sensory, motor and cognitive variables in VTA dopamine neurons. Nature 570, 509\u2013513 (2019).","journal-title":"Nature"},{"key":"9089_CR45","doi-asserted-by":"publisher","first-page":"735","DOI":"10.1038\/nn.4538","volume":"20","author":"MJ Sharpe","year":"2017","unstructured":"Sharpe, M. J. et al. Dopamine transients are sufficient and necessary for acquisition of model-based associations. Nat. Neurosci. 20, 735\u2013742 (2017).","journal-title":"Nat. Neurosci."},{"key":"9089_CR46","doi-asserted-by":"publisher","first-page":"eabq6740","DOI":"10.1126\/science.abq6740","volume":"378","author":"H Jeong","year":"2022","unstructured":"Jeong, H. et al. Mesolimbic dopamine release conveys causal associations. Science 378, eabq6740 (2022).","journal-title":"Science"},{"key":"9089_CR47","doi-asserted-by":"publisher","first-page":"1563","DOI":"10.1038\/s41593-018-0245-7","volume":"21","author":"LT Coddington","year":"2018","unstructured":"Coddington, L. T. & Dudman, J. T. The timing of action determines reward prediction signals in identified midbrain dopamine neurons. Nat. Neurosci. 21, 1563\u20131573 (2018).","journal-title":"Nat. Neurosci."},{"key":"9089_CR48","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1007\/BF00992697","volume":"8","author":"G Tesauro","year":"1992","unstructured":"Tesauro, G. Practical issues in temporal difference learning. Mach. Learn. 8, 257\u2013277 (1992).","journal-title":"Mach. Learn."},{"key":"9089_CR49","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1016\/j.conb.2011.02.009","volume":"21","author":"AM Bornstein","year":"2011","unstructured":"Bornstein, A. M. & Daw, N. D. Multiplicity of control in the basal ganglia: computational roles of striatal subregions. Curr. Opin. Neurobiol. 21, 374\u2013380 (2011).","journal-title":"Curr. Opin. Neurobiol."},{"key":"9089_CR50","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1038\/nn.2261","volume":"12","author":"HH Yin","year":"2009","unstructured":"Yin, H. H. et al. Dynamic reorganization of striatal circuits during the acquisition and consolidation of a skill. Nat. Neurosci. 12, 333\u2013341 (2009).","journal-title":"Nat. Neurosci."},{"key":"9089_CR51","doi-asserted-by":"publisher","first-page":"2733\u20132749","DOI":"10.1016\/j.cell.2021.03.046","volume":"184","author":"AA Hamid","year":"2021","unstructured":"Hamid, A. A., Frank, M. J. & Moore, C. I. Wave-like dopamine dynamics as a mechanism for spatiotemporal credit assignment. Cell 184, 2733\u20132749 (2021).","journal-title":"Cell"},{"key":"9089_CR52","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1038\/s41586-022-04894-9","volume":"607","author":"BF Cruz","year":"2022","unstructured":"Cruz, B. F. et al. Action suppression reveals opponent parallel control via striatal circuits. Nature 607, 521\u2013526 (2022).","journal-title":"Nature"},{"key":"9089_CR53","doi-asserted-by":"publisher","first-page":"1574","DOI":"10.1038\/s41593-024-01689-1","volume":"27","author":"RS Lee","year":"2024","unstructured":"Lee, R. S., Sagiv, Y., Engelhard, B., Witten, I. B. & Daw, N. D. A feature-specific prediction error model explains dopaminergic heterogeneity. Nat. Neurosci. 27, 1574\u20131586 (2024).","journal-title":"Nat. Neurosci."},{"key":"9089_CR54","doi-asserted-by":"publisher","first-page":"830","DOI":"10.1038\/s41593-023-01310-x","volume":"26","author":"YK Takahashi","year":"2023","unstructured":"Takahashi, Y. K. et al. Dopaminergic prediction errors in the ventral tegmental area reflect a multithreaded predictive model. Nat. Neurosci. 26, 830\u2013839 (2023).","journal-title":"Nat. Neurosci."},{"key":"9089_CR55","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1016\/j.tins.2008.10.004","volume":"32","author":"PD Balsam","year":"2009","unstructured":"Balsam, P. D. & Gallistel, C. R. Temporal maps and informativeness in associative learning. Trends Neurosci. 32, 73\u201378 (2009).","journal-title":"Trends Neurosci."},{"key":"9089_CR56","doi-asserted-by":"publisher","unstructured":"International Brain Laboratory. Behavior, Appendix 1: IBL protocol for headbar implant surgery in mice. Figshare https:\/\/doi.org\/10.6084\/m9.figshare.11634726.v5 (2020).","DOI":"10.6084\/m9.figshare.11634726.v5"},{"key":"9089_CR57","doi-asserted-by":"publisher","first-page":"1224","DOI":"10.1038\/nn1142","volume":"6","author":"N Uchida","year":"2003","unstructured":"Uchida, N. & Mainen, Z. F. Speed and accuracy of olfactory discrimination in the rat. Nat. Neurosci. 6, 1224\u20131229 (2003).","journal-title":"Nat. Neurosci."},{"key":"9089_CR58","doi-asserted-by":"publisher","first-page":"7","DOI":"10.3389\/fninf.2015.00007","volume":"9","author":"G Lopes","year":"2015","unstructured":"Lopes, G. et al. Bonsai: an event-based framework for processing and controlling data streams. Front. Neuroinform. 9, 7 (2015).","journal-title":"Front. Neuroinform."},{"key":"9089_CR59","doi-asserted-by":"publisher","first-page":"045003","DOI":"10.1088\/1741-2552\/aa5eea","volume":"14","author":"JH Siegle","year":"2017","unstructured":"Siegle, J. H. et al. Open ephys: an open-source, plugin-based platform for multichannel electrophysiology. J. Neural Eng. 14, 045003 (2017).","journal-title":"J. Neural Eng."},{"key":"9089_CR60","doi-asserted-by":"publisher","first-page":"1129","DOI":"10.1162\/neco.1995.7.6.1129","volume":"7","author":"AJ Bell","year":"1995","unstructured":"Bell, A. J. & Sejnowski, T. J. An information-maximization approach to blind separation and blind deconvolution. Neural Comput. 7, 1129\u20131159 (1995).","journal-title":"Neural Comput."},{"key":"9089_CR61","doi-asserted-by":"publisher","first-page":"626","DOI":"10.1109\/72.761722","volume":"10","author":"A Hyvarinen","year":"1999","unstructured":"Hyvarinen, A. Fast and robust fixed-point algorithms for independent component analysis. IEEE Trans. Neural Netw. 10, 626\u2013634 (1999).","journal-title":"IEEE Trans. Neural Netw."},{"key":"9089_CR62","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1038\/nature12176","volume":"498","author":"D Kvitsiani","year":"2013","unstructured":"Kvitsiani, D. et al. Distinct behavioural and network correlates of two interneuron types in prefrontal cortex. Nature 498, 363\u2013366 (2013).","journal-title":"Nature"},{"key":"9089_CR63","doi-asserted-by":"publisher","first-page":"8699","DOI":"10.1523\/JNEUROSCI.0971-11.2011","volume":"31","author":"DN Hill","year":"2011","unstructured":"Hill, D. N., Mehta, S. B. & Kleinfeld, D. Quality metrics to accompany spike sorting of extracellular signals. J. Neurosci. 31, 8699\u20138705 (2011).","journal-title":"J. Neurosci."},{"key":"9089_CR64","doi-asserted-by":"publisher","first-page":"3034","DOI":"10.1162\/neco.2008.11-07-654","volume":"20","author":"EA Ludvig","year":"2008","unstructured":"Ludvig, E. A., Sutton, R. S. & Kehoe, E. J. Stimulus representation and the timing of reward-prediction errors in models of the dopamine system. Neural Comput. 20, 3034\u20133054 (2008).","journal-title":"Neural Comput."},{"key":"9089_CR65","first-page":"5528","volume":"97","author":"M Rowland","year":"2019","unstructured":"Rowland, M. et al. Statistics and samples in distributional reinforcement learning. Proc. Mach. Learn. Res. 97, 5528\u20135536 (2019).","journal-title":"Proc. Mach. Learn. Res."},{"key":"9089_CR66","doi-asserted-by":"publisher","first-page":"819","DOI":"10.2307\/1911031","volume":"55","author":"WK Newey","year":"1987","unstructured":"Newey, W. K. & Powell, J. L. Asymmetric least squares estimation and testing. Econometrica 55, 819\u2013847 (1987).","journal-title":"Econometrica"},{"key":"9089_CR67","doi-asserted-by":"publisher","first-page":"1731","DOI":"10.1162\/089976698300017115","volume":"10","author":"N Brunel","year":"1998","unstructured":"Brunel, N. & Nadal, J.-P. Mutual information, fisher information, and population coding. Neural Comput. 10, 1731\u20131757 (1998).","journal-title":"Neural Comput."},{"key":"9089_CR68","unstructured":"Glimcher, P. W. & Fehr, E. Neuroeconomics: Decision Making and the Brain (Academic Press, 2013)."},{"key":"9089_CR69","doi-asserted-by":"publisher","first-page":"479","DOI":"10.1038\/nn.4239","volume":"19","author":"N Eshel","year":"2016","unstructured":"Eshel, N., Tian, J., Bukwich, M. & Uchida, N. Dopamine neurons share common response function for reward prediction error. Nat. Neurosci. 19, 479\u2013486 (2016).","journal-title":"Nat. Neurosci."},{"key":"9089_CR70","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1038\/nature10754","volume":"482","author":"JY Cohen","year":"2012","unstructured":"Cohen, J. Y., Haesler, S., Vong, L., Lowell, B. B. & Uchida, N. Neuron-type-specific signals for reward and punishment in the ventral tegmental area. Nature 482, 85\u201388 (2012).","journal-title":"Nature"},{"key":"9089_CR71","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1038\/s41593-019-0567-0","volume":"23","author":"K Lee","year":"2020","unstructured":"Lee, K. et al. Temporally restricted dopaminergic control of reward-conditioned movements. Nat. Neurosci. 23, 209\u2013216 (2020).","journal-title":"Nat. Neurosci."},{"key":"9089_CR72","doi-asserted-by":"publisher","first-page":"1699","DOI":"10.1002\/cne.23880","volume":"524","author":"WR Stauffer","year":"2016","unstructured":"Stauffer, W. R., Lak, A., Kobayashi, S. & Schultz, W. Components and characteristics of the dopamine reward utility signal. J. Comp. Neurol. 524, 1699\u20131711 (2016).","journal-title":"J. Comp. Neurol."},{"key":"9089_CR73","doi-asserted-by":"publisher","first-page":"7837","DOI":"10.1523\/JNEUROSCI.1600-08.2008","volume":"28","author":"S Kobayashi","year":"2008","unstructured":"Kobayashi, S. & Schultz, W. Influence of reward delays on responses of dopamine neurons. J. Neurosci. 28, 7837\u20137846 (2008).","journal-title":"J. Neurosci."},{"key":"9089_CR74","doi-asserted-by":"publisher","first-page":"1281","DOI":"10.1038\/s41593-018-0209-y","volume":"21","author":"A Mathis","year":"2018","unstructured":"Mathis, A., Mamidanna, P. & Cury, K. M. Deeplabcut: markerless pose estimation of user-defined body parts with deep learning. Nat. Neurosci. 21, 1281\u20131289 (2018).","journal-title":"Nat. Neurosci."},{"key":"9089_CR75","unstructured":"Yagle, A. E. Regularized matrix computations. Preprint at https:\/\/api.semanticscholar.org\/CorpusID:7810635 (2005)."},{"key":"9089_CR76","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1287\/moor.14.2.303","volume":"14","author":"N Chakravarti","year":"1989","unstructured":"Chakravarti, N. Isotonic median regression: a linear programming approach. Math. Oper. Res. 14, 303\u2013308 (1989).","journal-title":"Math. Oper. Res."},{"key":"9089_CR77","first-page":"1623","volume":"180","author":"V Picheny","year":"2022","unstructured":"Picheny, V., Moss, H., Torossian, L. & Durrande, N. Bayesian quantile and expectile optimisation. Proc. Mach. Learn. Res. 180, 1623\u20131633 (2022).","journal-title":"Proc. Mach. Learn. Res."},{"key":"9089_CR78","doi-asserted-by":"publisher","unstructured":"Sousa, M. et al. A multidimensional distributional map of future reward in dopamine neurons. Figshare https:\/\/doi.org\/10.6084\/m9.figshare.28390151.v1 (2025).","DOI":"10.6084\/m9.figshare.28390151.v1"}],"container-title":["Nature"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41586-025-09089-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41586-025-09089-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41586-025-09089-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T12:03:59Z","timestamp":1750248239000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41586-025-09089-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,4]]},"references-count":78,"journal-issue":{"issue":"8068","published-print":{"date-parts":[[2025,6,19]]}},"alternative-id":["9089"],"URL":"https:\/\/doi.org\/10.1038\/s41586-025-09089-6","relation":{},"ISSN":["0028-0836","1476-4687"],"issn-type":[{"value":"0028-0836","type":"print"},{"value":"1476-4687","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,4]]},"assertion":[{"value":"21 November 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 April 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 June 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}