{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T19:26:03Z","timestamp":1773948363486,"version":"3.50.1"},"reference-count":78,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T00:00:00Z","timestamp":1735603200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T00:00:00Z","timestamp":1735603200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100010661","name":"EC | Horizon 2020 Framework Programme","doi-asserted-by":"publisher","award":["101071178"],"award-info":[{"award-number":["101071178"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010661","name":"EC | Horizon 2020 Framework Programme","doi-asserted-by":"publisher","award":["101071178"],"award-info":[{"award-number":["101071178"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010661","name":"EC | Horizon 2020 Framework Programme","doi-asserted-by":"publisher","award":["101071178"],"award-info":[{"award-number":["101071178"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Mach Intell"],"DOI":"10.1038\/s42256-024-00950-3","type":"journal-article","created":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T10:02:04Z","timestamp":1735639324000},"page":"43-55","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Sequential memory improves sample and memory efficiency in episodic control"],"prefix":"10.1038","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5740-1513","authenticated-orcid":false,"given":"Ismael T.","family":"Freire","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adri\u00e1n F.","family":"Amil","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paul F. M. J.","family":"Verschure","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,31]]},"reference":[{"key":"950_CR1","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1126\/science.aar6404","volume":"362","author":"D Silver","year":"2018","unstructured":"Silver, D. et al. A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play. Science 362, 1140\u20131144 (2018).","journal-title":"Science"},{"key":"950_CR2","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O. et al. Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature 575, 350\u2013354 (2019).","journal-title":"Nature"},{"key":"950_CR3","unstructured":"Berner, C. et al. Dota 2 with large scale deep reinforcement learning. Preprint at http:\/\/arxiv.org\/abs\/1912.06680 (2019)."},{"key":"950_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1017\/S0140525X16001837","volume":"40","author":"BM Lake","year":"2017","unstructured":"Lake, B. M., Ullman, T. D., Tenenbaum, J. B. & Gershman, S. J. Building machines that learn and think like people. Behav. Brain Sci. 40, 1\u201358 (2017).","journal-title":"Behav. Brain Sci."},{"key":"950_CR5","unstructured":"Marcus, G. Deep learning: a critical appraisal. Preprint at http:\/\/arxiv.org\/abs\/1801.00631 (2018)."},{"key":"950_CR6","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V. et al. Human-level control through deep reinforcement learning. Nature 518, 529\u2013533 (2015).","journal-title":"Nature"},{"key":"950_CR7","unstructured":"Baker, B. et al. Emergent tool use from multi-agent autocurricula. International Conference on Learning Representations (ICLR, 2020)."},{"key":"950_CR8","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1016\/j.tics.2019.02.006","volume":"23","author":"M Botvinick","year":"2019","unstructured":"Botvinick, M. et al. Reinforcement learning fast and slow. Trends Cogn. Sci. 23, 408\u2013422 (2019).","journal-title":"Trends Cogn. Sci."},{"key":"950_CR9","unstructured":"Hansen, S., Pritzel, A., Sprechmann, P., Barreto, A. & Blundell, C. Fast deep reinforcement learning using online adjustments from the past. In Adv. Neural Information Processing Systems (eds. Bengio, S. et al.) 10567\u201310577 (Curran Associates, 2018)."},{"key":"950_CR10","unstructured":"Zhu, G., Lin, Z., Yang, G. & Zhang, C. Episodic reinforcement learning with associative memory. In International Conference on Learning Representations (eds Zhu, G, Lin, Z., Yang G. & Zhang, C.) 370\u2013384 (Curran Associates, 2019)."},{"key":"950_CR11","doi-asserted-by":"crossref","unstructured":"Lin, Z., Zhao, T., Yang, G. & Zhang, L. Episodic memory deep q-networks. In Proc. IJCAI International Joint Conference on Artificial Intelligence (ed. Lang, J.) 2433\u20132439 (IJCAI, 2018).","DOI":"10.24963\/ijcai.2018\/337"},{"key":"950_CR12","unstructured":"Lee, S. Y., Sungik, C. & Chung, S. Y. Sample-efficient deep reinforcement learning via episodic backward update. In Advances in Neural Information Processing Systems (eds Wallach, H. et al.) 2112\u20132121 (Curran Associates, 2019)."},{"key":"950_CR13","unstructured":"Blundell, C. et al. Model-free episodic control. Preprint at http:\/\/arxiv.org\/abs\/1606.04460 (2016)."},{"key":"950_CR14","unstructured":"Pritzel, A. et al. Neural episodic control. In Proc. 34th International Conference on Machine Learning (eds Precup, D. & Yeh, Y. W.) 2827\u20132836 (ACM, 2017)."},{"key":"950_CR15","doi-asserted-by":"publisher","first-page":"757244","DOI":"10.3389\/fncom.2022.757244","volume":"16","author":"A Yalnizyan-Carson","year":"2022","unstructured":"Yalnizyan-Carson, A. & Richards, B. A. Forgetting enhances episodic control with structured memories. Front. Comput. Neurosci. 16, 757244 (2022).","journal-title":"Front. Comput. Neurosci."},{"key":"950_CR16","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1016\/j.neuron.2009.07.027","volume":"63","author":"TJ Davidson","year":"2009","unstructured":"Davidson, T. J., Kloosterman, F. & Wilson, M. A. Hippocampal replay of extended experience. Neuron 63, 497\u2013507 (2009).","journal-title":"Neuron"},{"key":"950_CR17","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1515\/REVNEURO.1999.10.3-4.291","volume":"10","author":"T Voegtlin","year":"1999","unstructured":"Voegtlin, T. & Verschure, P. F. What can robots tell us about brains? A synthetic approach towards the study of learning and problem solving. Rev. Neurosci. 10, 291\u2013310 (1999).","journal-title":"Rev. Neurosci."},{"key":"950_CR18","doi-asserted-by":"publisher","first-page":"1512","DOI":"10.1126\/science.7878473","volume":"267","author":"JE Lisman","year":"1995","unstructured":"Lisman, J. E. & Idiart, M. A. Storage of 7+\/-2 short-term memories in oscillatory subcycles. Science 267, 1512\u20131515 (1995).","journal-title":"Science"},{"key":"950_CR19","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1017\/S0140525X01333927","volume":"24","author":"O Jensen","year":"2001","unstructured":"Jensen, O. & Lisman, J. E. Dual oscillations as the physiological basis for capacity limits. Behav. Brain Sci. 24, 126 (2001).","journal-title":"Behav. Brain Sci."},{"key":"950_CR20","unstructured":"Ramani, D. A short survey on memory based reinforcement learning. Preprint at http:\/\/arxiv.org\/abs\/1904.06736 (2019)."},{"key":"950_CR21","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1016\/j.tics.2018.07.006","volume":"22","author":"G Buzs\u00e1ki","year":"2018","unstructured":"Buzs\u00e1ki, G. & Tingley, D. Space and time: the hippocampus as a sequence generator. Trends Cogn. Sci. 22, 853\u2013869 (2018).","journal-title":"Trends Cogn. Sci."},{"key":"950_CR22","doi-asserted-by":"publisher","first-page":"1193","DOI":"10.1098\/rstb.2008.0316","volume":"364","author":"J Lisman","year":"2009","unstructured":"Lisman, J. & Redish, A. D. Prediction, sequences and the hippocampus. Philos. Trans. R. Soc. B 364, 1193\u20131201 (2009).","journal-title":"Philos. Trans. R. Soc. B"},{"key":"950_CR23","doi-asserted-by":"publisher","first-page":"20130483","DOI":"10.1098\/rstb.2013.0483","volume":"369","author":"PF Verschure","year":"2014","unstructured":"Verschure, P. F., Pennartz, C. M. & Pezzulo, G. The why, what, where, when and how of goal-directed choice: neuronal and computational principles. Philos. Trans. R. Soc. B 369, 20130483 (2014).","journal-title":"Philos. Trans. R. Soc. B"},{"key":"950_CR24","unstructured":"Merleau-Ponty, M. et al. The Primacy of Perception: And Other Essays on Phenomenological Psychology, the Philosophy of Art, Hhistory, and Politics (Northwestern Univ. Press, 1964)."},{"key":"950_CR25","doi-asserted-by":"publisher","first-page":"997","DOI":"10.1038\/nn.4573","volume":"20","author":"AM Bornstein","year":"2017","unstructured":"Bornstein, A. M. & Norman, K. A. Reinstated episodic context guides sampling-based decisions for reward. Nat. Neurosci. 20, 997\u20131003 (2017).","journal-title":"Nat. Neurosci."},{"key":"950_CR26","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1126\/science.1223252","volume":"338","author":"GE Wimmer","year":"2012","unstructured":"Wimmer, G. E. & Shohamy, D. Preference by association: how memory mechanisms in the hippocampus bias decisions. Science 338, 270\u2013273 (2012).","journal-title":"Science"},{"key":"950_CR27","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1007\/s42113-020-00091-x","volume":"4","author":"CM Wu","year":"2021","unstructured":"Wu, C. M., Schulz, E. & Gershman, S. J. Inference and search on graph-structured spaces. Comput. Brain Behav. 4, 125\u2013147 (2021).","journal-title":"Comput. Brain Behav."},{"key":"950_CR28","doi-asserted-by":"publisher","first-page":"12176","DOI":"10.1523\/JNEUROSCI.3761-07.2007","volume":"27","author":"A Johnson","year":"2007","unstructured":"Johnson, A. & Redish, A. D. Neural ensembles in ca3 transiently encode paths forward of the animal at a decision point. J. Neurosci. 27, 12176\u201312189 (2007).","journal-title":"J. Neurosci."},{"key":"950_CR29","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1037\/xge0000046","volume":"144","author":"EA Ludvig","year":"2015","unstructured":"Ludvig, E. A., Madan, C. R. & Spetch, M. L. Priming memories of past wins induces risk seeking. J. Exp. Psychol. Gen. 144, 24 (2015).","journal-title":"J. Exp. Psychol. Gen."},{"key":"950_CR30","doi-asserted-by":"publisher","first-page":"e1581","DOI":"10.1002\/wcs.1581","volume":"13","author":"S Wang","year":"2022","unstructured":"Wang, S., Feng, S. F. & Bornstein, A. M. Mixing memory and desire: How memory reactivation supports deliberative decision-making. Wiley Interdiscip. Rev. Cogn. Sci. 13, e1581 (2022).","journal-title":"Wiley Interdiscip. Rev. Cogn. Sci."},{"key":"950_CR31","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1146\/annurev-psych-122414-033625","volume":"68","author":"SJ Gershman","year":"2017","unstructured":"Gershman, S. J. & Daw, N. D. Reinforcement learning and episodic memory in humans and animals: an integrative framework. Annu. Rev. Psychol. 68, 101\u2013128 (2017).","journal-title":"Annu. Rev. Psychol."},{"key":"950_CR32","doi-asserted-by":"publisher","first-page":"582","DOI":"10.1016\/j.tics.2021.03.016","volume":"25","author":"D Santos-Pata","year":"2021","unstructured":"Santos-Pata, D. et al. Epistemic autonomy: self-supervised learning in the mammalian hippocampus. Trends Cogn. Sci. 25, 582\u2013595 (2021).","journal-title":"Trends Cogn. Sci."},{"key":"950_CR33","doi-asserted-by":"publisher","first-page":"102364","DOI":"10.1016\/j.isci.2021.102364","volume":"24","author":"D Santos-Pata","year":"2021","unstructured":"Santos-Pata, D. et al. Entorhinal mismatch: a model of self-supervised learning in the hippocampus. iScience 24, 102364 (2021).","journal-title":"iScience"},{"key":"950_CR34","unstructured":"Amil, A. F., Freire, I. T. & Verschure, P. F. Discretization of continuous input spaces in the hippocampal autoencoder. Preprint at http:\/\/arxiv.org\/abs\/2405.14600 (2024)."},{"key":"950_CR35","doi-asserted-by":"publisher","first-page":"1051","DOI":"10.1016\/j.neuron.2010.11.024","volume":"68","author":"C Renn\u00f3-Costa","year":"2010","unstructured":"Renn\u00f3-Costa, C., Lisman, J. E. & Verschure, P. F. The mechanism of rate remapping in the dentate gyrus. Neuron 68, 1051\u20131058 (2010).","journal-title":"Neuron"},{"key":"950_CR36","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-018-07882-8","volume":"10","author":"DP Estefan","year":"2019","unstructured":"Estefan, D. P. et al. Coordinated representational reinstatement in the human hippocampus and lateral temporal cortex during episodic memory retrieval. Nat. Commun. 10, 1\u201313 (2019).","journal-title":"Nat. Commun."},{"key":"950_CR37","doi-asserted-by":"publisher","first-page":"7497","DOI":"10.1523\/JNEUROSCI.6044-08.2009","volume":"29","author":"L de Almeida","year":"2009","unstructured":"de Almeida, L., Idiart, M. & Lisman, J. E. A second function of gamma frequency oscillations: an E%-max winner-take-all mechanism selects which cells fire. J. Neurosci. 29, 7497\u20137503 (2009).","journal-title":"J. Neurosci."},{"key":"950_CR38","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1002\/(SICI)1098-1063(1996)6:2<149::AID-HIPO6>3.0.CO;2-K","volume":"6","author":"WE Skaggs","year":"1996","unstructured":"Skaggs, W. E., McNaughton, B. L., Wilson, M. A. & Barnes, C. A. Theta phase precession in hippocampal neuronal populations and the compression of temporal sequences. Hippocampus 6, 149\u2013172 (1996).","journal-title":"Hippocampus"},{"key":"950_CR39","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1038\/nrn.2015.30","volume":"17","author":"AD Redish","year":"2016","unstructured":"Redish, A. D. Vicarious trial and error. Nat. Rev. Neurosci. 17, 147\u2013159 (2016).","journal-title":"Nat. Rev. Neurosci."},{"key":"950_CR40","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1038\/26216","volume":"395","author":"NS Clayton","year":"1998","unstructured":"Clayton, N. S. & Dickinson, A. Episodic-like memory during cache recovery by scrub jays. Nature 395, 272\u2013274 (1998).","journal-title":"Nature"},{"key":"950_CR41","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1016\/j.conb.2011.12.005","volume":"22","author":"DJ Foster","year":"2012","unstructured":"Foster, D. J. & Knierim, J. J. Sequence learning and the role of the hippocampus in rodent navigation. Curr. Opin. Neurobiol. 22, 294\u2013300 (2012).","journal-title":"Curr. Opin. Neurobiol."},{"key":"950_CR42","doi-asserted-by":"publisher","first-page":"1609","DOI":"10.1038\/s41593-018-0232-z","volume":"21","author":"MG Mattar","year":"2018","unstructured":"Mattar, M. G. & Daw, N. D. Prioritized memory access explains planning and hippocampal replay. Nat. Neurosci. 21, 1609\u20131617 (2018).","journal-title":"Nat. Neurosci."},{"key":"950_CR43","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1146\/annurev-psych-010416-044131","volume":"68","author":"H Eichenbaum","year":"2017","unstructured":"Eichenbaum, H. Memory: organization and control. Annu. Rev. Psychol. 68, 19\u201345 (2017).","journal-title":"Annu. Rev. Psychol."},{"key":"950_CR44","doi-asserted-by":"publisher","first-page":"e2021238118","DOI":"10.1073\/pnas.2021238118","volume":"118","author":"DP Estefan","year":"2021","unstructured":"Estefan, D. P. et al. Volitional learning promotes theta phase coding in the human hippocampus. Proc. Natl Acad. Sci. USA 118, e2021238118 (2021).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"950_CR45","doi-asserted-by":"publisher","unstructured":"Sutton, R. S. & Barto, A. G. Reinforcement Learning: An Introduction (MIT Press, 2018); https:\/\/doi.org\/10.1109\/tnn.2004.842673","DOI":"10.1109\/tnn.2004.842673"},{"key":"950_CR46","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF00992698","volume":"8","author":"CJCH Watkins","year":"1992","unstructured":"Watkins, C. J. C. H. & Dayan, P. Q-learning. Mach. Learn. 8, 279\u2013292 (1992).","journal-title":"Mach. Learn."},{"key":"950_CR47","doi-asserted-by":"publisher","first-page":"456","DOI":"10.1002\/hipo.20532","volume":"19","author":"JL Kubie","year":"2009","unstructured":"Kubie, J. L. & Fenton, A. A. Heading-vector navigation based on head-direction cells and path integration. Hippocampus 19, 456\u2013479 (2009).","journal-title":"Hippocampus"},{"key":"950_CR48","doi-asserted-by":"crossref","unstructured":"Mathews Z. et al. Insect-like mapless navigation based on head direction cells and contextual learning using chemo-visual sensors. 2009 IEEE\/RSJ International Conference on Intelligent Robots and Systems 2243\u20132250 (IEEE, 2009).","DOI":"10.1109\/IROS.2009.5354264"},{"key":"950_CR49","doi-asserted-by":"publisher","first-page":"045017","DOI":"10.1088\/2632-072X\/ac3ad2","volume":"2","author":"AF Amil","year":"2021","unstructured":"Amil, A. F. & Verschure, P. F. Supercritical dynamics at the edge-of-chaos underlies optimal decision-making. J. Phys. Complex. 2, 045017 (2021).","journal-title":"J. Phys. Complex."},{"key":"950_CR50","doi-asserted-by":"publisher","first-page":"620","DOI":"10.1038\/nature02024","volume":"425","author":"PF Verschure","year":"2003","unstructured":"Verschure, P. F., Voegtlin, T. & Douglas, R. J. Environmentally mediated synergy between perception and behaviour in mobile robots. Nature 425, 620\u2013624 (2003).","journal-title":"Nature"},{"key":"950_CR51","unstructured":"Vikbladh, O., Shohamy, D. & Daw, N. Episodic contributions to model-based reinforcement learning. In Annual Conference on Cognitive Computational Neuroscience (CCN, 2017)."},{"key":"950_CR52","doi-asserted-by":"publisher","first-page":"2877","DOI":"10.1152\/jn.00145.2018","volume":"120","author":"R Caz\u00e9","year":"2018","unstructured":"Caz\u00e9, R., Khamassi, M., Aubin, L. & Girard, B. Hippocampal replays under the scrutiny of reinforcement learning models. J. Neurophysiol. 120, 2877\u20132896 (2018).","journal-title":"J. Neurophysiol."},{"key":"950_CR53","first-page":"591","volume":"27","author":"C Gonzalez","year":"2003","unstructured":"Gonzalez, C., Lerch, J. F. & Lebiere, C. Instance-based learning in dynamic decision making. Cogn. Sci. 27, 591\u2013635 (2003).","journal-title":"Cogn. Sci."},{"key":"950_CR54","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1037\/a0024558","volume":"118","author":"C Gonzalez","year":"2011","unstructured":"Gonzalez, C. & Dutt, V. Instance-based learning: integrating sampling and repeated decisions from experience. Psychological Rev. 118, 523 (2011).","journal-title":"Psychological Rev."},{"key":"950_CR55","unstructured":"Lengyel, M. & Dayan, P. Hippocampal contributions to control: the third way. In Proc. Advances in Neural Information Processing Systems (eds. Platt, J. et al.) 889\u2013896 (Curran, 2008)."},{"key":"950_CR56","doi-asserted-by":"publisher","first-page":"e0234434","DOI":"10.1371\/journal.pone.0234434","volume":"15","author":"IT Freire","year":"2020","unstructured":"Freire, I. T., Moulin-Frier, C., Sanchez-Fibla, M., Arsiwalla, X. D. & Verschure, P. F. Modeling the formation of social conventions from embodied real-time interactions. PLoS ONE 15, e0234434 (2020).","journal-title":"PLoS ONE"},{"key":"950_CR57","unstructured":"Papoudakis, G., Christianos, F., Rahman, A. & Albrecht, S. V. Dealing with non-stationarity in multi-agent deep reinforcement learning. Preprint at http:\/\/arxiv.org\/abs\/1906.04737 (2019)."},{"key":"950_CR58","unstructured":"Freire, I. & Verschure, P. High-fidelity social learning via shared episodic memories can improve collaborative foraging. Paper presented at Intrinsically Motivated Open-Ended Learning Workshop@NeurIPS 2023 (2023)."},{"key":"950_CR59","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1016\/j.artint.2018.01.002","volume":"258","author":"SV Albrecht","year":"2018","unstructured":"Albrecht, S. V. & Stone, P. Autonomous agents modelling other agents: a comprehensive survey and open problems. Artif. Intell. 258, 66\u201395 (2018).","journal-title":"Artif. Intell."},{"key":"950_CR60","unstructured":"Freire, I. T., Arsiwalla, X. D., Puigb\u00f2, J.-Y. & Verschure, P. F. Limits of multi-agent predictive models in the formation of social conventions. In Proc. Artificial Intelligence Research and Development (eds Falomir, Z. et al.) 297\u2013301 (IOS, 2018)."},{"key":"950_CR61","doi-asserted-by":"crossref","unstructured":"Freire, I. T., Puigb\u00f2, J.-Y., Arsiwalla, X. D. & Verschure, P. F. Modeling the opponent\u2019s action using control-based reinforcement learning. In Proc. Conference on Biomimetic and Biohybrid Systems (eds Vouloutsi, V. et al.) 179\u2013186 (Springer, 2018).","DOI":"10.1007\/978-3-319-95972-6_19"},{"key":"950_CR62","doi-asserted-by":"publisher","first-page":"441","DOI":"10.3390\/info14080441","volume":"14","author":"IT Freire","year":"2023","unstructured":"Freire, I. T., Arsiwalla, X. D., Puigb\u00f2, J.-Y. & Verschure, P. Modeling theory of mind in dyadic games using adaptive feedback control. Information 14, 441 (2023).","journal-title":"Information"},{"key":"950_CR63","doi-asserted-by":"crossref","unstructured":"Kahali, S. et al. Distributed adaptive control for virtual cyborgs: a case study for personalized rehabilitation. In Proc. Conference on Biomimetic and Biohybrid Systems (eds Meder, F. et al.) 16\u201332 (Springer, 2023).","DOI":"10.1007\/978-3-031-38857-6_2"},{"key":"950_CR64","doi-asserted-by":"publisher","first-page":"1248646","DOI":"10.3389\/frobt.2024.1248646","volume":"11","author":"IT Freire","year":"2024","unstructured":"Freire, I. T., Guerrero-Rosado, O., Amil, A. F. & Verschure, P. F. Socially adaptive cognitive architecture for human-robot collaboration in industrial settings. Front. Robot. AI 11, 1248646 (2024).","journal-title":"Front. Robot. AI"},{"key":"950_CR65","first-page":"55","volume":"1","author":"PF Verschure","year":"2012","unstructured":"Verschure, P. F. Distributed adaptive control: a theory of the mind, brain, body nexus. BICA 1, 55\u201372 (2012).","journal-title":"BICA"},{"key":"950_CR66","doi-asserted-by":"publisher","first-page":"1052998","DOI":"10.3389\/frobt.2022.1052998","volume":"9","author":"OG Rosado","year":"2022","unstructured":"Rosado, O. G., Amil, A. F., Freire, I. T. & Verschure, P. F. Drive competition underlies effective allostatic orchestration. Front. Robot. AI 9, 1052998 (2022).","journal-title":"Front. Robot. AI"},{"key":"950_CR67","doi-asserted-by":"publisher","first-page":"1497","DOI":"10.1038\/s41593-018-0258-2","volume":"21","author":"ND Daw","year":"2018","unstructured":"Daw, N. D. Are we of two minds? Nat. Neurosci. 21, 1497\u20131499 (2018).","journal-title":"Nat. Neurosci."},{"key":"950_CR68","doi-asserted-by":"crossref","unstructured":"Freire, I. T., Urikh, D., Arsiwalla, X. D. & Verschure, P. F. Machine morality: from harm-avoidance to human-robot cooperation. In Proc. Conference on Biomimetic and Biohybrid Systems (eds Vouloutsi, V. et al.) 116\u2013127 (Springer, 2020).","DOI":"10.1007\/978-3-030-64313-3_13"},{"key":"950_CR69","doi-asserted-by":"publisher","first-page":"20150448","DOI":"10.1098\/rstb.2015.0448","volume":"371","author":"PF Verschure","year":"2016","unstructured":"Verschure, P. F. Synthetic consciousness: the distributed adaptive control perspective. Philos. Trans. R. Soc. B 371, 20150448 (2016).","journal-title":"Philos. Trans. R. Soc. B"},{"key":"950_CR70","doi-asserted-by":"publisher","first-page":"805","DOI":"10.1016\/j.neuron.2020.07.011","volume":"107","author":"TD Goode","year":"2020","unstructured":"Goode, T. D., Tanaka, K. Z., Sahay, A. & McHugh, T. J. An integrated index: engrams, place cells, and hippocampal memory. Neuron 107, 805\u2013820 (2020).","journal-title":"Neuron"},{"key":"950_CR71","doi-asserted-by":"publisher","first-page":"e1012628","DOI":"10.1371\/journal.pcbi.1012628","volume":"20.12","author":"AF Amil","year":"2024","unstructured":"Amil, A F., Albesa-Gonz\u00e1lez, A. & Verschure, P. F. M. J. Theta oscillations optimize a speed-precision trade-off in phase coding neurons. PLOS Comp. Biol. 20.12, e1012628 (2024).","journal-title":"PLOS Comp. Biol."},{"key":"950_CR72","doi-asserted-by":"publisher","first-page":"704","DOI":"10.1038\/19525","volume":"398","author":"L Tremblay","year":"1999","unstructured":"Tremblay, L. & Schultz, W. Relative reward preference in primate orbitofrontal cortex. Nature 398, 704\u2013708 (1999).","journal-title":"Nature"},{"key":"950_CR73","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1007\/s00221-005-2223-z","volume":"162","author":"HC Cromwell","year":"2005","unstructured":"Cromwell, H. C., Hassani, O. K. & Schultz, W. Relative reward processing in primate striatum. Exp. Brain Res. 162, 520\u2013525 (2005).","journal-title":"Exp. Brain Res."},{"key":"950_CR74","doi-asserted-by":"publisher","first-page":"20160853","DOI":"10.1098\/rsbl.2016.0853","volume":"13","author":"F Soldati","year":"2017","unstructured":"Soldati, F., Burman, O. H., John, E. A., Pike, T. W. & Wilkinson, A. Long-term memory of relative reward values. Biol. Lett. 13, 20160853 (2017).","journal-title":"Biol. Lett."},{"key":"950_CR75","unstructured":"Beyret, B. et al. The Animal-AI environment: training and testing animal-like artificial cognition. Preprint at http:\/\/arxiv.org\/abs\/1909.07483 (2019)."},{"key":"950_CR76","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1038\/s42256-019-0050-3","volume":"1","author":"M Crosby","year":"2019","unstructured":"Crosby, M., Beyret, B. & Halina, M. The Animal-AI olympics. Nat. Mach. Intell. 1, 257 (2019).","journal-title":"Nat. Mach. Intell."},{"key":"950_CR77","doi-asserted-by":"publisher","unstructured":"Freire, I. T. Dataset for \u2018Sequential memory improves sample and memory efficiency in episodic control\u2019. Zenodo https:\/\/doi.org\/10.5281\/zenodo.11506323 (2024).","DOI":"10.5281\/zenodo.11506323"},{"key":"950_CR78","doi-asserted-by":"publisher","unstructured":"Freire, I. T. IsmaelTito\/SEC: SEC v.1.0 release (v.1.0.0). Zenodo https:\/\/doi.org\/10.5281\/zenodo.14014111 (2024).","DOI":"10.5281\/zenodo.14014111"}],"container-title":["Nature Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s42256-024-00950-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-024-00950-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-024-00950-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,26]],"date-time":"2025-01-26T23:03:48Z","timestamp":1737932628000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s42256-024-00950-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,31]]},"references-count":78,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,1]]}},"alternative-id":["950"],"URL":"https:\/\/doi.org\/10.1038\/s42256-024-00950-3","relation":{},"ISSN":["2522-5839"],"issn-type":[{"value":"2522-5839","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,31]]},"assertion":[{"value":"6 October 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 November 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 December 2024","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"}}]}}