{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T09:11:38Z","timestamp":1768813898610,"version":"3.49.0"},"reference-count":81,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2018,3,1]],"date-time":"2018-03-01T00:00:00Z","timestamp":1519862400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"name":"FET Project DREAM through the European Union\u2019s Horizon 2020 Research and Innovation Programme","award":["640891"],"award-info":[{"award-number":["640891"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2018,3]]},"DOI":"10.1109\/tcds.2016.2628817","type":"journal-article","created":{"date-parts":[[2017,3,16]],"date-time":"2017-03-16T01:49:42Z","timestamp":1489628982000},"page":"102-119","source":"Crossref","is-referenced-by-count":18,"title":["Bootstrapping $Q$ -Learning for Robotics From Neuro-Evolution Results"],"prefix":"10.1109","volume":"10","author":[{"given":"Matthieu","family":"Zimmer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1541-054X","authenticated-orcid":false,"given":"Stephane","family":"Doncieux","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9780262016438.003.0019"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(02)00044-8"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32375-1"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.3389\/neuro.12.006.2007"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.07.003"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/11564096_32"},{"key":"ref39","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"Reinforcement learning: A survey","volume":"4","author":"kaelbling","year":"1996","journal-title":"J Artif Intell Res"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2014.2308294"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2015.7346098"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914554471"},{"key":"ref78","first-page":"877","article-title":"Evolutionary function approximation for reinforcement learning","volume":"7","author":"whiteson","year":"2006","journal-title":"J Mach Learn Res"},{"key":"ref79","author":"eaton","year":"2007","journal-title":"GNU Octave Version 3 0 1 Manual A High-level Interactive Language for Numerical Computations"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553471"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2012.01.002"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2319733"},{"key":"ref30","first-page":"119","article-title":"Speeding-up reinforcement learning through abstraction and transfer learning","author":"koga","year":"2013","journal-title":"Proc Int Conf Auton Agents Multi-Agent Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2014.6889784"},{"key":"ref36","article-title":"Continual curiosity-driven skill acquisition from high-dimensional video inputs for humanoid robots","author":"kompella","year":"2015","journal-title":"Artif Intell"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2006.890271"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1991.170605"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1177\/1059712313487390"},{"key":"ref62","author":"deb","year":"2001","journal-title":"Multi-Objective Optimization Using Evolutionary Algorithms"},{"key":"ref61","author":"eiben","year":"2008","journal-title":"Introduction to Evolutionary Computing (Natural Computing Series)"},{"key":"ref28","first-page":"1015","article-title":"Skill discovery in continuous reinforcement learning domains using skill chaining","author":"konidaris","year":"2009","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s12065-014-0110-x"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/2492007.2493883"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1162\/EVCO_a_00048"},{"key":"ref29","first-page":"895","article-title":"Building portable options: Skill transfer in reinforcement learning","author":"konidaris","year":"2007","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1162\/106365602320169811"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/0098-3004(84)90020-7"},{"key":"ref68","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"tibshirani","year":"1996","journal-title":"J Roy Statist Soc Series B (Methodol )"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref69","author":"smith","year":"2005","journal-title":"Open dynamics engine"},{"key":"ref1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9120-4"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/0921-8890(95)00004-Y"},{"key":"ref24","first-page":"880","article-title":"Value functions for RL-based behavior transfer: A comparative study","volume":"2","author":"taylor","year":"2005","journal-title":"Proc Nat Conf Artif Intell"},{"key":"ref23","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"taylor","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref26","article-title":"Knowledge extraction from learning traces in continuous domains","author":"doncieux","year":"2014","journal-title":"Proc Fall Symp Knowl Skill Behav Transfer Auton Robots (AAAI)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/DevLrn.2013.6652568"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2015.00004"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/BF02551274"},{"key":"ref59","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/2889.001.0001","author":"nolfi","year":"2000","journal-title":"Evolutionary Robotics The Biology Intelligence and Technology of Self-Organizing Machines"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1038\/nature14422"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1162\/EVCO_a_00143"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1162\/EVCO_a_00025"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2009.5354077"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2013.6557731"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1080\/095400999116232"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.09.009"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2001576.2001613"},{"key":"ref40","author":"howard","year":"1960","journal-title":"Dynamic Programming and Markov Processes"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2011.2160943"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1992.287219"},{"key":"ref13","first-page":"160","article-title":"The crawler, a class room demonstrator for reinforcement learning","author":"tokic","year":"2009","journal-title":"Proc FLAIRS Conf"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/RAAD.2010.5524570"},{"key":"ref15","article-title":"Reinforcement learning of behaviors in mobile robots using noisy infrared sensing","author":"willgoss","year":"1999","journal-title":"Proc Aust Conf Robot Autom"},{"key":"ref16","first-page":"1468","article-title":"Autonomous skill acquisition on a mobile manipulator","author":"konidaris","year":"2011","journal-title":"Proc 5th Nat Conf Amer Assoc Artif Intell"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389903"},{"key":"ref81","first-page":"4079","article-title":"SFERESv2: Evolvin’ in the multi-core world","author":"mouret","year":"2010","journal-title":"Proc WCCI IEEE World Congr Comput Intell Congr Evol Comput (CEC)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/105971230501300301"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509181"},{"key":"ref80","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5223-6"},{"key":"ref3","first-page":"1","article-title":"An application of reinforcement learning to aerobatic helicopter flight","author":"abbeel","year":"2007","journal-title":"Proc Adv Neural Inf Process Syst Conf"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888911000038"},{"key":"ref5","first-page":"205","article-title":"Creativity: A driver for research on robotics in open environments","volume":"2016 1","author":"doncieux","year":"2016","journal-title":"Intellectica"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/5.784219"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s12065-007-0002-4"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.2478\/pjbr-2013-0003"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2001576.2001612"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992697"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50030-7"},{"key":"ref48","article-title":"Roles of macro-actions in accelerating reinforcement learning","author":"mcgovern","year":"1997","journal-title":"Proc Grace Hopper Celebration of Women in Computing Conf"},{"key":"ref47","article-title":"On-line Q-learning using connectionist systems","author":"rummery","year":"1994"},{"key":"ref42","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/4235.996017"},{"key":"ref44","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref43","article-title":"Neural fitted actor-critic","author":"zimmer","year":"2016","journal-title":"Proc Eur Symp Artif Neural Netw -Adv Comput Intell Learn"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/8310712\/07879193.pdf?arnumber=7879193","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T22:40:59Z","timestamp":1750113659000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7879193\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,3]]},"references-count":81,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2016.2628817","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,3]]}}}