{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T09:03:05Z","timestamp":1765357385425,"version":"3.37.3"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Union Horizon 2020 Research and Innovation Programme through the Project Goal-Robots\u2014Goal-based Open-Ended Autonomous Learning Robots","doi-asserted-by":"publisher","award":["713010"],"award-info":[{"award-number":["713010"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tcds.2023.3270081","type":"journal-article","created":{"date-parts":[[2023,5,24]],"date-time":"2023-05-24T17:49:00Z","timestamp":1684950540000},"page":"2014-2030","source":"Crossref","is-referenced-by-count":4,"title":["REAL-X\u2014Robot Open-Ended Autonomous Learning Architecture: Building Truly End-to-End Sensorimotor Autonomous Learning Systems"],"prefix":"10.1109","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8026-5145","authenticated-orcid":false,"given":"Emilio","family":"Cartoni","sequence":"first","affiliation":[{"name":"Institute of Cognitive Sciences and Technologies, National Research Council, Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4915-0380","authenticated-orcid":false,"given":"Davide","family":"Montella","sequence":"additional","affiliation":[{"name":"Institute of Cognitive Sciences and Technologies, National Research Council, Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8166-2441","authenticated-orcid":false,"given":"Jochen","family":"Triesch","sequence":"additional","affiliation":[{"name":"Frankfurt Institute of Advanced Studies, Frankfurt, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1277-4447","authenticated-orcid":false,"given":"Gianluca","family":"Baldassarre","sequence":"additional","affiliation":[{"name":"Institute of Cognitive Sciences and Technologies, National Research Council, Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1037\/11164-000"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2011.6037367"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2013.09.001"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32375-1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2018.00059"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1080\/09540090310001655110"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9320.001.0001"},{"key":"ref8","first-page":"112","article-title":"Intrinsically motivated learning of hierarchical collections of skills","volume-title":"Proc. 3rd Int. Conf. Develop. Learn.","author":"Barto"},{"key":"ref9","first-page":"141","article-title":"Evolving childhood\u2019s length and learning parameters in an intrinsically motivated reinforcement learning robot","volume-title":"Proc. 7th Int. Conf. Epigenet. Robot. (EpiRob)","author":"Schembri"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2006.890271"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2056368"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/DevLrn.2012.6400876"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-37577-4_7"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.10.005"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1908100117"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2086453"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"issue":"1","key":"ref18","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1023\/A:1025696116075","article-title":"Recent advances in hierarchical reinforcement learning","volume":"13","author":"Barto","year":"2003","journal-title":"Discrete Event Dyn. Syst."},{"key":"ref19","first-page":"1","article-title":"Intrinsic motivation signals for driving the acquisition of multiple tasks: A simulated robotic study","volume-title":"Proc. 12th Int. Conf. Cogn. Model. (ICCM)","author":"Santucci"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/devlrn.2014.6983020"},{"key":"ref21","article-title":"Intrinsically motivated goal exploration processes with automatic curriculum learning","author":"Forestier","year":"2017","journal-title":"arXiv:1708.02190"},{"key":"ref22","first-page":"9209","article-title":"Visual reinforcement learning with imagined goals","volume-title":"Proc. 2nd Lifelong Learn. Reinforcement Learn. Approach Workshop (LLRLA FAIM)","author":"Nair"},{"key":"ref23","article-title":"Automatic goal generation for reinforcement learning agents","author":"Held","year":"2017","journal-title":"arXiv:1705.06366"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2017.8329807"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2014.6982980"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2016.2538961"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2017.8329804"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2020.103710"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2017.2772908"},{"key":"ref30","article-title":"A Laplacian framework for option discovery in reinforcement learning","author":"Machado","year":"2017","journal-title":"arXiv:1703.00956"},{"key":"ref31","first-page":"1471","article-title":"Unifying count-based exploration and intrinsic motivation","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Bellemare"},{"key":"ref32","article-title":"Diversity is all you need: Learning skills without a reward function","author":"Eysenbach","year":"2018","journal-title":"arXiv:1802.06070"},{"key":"ref33","article-title":"Variational option discovery algorithms","author":"Achiam","year":"2018","journal-title":"arXiv:1807.10299"},{"key":"ref34","first-page":"142","article-title":"REAL-2019: Robot open-ended autonomous learning competition","volume-title":"Proc. Int. Conf. Mach. Learn. Res.","author":"Cartoni"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICDL49984.2021.9515624"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2019.00045"},{"volume-title":"Principles of Psychology","year":"1980","author":"James","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref39","article-title":"Large-scale study of curiosity-driven learning","author":"Burda","year":"2018","journal-title":"arXiv:1808.04355"},{"key":"ref40","first-page":"8887","article-title":"Self-supervised exploration via disagreement","volume-title":"Proc. 36th Int. Conf. Mach. Learn. (ICML)","author":"Pathak"},{"key":"ref41","article-title":"Planning to explore via self-supervised world models","author":"Sekar","year":"2020","journal-title":"arXiv:2005.05960"},{"key":"ref42","article-title":"Discovering and achieving goals via world models","volume-title":"Advances in Neural Information Processing Systems","author":"Mendonca","year":"2021"},{"key":"ref43","article-title":"Visual reinforcement learning with imagined goals","author":"Nair","year":"2018","journal-title":"arXiv:1807.04742"},{"key":"ref44","article-title":"Skew-fit: State-covering self-supervised reinforcement learning","author":"Pong","year":"2019","journal-title":"arXiv:1903.03698"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560922"},{"key":"ref46","first-page":"1","article-title":"Mutual information state intrinsic control","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhao"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2013.00022"},{"key":"ref48","article-title":"Mutual information maximization for robust plannable representations","author":"Ding","year":"2020","journal-title":"arXiv:2005.08114"},{"key":"ref49","article-title":"Sparse graphical memory for robust planning","author":"Laskin","year":"2019","journal-title":"arXiv:2003.06417"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.020"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.074"},{"key":"ref52","first-page":"1","article-title":"Information prioritization through empowerment in visual model-based RL","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Bharadhwaj"},{"key":"ref53","first-page":"1","article-title":"Model-based visual planning with self-supervised functional distances","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Tian"},{"key":"ref54","article-title":"Optimal options for multi-task reinforcement learning under time constraints","author":"Verme","year":"2020","journal-title":"arXiv:2001.01620"},{"volume-title":"Robogym","year":"2020","key":"ref55"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref57","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","author":"Yu","year":"2019","journal-title":"arXiv:1910.10897"},{"key":"ref58","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv:1312.6114v10"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340794"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1111\/j.1469-8749.1996.tb12136.x"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.4324\/9780429467875-13"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2013.2264321"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2013.00907"},{"key":"ref64","article-title":"Autonomous discovery of the goal space to learn a parameterized skill","author":"Cartoni","year":"2018","journal-title":"arXiv:1805.07547"},{"key":"ref65","first-page":"1","article-title":"Autonomous reinforcement learning: Formalism and benchmarking","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Sharma"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s00422-015-0662-6"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR53236.2021.9659371"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2019.03.005"},{"key":"ref71","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","volume-title":"Proc. Int. Conf. Robot Learn.","author":"Kalashnikov"},{"key":"ref72","article-title":"Dream to control: Learning behaviors by latent imagination","author":"Hafner","year":"2019","journal-title":"arXiv:1912.01603"},{"key":"ref73","first-page":"1","article-title":"Diversity is all you need: Learning skills without a reward function","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Eysenbach"},{"key":"ref74","first-page":"1","article-title":"Unsupervised control through non-parametric discriminative rewards","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Warde-Farley"},{"key":"ref75","first-page":"1518","article-title":"Actionable models: Unsupervised offline reinforcement learning of robotic skills","volume-title":"Proc. ICML","author":"Chebotar"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9320.001.0001"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/10360134\/10132490.pdf?arnumber=10132490","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T01:06:46Z","timestamp":1705021606000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10132490\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":76,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2023.3270081","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"type":"print","value":"2379-8920"},{"type":"electronic","value":"2379-8939"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}