{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T07:33:16Z","timestamp":1768289596350,"version":"3.49.0"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,2,27]],"date-time":"2021-02-27T00:00:00Z","timestamp":1614384000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,2,27]],"date-time":"2021-02-27T00:00:00Z","timestamp":1614384000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100008530","name":"European Regional Development Fund","doi-asserted-by":"publisher","award":["VITAAL"],"award-info":[{"award-number":["VITAAL"]}],"id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fondation Mines Telecom"},{"DOI":"10.13039\/100012948","name":"Minist\u00e8re de l\u2019Enseignement sup\u00e9rieur, de la Recherche et de l\u2019Innovation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100012948","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["K\u00fcnstl Intell"],"published-print":{"date-parts":[[2021,3]]},"DOI":"10.1007\/s13218-021-00708-8","type":"journal-article","created":{"date-parts":[[2021,2,27]],"date-time":"2021-02-27T09:03:51Z","timestamp":1614416631000},"page":"81-90","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Robots Learn Increasingly Complex Tasks with Intrinsic Motivation and Automatic Curriculum Learning"],"prefix":"10.1007","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0929-0019","authenticated-orcid":false,"given":"Sao Mai","family":"Nguyen","sequence":"first","affiliation":[]},{"given":"Nicolas","family":"Duminy","sequence":"additional","affiliation":[]},{"given":"Alexandre","family":"Manoury","sequence":"additional","affiliation":[]},{"given":"Dominique","family":"Duhaut","sequence":"additional","affiliation":[]},{"given":"Cedric","family":"Buche","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,2,27]]},"reference":[{"issue":"2\u20133","key":"708_CR1","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1016\/S0921-8890(01)00157-9","volume":"37","author":"M Asada","year":"2001","unstructured":"Asada M, MacDorman KF, Ishiguro H, Kuniyoshi Y (2001) Cognitive developmental robotics as a new paradigm for the design of humanoid robots. Robot Auton Syst 37(2\u20133):185\u2013193. https:\/\/doi.org\/10.1016\/S0921-8890(01)00157-9","journal-title":"Robot Auton Syst"},{"issue":"3","key":"708_CR2","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1109\/TAMD.2009.2037513","volume":"1","author":"A Baranes","year":"2009","unstructured":"Baranes A, Py Oudeyer (2009) R-IAC: robust intrinsically motivated exploration and active learning. IEEE Trans Auton Ment Dev 1(3):155\u2013169","journal-title":"IEEE Trans Auton Ment Dev"},{"issue":"1","key":"708_CR3","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1016\/j.robot.2012.05.008","volume":"61","author":"A Baranes","year":"2013","unstructured":"Baranes A, Oudeyer PY (2013) Active learning of inverse models with intrinsically motivated goal exploration in robots. Robot Auton Syst 61(1):49\u201373","journal-title":"Robot Auton Syst"},{"key":"708_CR4","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1007\/978-3-319-77182-3_2","volume-title":"Active learning from infancy to childhood","author":"K Begus","year":"2018","unstructured":"Begus K, Southgate V (2018) Curious learners: how infants\u2019 motivation to learn shapes and is shaped by infants\u2019 interactions with the social world. In: Saylor MM, Ganea PA (eds) Active learning from infancy to childhood. Springer International Publishing, Cham, pp 13\u201337. https:\/\/doi.org\/10.1007\/978-3-319-77182-3_2"},{"key":"708_CR5","doi-asserted-by":"publisher","unstructured":"Bengio Y, Louradour J, Collobert R, Weston J (2009) Curriculum learning. In: International conference on machine learning, ACM, New York, NY, USA, ICML \u201909, pp 41\u201348. https:\/\/doi.org\/10.1145\/1553374.1553380","DOI":"10.1145\/1553374.1553380"},{"key":"708_CR6","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9320.001.0001","volume-title":"Developmental robotics: from babies to robots","author":"A Cangelosi","year":"2015","unstructured":"Cangelosi A, Schlesinger M (2015) Developmental robotics: from babies to robots. MIT press, Cambridge"},{"key":"708_CR7","unstructured":"Colas C, Sigaud O, Oudeyer PY (2018) GEP-PG: decoupling exploration and exploitation in deep reinforcement learning algorithms. In: ICML, Stockholm, Sweden. https:\/\/hal.inria.fr\/hal-01890151"},{"key":"708_CR8","unstructured":"Colas C, Fournier P, Chetouani M, Sigaud O, Oudeyer PY (2019) CURIOUS: intrinsically motivated modular multi-goal reinforcement learning. In: International conference on machine learning, PMLR, Long Beach, California, USA, vol\u00a097, pp 1331\u20131340. http:\/\/proceedings.mlr.press\/v97\/colas19a.html"},{"key":"708_CR9","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-2271-7","volume-title":"Intrinsic motivation and self-determination in human behavior","author":"E Deci","year":"1985","unstructured":"Deci E, Ryan RM (1985) Intrinsic motivation and self-determination in human behavior. Plenum Press, New York"},{"key":"708_CR10","doi-asserted-by":"publisher","unstructured":"Duminy N, Nguyen SM, Duhaut D (2016) Strategic and interactive learning of a hierarchical set of tasks by the Poppy humanoid robot. In: ICDL-EPIROB 2016: 6th Joint IEEE international conference developmental learning and epigenetic robotics, pp 204\u2013209. https:\/\/doi.org\/10.1109\/DEVLRN.2016.7846820","DOI":"10.1109\/DEVLRN.2016.7846820"},{"key":"708_CR11","unstructured":"Duminy N, Manoury A, Nguyen SM, Buche C, Duhaut D (2018a) Learning sequences of policies by using an intrinsically motivated learner and a task hierarchy. In: Workshop on continual unsupervised sensorimotor learning, ICDL-EpiRob, Tokyo, Japan. https:\/\/hal.archives-ouvertes.fr\/hal-01887073. https:\/\/youtu.be\/US84HjUuUtg"},{"key":"708_CR12","doi-asserted-by":"crossref","unstructured":"Duminy N, Nguyen SM, Duhaut D (2018b) Effects of social guidance on a robot learning sequences of policies in hierarchical learning. In: IEEE (ed) International conference on systems man and cybernetics","DOI":"10.1109\/SMC.2018.00636"},{"key":"708_CR13","doi-asserted-by":"crossref","unstructured":"Duminy N, Nguyen SM, Duhaut D (2018c) Learning a set of interrelated tasks by using sequences of motor policies for a strategic intrinsically motivated learner. In: IEEE international on robotic computing, pp 288\u2013291","DOI":"10.1109\/IRC.2018.00061"},{"issue":"3","key":"708_CR14","doi-asserted-by":"publisher","DOI":"10.3390\/app11030975","volume":"11","author":"N Duminy","year":"2021","unstructured":"Duminy N, Nguyen SM, Zhu J, Duhaut D, Kerdreux J (2021) Intrinsically motivated open-ended multi-task learning using transfer learning to discover task hierarchy. Appl Sci 11(3):975. https:\/\/doi.org\/10.3390\/app11030975","journal-title":"Appl Sci"},{"key":"708_CR15","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/0010-0277(93)90058-4","volume":"48","author":"J Elman","year":"1993","unstructured":"Elman J (1993) Learning and development in neural networks: the importance of starting small. Cognition 48:71\u201399","journal-title":"Cognition"},{"key":"708_CR16","unstructured":"Forestier S, Mollard Y, Oudeyer P (2017) Intrinsically motivated goal exploration processes with automatic curriculum learning. CoRR abs\/1708.02190. arxiv:1708.02190"},{"key":"708_CR17","unstructured":"Gibson JJ (1979) The theory of affordances. In: Shaw R, Bransford J (eds) Perceiving, acting, and knowing. Houghton Mifflin, Boston, pp 67\u201382"},{"issue":"1","key":"708_CR18","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/TCDS.2016.2594134","volume":"10","author":"L Jamone","year":"2016","unstructured":"Jamone L, Ugur E, Cangelosi A, Fadiga L, Bernardino A, Piater J, Santos-Victor J (2016) Affordances in psychology, neuroscience, and robotics: a survey. IEEE Trans Cogn Dev Syst 10(1):4\u201325","journal-title":"IEEE Trans Cogn Dev Syst"},{"key":"708_CR19","first-page":"1015","volume":"22","author":"G Konidaris","year":"2009","unstructured":"Konidaris G, Barto AG (2009) Skill discovery in continuous reinforcement learning domains using skill chaining. Adv Neural Inf Process Syst 22:1015\u20131023","journal-title":"Adv Neural Inf Process Syst"},{"key":"708_CR20","unstructured":"Kulkarni TD, Narasimhan K, Saeedi A, Tenenbaum J (2016) Hierarchical deep reinforcement learning: integrating temporal abstraction and intrinsic motivation. In: Lee D, Sugiyama M, Luxburg U, Guyon I, Garnett R (eds) Advances in neural information processing systems, vol 29. Curran Associates, Inc., pp 3675\u20133683"},{"issue":"4\u20135","key":"708_CR21","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1177\/0278364917710318","volume":"37","author":"S Levine","year":"2018","unstructured":"Levine S, Pastor P, Krizhevsky A, Ibarz J, Quillen D (2018) Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection. Int J Robot Res 37(4\u20135):421\u2013436. https:\/\/doi.org\/10.1177\/0278364917710318","journal-title":"Int J Robot Res"},{"key":"708_CR22","doi-asserted-by":"crossref","unstructured":"Manoury A, Nguyen SM, Buche C (2019) Hierarchical affordance discovery using intrinsic motivation. In: Proceedings of the 7th international conference on human-agent interaction, HAI '19,Kyoto, Japan. Association for Computing Machinery, New York, pp 186\u2013193","DOI":"10.1145\/3349537.3351898"},{"key":"708_CR23","doi-asserted-by":"publisher","unstructured":"Mitriakov A, Papadakis P, Nguyen SM, Garlatti S (2020) Staircase traversal via reinforcement learning for active reconfiguration of assistive robots. In: International conference on fuzzy systems (FUZZ-IEEE), pp 1\u20138. https:\/\/doi.org\/10.1109\/FUZZ48607.2020.9177581","DOI":"10.1109\/FUZZ48607.2020.9177581"},{"issue":"7540","key":"708_CR24","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G, Petersen S, Beattie C, Sadik A, Antonoglou I, King H, Kumaran D, Wierstra D, Legg S, Hassabis D (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529\u2013533. https:\/\/doi.org\/10.1038\/nature14236","journal-title":"Nature"},{"key":"708_CR25","unstructured":"Mnih V, Badia AP, Mirza M, Graves A, Lillicrap TP, Harley T, Silver D, Kavukcuoglu K (2016) Asynchronous methods for deep reinforcement learning. CoRR abs\/1602.01783. arxiv:1602.01783"},{"key":"708_CR26","doi-asserted-by":"publisher","unstructured":"Montesano L, Lopes M (2009) Learning grasping affordances from local visual descriptors. In: 2009 IEEE 8th international conference on development and learning, pp 1\u20136. https:\/\/doi.org\/10.1109\/DEVLRN.2009.5175529","DOI":"10.1109\/DEVLRN.2009.5175529"},{"key":"708_CR27","doi-asserted-by":"publisher","unstructured":"Moulin-Frier C, Nguyen SM, Oudeyer PY (2014) Self-organization of early vocal development in infants and machines: the role of intrinsic motivation. Front Psychol 4(1006). https:\/\/doi.org\/10.3389\/fpsyg.2013.01006. http:\/\/www.frontiersin.org\/cognitive_science\/10.3389\/fpsyg.2013.01006\/abstract","DOI":"10.3389\/fpsyg.2013.01006"},{"issue":"3","key":"708_CR28","doi-asserted-by":"publisher","first-page":"136","DOI":"10.2478\/s13230-013-0110-z","volume":"3","author":"SM Nguyen","year":"2012","unstructured":"Nguyen SM, Oudeyer PY (2012) Active choice of teachers, learning strategies and goals for a socially guided intrinsic motivation learner. Paladyn J Behav Robot 3(3):136\u2013146. https:\/\/doi.org\/10.2478\/s13230-013-0110-z","journal-title":"Paladyn J Behav Robot"},{"issue":"3","key":"708_CR29","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/s10514-013-9339-y","volume":"36","author":"SM Nguyen","year":"2014","unstructured":"Nguyen SM, Oudeyer PY (2014) Socially guided intrinsic motivation for robot learning of motor skills. Auton Robots 36(3):273\u2013294. https:\/\/doi.org\/10.1007\/s10514-013-9339-y","journal-title":"Auton Robots"},{"key":"708_CR30","doi-asserted-by":"publisher","unstructured":"Nguyen SM, Ivaldi S, Lyubova N, Droniou A, Gerardeaux-Viret D, Filliat D, Padois V, Sigaud O, Oudeyer PY (2013) Learning to recognize objects through curiosity-driven manipulation with the iCub humanoid robot. In: IEEE international conference on development and learning - Epirob, No 1\u20138. https:\/\/doi.org\/10.1109\/DevLrn.2013.6652525","DOI":"10.1109\/DevLrn.2013.6652525"},{"issue":"2","key":"708_CR31","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1109\/TEVC.2006.890271","volume":"11","author":"PY Oudeyer","year":"2007","unstructured":"Oudeyer PY, Kaplan F, Hafner V (2007) Intrinsic motivation systems for autonomous mental development. IEEE Trans Evol Comput 11(2):265\u2013286. https:\/\/doi.org\/10.1109\/TEVC.2006.890271","journal-title":"IEEE Trans Evol Comput"},{"key":"708_CR32","first-page":"1313","volume-title":"Advances in neural information processing systems","author":"E Rafols","year":"2006","unstructured":"Rafols E, Koop A, Sutton RS (2006) Temporal abstraction in temporal-difference networks. In: Weiss Y, Sch\u00f6lkopf B, Platt J (eds) Advances in neural information processing systems, vol 18. MIT Press, Cambridge, pp 1313\u20131320"},{"key":"708_CR33","unstructured":"Sutton RS, Barto AG (1998) Reinforcement learning: an introduction. MIT Press, Cambridge. http:\/\/webdocs.cs.ualberta.ca\/~sutton\/book\/the-book.html"},{"key":"708_CR34","doi-asserted-by":"crossref","unstructured":"Sutton RS, Precup D, Singh S (1999) Between mdps and semi-mdps: a framework for temporal abstraction in reinforcement learning. Artif Intell 112:181\u2013211. http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0004370299000521","DOI":"10.1016\/S0004-3702(99)00052-1"},{"issue":"4","key":"708_CR35","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1109\/TCDS.2016.25813072016.2581307","volume":"9","author":"E Ugur","year":"2017","unstructured":"Ugur E, Piater J (2017) Emergent structuring of interdependent affordance learning tasks using intrinsic motivation and empirical feature selection. IEEE Trans Cogn Dev Syst 9(4):328\u2013340. https:\/\/doi.org\/10.1109\/TCDS.2016.25813072016.2581307","journal-title":"IEEE Trans Cogn Dev Syst"},{"key":"708_CR36","unstructured":"Ugur E, Piater J, Sahin E, Oztop E (2009) Affordance learning from range data for multi-step planning. In: International conference on epigenetic robotics. http:\/\/win.rossiproject.net\/downloads\/ugur-epirob-2009.pdf"},{"key":"708_CR37","doi-asserted-by":"crossref","unstructured":"Vigorito C, Barto A (2010) Intrinsically motivated hierarchical skill learning in structured environments. IEEE Trans Auton Ment Dev 2(2):132\u2013143. https:\/\/ieeexplore.ieee.org\/document\/5464347\/","DOI":"10.1109\/TAMD.2010.2050205"},{"issue":"5","key":"708_CR38","doi-asserted-by":"publisher","first-page":"518","DOI":"10.1177\/0278364919835020","volume":"38","author":"P Zech","year":"2019","unstructured":"Zech P, Renaudo E, Haller S, Zhang X, Piater J (2019) Action representations in robotics: a taxonomy and systematic classification. Int J Robot Res 38(5):518\u2013562. https:\/\/doi.org\/10.1177\/0278364919835020","journal-title":"Int J Robot Res"}],"container-title":["KI - K\u00fcnstliche Intelligenz"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13218-021-00708-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s13218-021-00708-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13218-021-00708-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,26]],"date-time":"2021-03-26T13:36:19Z","timestamp":1616765779000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s13218-021-00708-8"}},"subtitle":["Domain Knowledge by Emergence of Affordances, Hierarchical Reinforcement and Active Imitation Learning"],"short-title":[],"issued":{"date-parts":[[2021,2,27]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,3]]}},"alternative-id":["708"],"URL":"https:\/\/doi.org\/10.1007\/s13218-021-00708-8","relation":{},"ISSN":["0933-1875","1610-1987"],"issn-type":[{"value":"0933-1875","type":"print"},{"value":"1610-1987","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,27]]},"assertion":[{"value":"30 June 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 January 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 February 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}