{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T10:31:35Z","timestamp":1779877895207,"version":"3.53.1"},"reference-count":97,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:00:00Z","timestamp":1740096000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:00:00Z","timestamp":1740096000000},"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":["Nat Mach Intell"],"DOI":"10.1038\/s42256-025-00981-4","type":"journal-article","created":{"date-parts":[[2025,2,23]],"date-time":"2025-02-23T23:02:57Z","timestamp":1740351777000},"page":"205-220","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Goals as reward-producing programs"],"prefix":"10.1038","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8184-8940","authenticated-orcid":false,"given":"Guy","family":"Davidson","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Graham","family":"Todd","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julian","family":"Togelius","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Todd M.","family":"Gureckis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8959-3401","authenticated-orcid":false,"given":"Brenden M.","family":"Lake","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,2,21]]},"reference":[{"key":"981_CR1","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1111\/j.1467-9280.1992.tb00019.x","volume":"3","author":"CS Dweck","year":"1992","unstructured":"Dweck, C. S. Article commentary: the study of goals in psychology. Psychol. Sci. 3, 165\u2013167 (1992).","journal-title":"Psychol. Sci."},{"key":"981_CR2","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1037\/0033-2909.120.3.338","volume":"120","author":"JT Austin","year":"1996","unstructured":"Austin, J. T. & Vancouver, J. B. Goal constructs in psychology: structure, process, and content. Psychol. Bull. 120, 338\u2013375 (1996).","journal-title":"Psychol. Bull."},{"key":"981_CR3","unstructured":"Elliot, A. J. & Fryer, J. W. in Handbook of Motivation Science Vol. 638 (ed. Shah, J. Y.) 235\u2013250 (The Guilford Press, 2008)."},{"key":"981_CR4","doi-asserted-by":"publisher","first-page":"642","DOI":"10.1037\/0022-3514.55.4.642","volume":"55","author":"ME Hyland","year":"1988","unstructured":"Hyland, M. E. Motivational control theory: an integrative framework. J. Pers. Soc. Psychol. 55, 642\u2013651 (1988).","journal-title":"J. Pers. Soc. Psychol."},{"key":"981_CR5","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1146\/annurev.psych.53.100901.135153","volume":"53","author":"JS Eccles","year":"2002","unstructured":"Eccles, J. S. & Wigfield, A. Motivational beliefs, values, and goals. Annu. Rev. Psychol. 53, 109\u2013132 (2002).","journal-title":"Annu. Rev. Psychol."},{"key":"981_CR6","unstructured":"Brown, L. V. Psychology of Motivation (Nova Science Publishers, 2007); https:\/\/books.google.com\/books?id=hzPCuKfpXLMC"},{"key":"981_CR7","unstructured":"Fishbach, A. & Ferguson, M. J. in Social Psychology: Handbook of Basic Principles Vol. 2 (eds Kruglanski, A. W. & Higgins, E. T.) 490\u2013515 (The Guilford Press, 2007)."},{"key":"981_CR8","doi-asserted-by":"crossref","unstructured":"Pervin, L. A. Goal Concepts in Personality and Social Psychology (Taylor & Francis, 2015); https:\/\/books.google.com\/books?id=lIXwCQAAQBAJ","DOI":"10.4324\/9781315717517"},{"key":"981_CR9","unstructured":"Moskowitz, G. B. & Grant, H. The Psychology of Goals Vol. 548 (Guilford Press, 2009)."},{"key":"981_CR10","doi-asserted-by":"publisher","first-page":"1150","DOI":"10.1016\/j.tics.2023.08.011","volume":"27","author":"G Molinaro","year":"2023","unstructured":"Molinaro, G. & Collins, A. G. E. A goal-centric outlook on learning. Trends Cogn. Sci. 27, 1150\u20131164 (2023).","journal-title":"Trends Cogn. Sci."},{"key":"981_CR11","unstructured":"Sutton, R. S. & Barto, A. G. Reinforcement Learning: An Introduction (MIT Press, 2018)."},{"key":"981_CR12","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":"981_CR13","doi-asserted-by":"publisher","first-page":"628","DOI":"10.1016\/j.tics.2024.03.006","volume":"28","author":"J Chu","year":"2024","unstructured":"Chu, J., Tenenbaum, J. B. & Schulz, L. E. In praise of folly: flexible goals and human cognition. Trends Cogn. Sci. 28, 628\u2013642 (2024).","journal-title":"Trends Cogn. Sci."},{"key":"981_CR14","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1146\/annurev-devpsych-070120-014806","volume":"2","author":"J Chu","year":"2020","unstructured":"Chu, J. & Schulz, L. E. Play, curiosity, and cognition. Annu. Rev. Dev. Psychol. 2, 317\u2013343 (2020).","journal-title":"Annu. Rev. Dev. Psychol."},{"key":"981_CR15","unstructured":"Lillard, A. S. in Handbook of Child Psychology and Developmental Science Vol. 3 (eds Liben, L. & Mueller, U.) 425\u2013468 (Wiley-Blackwell, 2015)."},{"key":"981_CR16","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1037\/rev0000369","volume":"130","author":"MM Andersen","year":"2023","unstructured":"Andersen, M. M., Kiverstein, J., Miller, M. & Roepstorff, A. Play in predictive minds: a cognitive theory of play. Psychol. Rev. 130, 462\u2013479 (2023).","journal-title":"Psychol. Rev."},{"key":"981_CR17","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1109\/TEVC.2006.890271","volume":"11","author":"P-Y Oudeyer","year":"2007","unstructured":"Oudeyer, P.-Y., Kaplan, F. & Hafner, V. V. Intrinsic motivation systems for autonomous mental development. IEEE Trans. Evol. Comput. 11, 265\u2013286 (2007).","journal-title":"IEEE Trans. Evol. Comput."},{"key":"981_CR18","doi-asserted-by":"crossref","unstructured":"Nguyen, C. T. Games: Agency as Art (Oxford Univ. Press, 2020).","DOI":"10.1093\/oso\/9780190052089.001.0001"},{"key":"981_CR19","unstructured":"Kolve, E. et al. AI2-THOR: an interactive 3D environment for visual AI. Preprint at https:\/\/arxiv.org\/abs\/1712.05474 (2017)."},{"key":"981_CR20","unstructured":"Fodor, J. A. The Language of Thought (Harvard Univ. Press, 1979)."},{"key":"981_CR21","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1080\/03640210701802071","volume":"32","author":"ND Goodman","year":"2008","unstructured":"Goodman, N. D., Tenenbaum, J. B., Feldman, J. & Griffiths, T. L. A rational analysis of rule-based concept learning. Cogn. Sci. 32, 108\u2013154 (2008).","journal-title":"Cogn. Sci."},{"key":"981_CR22","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1016\/j.cognition.2011.11.005","volume":"123","author":"ST Piantadosi","year":"2012","unstructured":"Piantadosi, S. T., Tenenbaum, J. B. & Goodman, N. D. Bootstrapping in a language of thought: a formal model of numerical concept learning. Cognition 123, 199\u2013217 (2012).","journal-title":"Cognition"},{"key":"981_CR23","doi-asserted-by":"publisher","first-page":"900","DOI":"10.1016\/j.tics.2020.07.005","volume":"24","author":"JS Rule","year":"2020","unstructured":"Rule, J. S., Tenenbaum, J. B. & Piantadosi, S. T. The child as hacker. Trends Cogn. Sci.24, 900\u2013915 (2020).","journal-title":"Trends Cogn. Sci."},{"key":"981_CR24","unstructured":"Wong, L. et al. From word models to world models: translating from natural language to the probabilistic language of thought. Preprint at https:\/\/arxiv.org\/abs\/2306.12672 (2023)."},{"key":"981_CR25","unstructured":"Ghallab, M. et al. PDDL\u2014The Planning Domain Definition Language Tech Report CVC TR-98-003\/DCS TR-1165 (Yale Center for Computational Vision and Control, 1998)."},{"key":"981_CR26","doi-asserted-by":"crossref","unstructured":"Chopra, S., Hadsell, R. & LeCun, Y. Learning a similarity metric discriminatively, with application to face verification. In 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition 539\u2013546 (IEEE, 2005).","DOI":"10.1109\/CVPR.2005.202"},{"key":"981_CR27","doi-asserted-by":"publisher","first-page":"193907","DOI":"10.1109\/ACCESS.2020.3031549","volume":"8","author":"PH Le-Khac","year":"2020","unstructured":"Le-Khac, P. H., Healy, G. & Smeaton, A. F. Contrastive representation learning: a framework and review. IEEE Access 8, 193907\u2013193934 (2020).","journal-title":"IEEE Access"},{"key":"981_CR28","doi-asserted-by":"publisher","unstructured":"Pugh, J. K., Soros, L. B & Stanley, K. O. Quality diversity: a new frontier for evolutionary computation. Front. Robot. AI https:\/\/doi.org\/10.3389\/frobt.2016.00040 (2016).","DOI":"10.3389\/frobt.2016.00040"},{"key":"981_CR29","first-page":"109","volume":"170","author":"K Chatzilygeroudis","year":"2020","unstructured":"Chatzilygeroudis, K., Cully, A., Vassiliades, V. & Mouret, J. B. Quality-diversity optimization: a novel branch of stochastic optimization. Springer Optim. Appl. 170, 109\u2013135 (2020).","journal-title":"Springer Optim. Appl."},{"key":"981_CR30","unstructured":"Mouret, J.-B. & Clune, J. Illuminating search spaces by mapping elites. Preprint at https:\/\/arxiv.org\/abs\/1504.04909 (2015)."},{"key":"981_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1006\/cogp.1994.1010","volume":"27","author":"TB Ward","year":"1994","unstructured":"Ward, T. B. Structured imagination: the role of category structure in exemplar generation. Cogn. Psychol. 27, 1\u201340 (1994).","journal-title":"Cogn. Psychol."},{"key":"981_CR32","doi-asserted-by":"publisher","unstructured":"Allen, K. R. et al. Using games to understand the mind. Nat. Hum. Behav. https:\/\/doi.org\/10.1038\/s41562-024-01878-9 (2024).","DOI":"10.1038\/s41562-024-01878-9"},{"key":"981_CR33","doi-asserted-by":"crossref","unstructured":"Liu, M., Zhu, M. & Zhang, W. Goal-conditioned reinforcement learning: problems and solutions. In Proc. 31st International Joint Conference on Artificial Intelligence: Survey Track (ed. De Raedt, L.) 5502\u20135511 (IJCAI, 2022).","DOI":"10.24963\/ijcai.2022\/770"},{"key":"981_CR34","doi-asserted-by":"publisher","first-page":"1159","DOI":"10.1613\/jair.1.13554","volume":"74","author":"C Colas","year":"2022","unstructured":"Colas, C., Karch, T., Sigaud, O. & Oudeyer, P.-Y. Autotelic agents with intrinsically motivated goal-conditioned reinforcement learning: a short survey. J. Artif. Intell. Res. 74, 1159\u20131199 (2022).","journal-title":"J. Artif. Intell. Res."},{"key":"981_CR35","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1613\/jair.1.12440","volume":"73","author":"RT Icarte","year":"2022","unstructured":"Icarte, R. T., Klassen, T. Q., Valenzano, R. & McIlraith, S. A. Reward machines: exploiting reward function structure in reinforcement learning. J. Artif. Intell. Res. 73, 173\u2013208 (2022).","journal-title":"J. Artif. Intell. Res."},{"key":"981_CR36","unstructured":"Pell, B. Metagame in Symmetric Chess-Like Games UCAM-CL-TR-277 (Univ. Cambridge, Computer Laboratory, 1992)."},{"key":"981_CR37","doi-asserted-by":"crossref","unstructured":"Hom, V. & Marks, J. Automatic design of balanced board games. In Proc. AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment Vol. 3 (eds Schaeffer, J. & Mateasvol, M.) 25\u201330 (AAAI Press, 2007).","DOI":"10.1609\/aiide.v3i1.18777"},{"key":"981_CR38","doi-asserted-by":"crossref","unstructured":"Browne, C. & Maire, F. Evolutionary game design. IEEE Trans. Comput. Intell. AI Games 2, 1\u201316 (IEEE, 2010).","DOI":"10.1109\/TCIAIG.2010.2041928"},{"key":"981_CR39","doi-asserted-by":"crossref","unstructured":"Togelius, J. & Schmidhuber, J. An experiment in automatic game design. In 2008 IEEE Symposium On Computational Intelligence and Games 111\u2013118 (IEEE, 2008).","DOI":"10.1109\/CIG.2008.5035629"},{"key":"981_CR40","doi-asserted-by":"crossref","unstructured":"Smith, A. M., Nelson, M. J. & Mateas, M. Ludocore: a logical game engine for modeling videogames. In Proc. 2010 IEEE Conference on Computational Intelligence and Games 91\u201398 (IEEE, 2010).","DOI":"10.1109\/ITW.2010.5593368"},{"key":"981_CR41","doi-asserted-by":"publisher","unstructured":"Zook, A. & Riedl, M. Automatic game design via mechanic generation. In Proc. AAAI Conference on Artificial Intelligence Vol. 28, https:\/\/doi.org\/10.1609\/aaai.v28i1.8788 (AAAI Press, 2014).","DOI":"10.1609\/aaai.v28i1.8788"},{"key":"981_CR42","doi-asserted-by":"crossref","unstructured":"Khalifa, A., Green, M. C., Perez-Liebana, D. & Togelius, J. General video game rule generation. In 2017 IEEE Conference on Computational Intelligence and Games 170\u2013177 (IEEE, 2017).","DOI":"10.1109\/CIG.2017.8080431"},{"key":"981_CR43","doi-asserted-by":"publisher","first-page":"e253","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, e253 (2017).","journal-title":"Behav. Brain Sci."},{"key":"981_CR44","doi-asserted-by":"crossref","unstructured":"Cully, A. Autonomous skill discovery with quality-diversity and unsupervised descriptors. In Proc. Genetic and Evolutionary Computation Conference (ed. L\u00f3pez-Ib\u00e1\u00f1ez, M.) 81\u201389 (Association for Computing Machinery, 2019).","DOI":"10.1145\/3321707.3321804"},{"key":"981_CR45","doi-asserted-by":"publisher","first-page":"1539","DOI":"10.1109\/TEVC.2022.3159855","volume":"26","author":"L Grillotti","year":"2022","unstructured":"Grillotti, L. & Cully, A. Unsupervised behavior discovery with quality-diversity optimization. IEEE Trans. Evol. Comput. 26, 1539\u20131552 (2022).","journal-title":"IEEE Trans. Evol. Comput."},{"key":"981_CR46","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1016\/j.tics.2017.05.012","volume":"21","author":"TD Ullman","year":"2017","unstructured":"Ullman, T. D., Spelke, E., Battaglia, P. & Tenenbaum, J. B. Mind games: game engines as an architecture for intuitive physics. Trends Cogn. Sci. 21, 649\u2013665 (2017).","journal-title":"Trends Cogn. Sci."},{"key":"981_CR47","unstructured":"Chen, T., Allen, K. R., Cheyette, S. J., Tenenbaum, J. & Smith, K. A. \u2018Just in time\u2019 representations for mental simulation in intuitive physics. In Proc. Annual Meeting of the Cognitive Science Society Vol. 45 (UC Merced, 2023); https:\/\/escholarship.org\/uc\/item\/3hq021qs"},{"key":"981_CR48","unstructured":"Tang, H., Key, D. & Ellis, K. WorldCoder, a model-based LLM agent: building world models by writing code and interacting with the environment. Preprint at https:\/\/arxiv.org\/abs\/2402.12275 (2024)."},{"key":"981_CR49","unstructured":"Reed, S. et al. A generalist agent. Trans. Mach. Learn. Res. 1ikK0kHjvj (2022)."},{"key":"981_CR50","unstructured":"Gallou\u00e9dec, Q., Beeching, E., Romac, C. & Dellandr\u00e9a, E. Jack of all trades, master of some, a multi-purpose transformer agent. Preprint at https:\/\/arxiv.org\/abs\/2402.09844 (2024)."},{"key":"981_CR51","unstructured":"Florensa, C., Held, D., Geng, X. & Abbeel, P. Automatic goal generation for reinforcement learning agents. In Proc. 35th International Conference on Machine Learning Vol. 80 (eds Dy, J. & Krause, A.) 1515\u20131528 (PMLR, 2018)."},{"key":"981_CR52","unstructured":"Open Ended Learning Team et al. Open-ended learning leads to generally capable agents. Preprint at https:\/\/arxiv.org\/abs\/2107.12808 (2021)."},{"key":"981_CR53","unstructured":"Du, Y. et al. Guiding pretraining in reinforcement learning with large language models. In Proc. of the 40th International Conference on Machine Learning (eds Krause, A. et al.) 8657\u20138677 (JMLR, 2023)."},{"key":"981_CR54","unstructured":"Colas, C., Teodorescu, L., Oudeyer, P.-Y., Yuan, X. & C\u00f4t\u00e9, M.-A. Augmenting autotelic agents with large language models. Preprint at https:\/\/arxiv.org\/abs\/2305.12487v1 (2023)."},{"key":"981_CR55","unstructured":"Littman, M. L. et al. Environment-independent task specifications via GLTL. Preprint at http:\/\/arxiv.org\/abs\/1704.04341 (2017)."},{"key":"981_CR56","unstructured":"Leon, B. G., Shanahan, M. & Belardinelli, F. In a nutshell, the human asked for this: latent goals for following temporal specifications. In 10th International Conference on Learning Representations (OpenReview, 2022); https:\/\/openreview.net\/forum?id=rUwm9wCjURV"},{"key":"981_CR57","unstructured":"Ma, Y. J. et al. Eureka: Human-Level Reward Design via Coding Large Language Models (ICLR, 2023)."},{"key":"981_CR58","unstructured":"Faldor, M., Zhang, J., Cully, A. & Clune, J. OMNI-EPIC: open-endedness via models of human notions of interestingness with environments programmed in code. In 12th International Conference on Learning Representations (OpenReview, 2024); https:\/\/openreview.net\/forum?id=AgM3MzT99c"},{"key":"981_CR59","unstructured":"Colas, C. et al. Language as a cognitive tool to imagine goals in curiosity-driven exploration. In Proc. 34th International Conference on Neural Information Processing Systems (NIPS \u201920) (eds Larochelle, H. et al.) 3761\u20133774 (Curran Associates, 2020)."},{"key":"981_CR60","doi-asserted-by":"publisher","first-page":"915","DOI":"10.1038\/s41562-018-0467-4","volume":"2","author":"CM Wu","year":"2018","unstructured":"Wu, C. M., Schulz, E., Speekenbrink, M., Nelson, J. D. & Meder, B. Generalization guides human exploration in vast decision spaces. Nat. Hum. Behav. 2, 915\u2013924 (2018).","journal-title":"Nat. Hum. Behav."},{"key":"981_CR61","unstructured":"Ten, A. et al. in The Drive for Knowledge: The Science of Human Information Seeking (eds. Dezza, I. C. et al.) 53\u201376 (Cambridge Univ. Press, 2022)."},{"key":"981_CR62","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1111\/j.2044-8295.1950.tb00262.x","volume":"41","author":"DE Berlyne","year":"1950","unstructured":"Berlyne, D. E. Novelty and curiosity as determinants of exploratory behaviour. Br. J. Psychol. Gen. Sect. 41, 68\u201380 (1950).","journal-title":"Br. J. Psychol. Gen. Sect."},{"key":"981_CR63","doi-asserted-by":"crossref","unstructured":"Gopnik, A. Empowerment as causal learning, causal learning as empowerment: a bridge between Bayesian causal hypothesis testing and reinforcement learning. PhilSci-Archive https:\/\/philsci-archive.pitt.edu\/23268\/ (2024).","DOI":"10.21428\/e2759450.02bf2682"},{"key":"981_CR64","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1111\/cdev.12060","volume":"84","author":"C Addyman","year":"2013","unstructured":"Addyman, C. & Mareschal, D. Local redundancy governs infants\u2019 spontaneous orienting to visual-temporal sequences. Child Dev. 84, 1137\u20131144 (2013).","journal-title":"Child Dev."},{"key":"981_CR65","unstructured":"Du, Y. et al. What can AI learn from human exploration? Intrinsically-motivated humans and agents in open-world exploration. In NeurIPS 2023 Workshop: Information-Theoretic Principles in Cognitive Systems (OpenReview, 2023); https:\/\/openreview.net\/forum?id=aFEZdGL3gn"},{"key":"981_CR66","doi-asserted-by":"publisher","first-page":"e13411","DOI":"10.1111\/desc.13411","volume":"27","author":"A Ruggeri","year":"2024","unstructured":"Ruggeri, A., Stanciu, O., Pelz, M., Gopnik, A. & Schulz, E. Preschoolers search longer when there is more information to be gained. Dev. Sci. 27, e13411 (2024).","journal-title":"Dev. Sci."},{"key":"981_CR67","unstructured":"Liquin, E. G., Callaway, F. & Lombrozo, T. Developmental change in what elicits curiosity. In Proc. Annual Meeting of the Cognitive Science Society Vol. 43 (UC Merced, 2021); https:\/\/escholarship.org\/uc\/item\/43g7m167"},{"key":"981_CR68","doi-asserted-by":"publisher","first-page":"2167","DOI":"10.1007\/s00221-014-3907-z","volume":"232","author":"F Taffoni","year":"2014","unstructured":"Taffoni, F. et al. Development of goal-directed action selection guided by intrinsic motivations: an experiment with children. Exp. Brain Res. 232, 2167\u20132177 (2014).","journal-title":"Exp. Brain Res."},{"key":"981_CR69","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-26196-w","volume":"12","author":"A Ten","year":"2021","unstructured":"Ten, A., Kaushik, P., Oudeyer, P.-Y. & Gottlieb, J. Humans monitor learning progress in curiosity-driven exploration. Nat. Commun. 12, 5972 (2021).","journal-title":"Nat. Commun."},{"key":"981_CR70","doi-asserted-by":"publisher","first-page":"985","DOI":"10.3389\/fpsyg.2014.00985","volume":"5","author":"G Baldassarre","year":"2014","unstructured":"Baldassarre, G. et al. Intrinsic motivations and open-ended development in animals, humans, and robots: an overview. Front. Psychol. 5, 985 (2014).","journal-title":"Front. Psychol."},{"key":"981_CR71","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1111\/j.1467-7687.2007.00569.x","volume":"10","author":"ES Spelke","year":"2007","unstructured":"Spelke, E. S. & Kinzler, K. D. Core knowledge. Dev. Sci. 10, 89\u201396 (2007).","journal-title":"Dev. Sci."},{"key":"981_CR72","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1016\/j.tics.2016.05.011","volume":"20","author":"J Jara-Ettinger","year":"2016","unstructured":"Jara-Ettinger, J., Gweon, H., Schulz, L. E. & Tenenbaum, J. B. The na\u00efve utility calculus: computational principles underlying commonsense psychology. Trends Cogn. Sci. 20, 589\u2013604 (2016).","journal-title":"Trends Cogn. Sci."},{"key":"981_CR73","doi-asserted-by":"publisher","first-page":"17747","DOI":"10.1073\/pnas.1904410116","volume":"116","author":"S Liu","year":"2019","unstructured":"Liu, S., Brooks, N. B. & Spelke, E. S. Origins of the concepts cause, cost, and goal in prereaching infants. Proc. Natl Acad. Sci. USA 116, 17747\u201317752 (2019).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"981_CR74","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1016\/j.cobeha.2019.04.010","volume":"29","author":"J Jara-Ettinger","year":"2019","unstructured":"Jara-Ettinger, J. Theory of mind as inverse reinforcement learning. Curr. Opin. Behav. Sci. 29, 105\u2013110 (2019).","journal-title":"Curr. Opin. Behav. Sci."},{"key":"981_CR75","doi-asserted-by":"publisher","first-page":"103500","DOI":"10.1016\/j.artint.2021.103500","volume":"297","author":"S Arora","year":"2021","unstructured":"Arora, S. & Doshi, P. A survey of inverse reinforcement learning: challenges, methods and progress. Artif. Intell. 297, 103500 (2021).","journal-title":"Artif. Intell."},{"key":"981_CR76","unstructured":"Baker, C., Saxe, R. & Tenenbaum, J. Bayesian theory of mind: Modeling joint belief\u2013desire attribution. In Proc. Annual Meeting of the Cognitive Science Society Vol. 33 (UC Merced, 2011); https:\/\/escholarship.org\/uc\/item\/5rk7z59q"},{"key":"981_CR77","unstructured":"Velez-Ginorio, J., Siegel, M. H., Tenenbaum, J. B. & Jara-Ettinger, J. Interpreting actions by attributing compositional desires. In Proc. Annual Meeting of the Cognitive Science Society Vol. 39 (eds Gunzelmann, G. et al.) (UC Merced, 2017); https:\/\/escholarship.org\/uc\/item\/3qw110xj"},{"key":"981_CR78","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1146\/annurev-control-042920-015547","volume":"5","author":"MK Ho","year":"2022","unstructured":"Ho, M. K. & Griffiths, T. L. Cognitive science as a source of forward and inverse models of human decisions for robotics and control. Annu. Rev. Control Robot. Auton. Syst. 5, 33\u201353 (2022).","journal-title":"Annu. Rev. Control Robot. Auton. Syst."},{"key":"981_CR79","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.jbef.2017.12.004","volume":"17","author":"S Palan","year":"2018","unstructured":"Palan, S. & Schitter, C. Prolific.ac\u2014a subject pool for online experiments. J. Behav. Exp. Finance 17, 22\u201327 (2018).","journal-title":"J. Behav. Exp. Finance"},{"key":"981_CR80","unstructured":"Icarte, R. T., Klassen, T., Valenzano, R. & McIlraith, S. Using reward machines for high-level task specification and decomposition in reinforcement learning. In Proc. 35th International Conference on Machine Learning Vol. 80 (eds Dy, J. & Krause, A.) 2107\u20132116 (PMLR, 2018)."},{"key":"981_CR81","unstructured":"Brants, T., Popat, A. C, Xu, P., Och, F. J. & Dean, J. Large language models in machine translation. In Proc. 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (ed. Eisner, J.) 858\u2013867 (Association for Computational Linguistics, 2007)."},{"key":"981_CR82","unstructured":"Rothe, A., Lake, B. M. & Gureckis, T. M. Question asking as program generation. In Advances in Neural Information Processing Systems 30 (eds Von Luxburg, U. et al.) 1047\u20131056 (Curran Associates, 2017)."},{"key":"981_CR83","unstructured":"LeCun, Y., Chopra, S., Hadsell, R., Ranzato, M.\u2019A. & Huang, F. J. in Predicting Structured Data (eds Bakir, G. et al.) Ch. 10 (MIT Press, 2006)."},{"key":"981_CR84","unstructured":"van den Oord, A., Li, Y. & Vinyals, O. Representation learning with contrastive predictive coding. Preprint at https:\/\/arxiv.org\/abs\/1807.03748v2 7 (2018)."},{"key":"981_CR85","doi-asserted-by":"crossref","unstructured":"Charity, M., Green, M. C., Khalifa, A. & Togelius, J. Mech-elites: illuminating the mechanic space of GVG-AI. In Proc. 15th International Conference on the Foundations of Digital Games (eds Yannakakis, G. N. et al.) 8 (Association for Computing Machinery, 2020).","DOI":"10.1145\/3402942.3402954"},{"key":"981_CR86","unstructured":"GPT-4 Technical Report (OpenAI, 2023)."},{"key":"981_CR87","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1214\/aoms\/1177730491","volume":"18","author":"HB Mann","year":"1947","unstructured":"Mann, H. B. & Whitney, D. R. On a test of whether one of two random variables is stochastically larger than the other. Ann. Math. Stat. 18, 50\u201360 (1947).","journal-title":"Ann. Math. Stat."},{"key":"981_CR88","unstructured":"Castro, S. Fast Krippendorff: fast computation of Krippendorff\u2019s alpha agreement measure. GitHub https:\/\/github.com\/pln-fing-udelar\/fast-krippendorff (2017)."},{"key":"981_CR89","unstructured":"Radenbush, S. W. & Bryk, A. S. Hierarchical Linear Models. Applications and Data Analysis Methods 2nd edn (Sage Publications, 2002)."},{"key":"981_CR90","doi-asserted-by":"crossref","unstructured":"Hox, J., Moerbeek, M. & van de Schoot, R. Multilevel Analysis (Techniques and Applications) 3rd edn (Routledge, 2018).","DOI":"10.4324\/9781315650982"},{"key":"981_CR91","unstructured":"Argesti, A. Categorical Data Analysis 3rd edn (Wiley, 2018)."},{"key":"981_CR92","doi-asserted-by":"crossref","unstructured":"Greene, W. H. & Hensher, D. A. Modeling Ordered Choices: A Primer (Cambridge Univ. Press, 2010).","DOI":"10.1017\/CBO9780511845062"},{"key":"981_CR93","unstructured":"Christensen, R. H. B. ordinal\u2014regression models for ordinal data. R package version 2023.12-4 https:\/\/CRAN.R-project.org\/package=ordinal (2023)."},{"key":"981_CR94","unstructured":"R Core Team. R: A Language and Environment for Statistical Computing Version 4.3.2 https:\/\/www.R-project.org\/ (R Foundation for Statistical Computing, 2023)."},{"key":"981_CR95","doi-asserted-by":"publisher","first-page":"6610","DOI":"10.21105\/joss.06610","volume":"9","author":"JA Long","year":"2024","unstructured":"Long, J. A. jtools: analysis and presentation of social scientific data. J. Open Source Softw. 9, 6610 (2024).","journal-title":"J. Open Source Softw."},{"key":"981_CR96","unstructured":"Lenth, R. V. emmeans: estimated marginal means, aka least-squares means. R package version 1.10.0 https:\/\/CRAN.R-project.org\/package=emmeans (2024)."},{"key":"981_CR97","doi-asserted-by":"publisher","unstructured":"Davidson, G., Todd, G., Togelius, J., Gureckis, T. M. & Lake, B. M. guydav\/goals-as-reward-producing-programs: release for DOI. Zenodo https:\/\/doi.org\/10.5281\/zenodo.14238893 (2024).","DOI":"10.5281\/zenodo.14238893"}],"container-title":["Nature Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s42256-025-00981-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-025-00981-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-025-00981-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,23]],"date-time":"2025-02-23T23:03:33Z","timestamp":1740351813000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s42256-025-00981-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,21]]},"references-count":97,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,2]]}},"alternative-id":["981"],"URL":"https:\/\/doi.org\/10.1038\/s42256-025-00981-4","relation":{},"ISSN":["2522-5839"],"issn-type":[{"value":"2522-5839","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,21]]},"assertion":[{"value":"14 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 January 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 February 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"}}]}}