{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T13:24:22Z","timestamp":1768915462436,"version":"3.49.0"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2018,8,1]],"date-time":"2018-08-01T00:00:00Z","timestamp":1533081600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Intelligent Robot Learning (IRL) Lab"},{"DOI":"10.13039\/100007588","name":"Washington State University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100007588","id-type":"DOI","asserted-by":"crossref"}]},{"name":"CIIGAR Lab at North Carolina State University"},{"name":"National Science Foundation","award":["IIS-1149917"],"award-info":[{"award-number":["IIS-1149917"]}]},{"name":"CIIGAR NSF","award":["IIS-1643411"],"award-info":[{"award-number":["IIS-1643411"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Emerg. Top. Comput. Intell."],"published-print":{"date-parts":[[2018,8]]},"DOI":"10.1109\/tetci.2018.2829980","type":"journal-article","created":{"date-parts":[[2018,7,20]],"date-time":"2018-07-20T18:54:23Z","timestamp":1532112863000},"page":"268-277","source":"Crossref","is-referenced-by-count":9,"title":["Curriculum Design for Machine Learners in Sequential Decision Tasks"],"prefix":"10.1109","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0152-3180","authenticated-orcid":false,"given":"Bei","family":"Peng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James","family":"MacGlashan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9888-178X","authenticated-orcid":false,"given":"Robert","family":"Loftin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael L.","family":"Littman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7872-4840","authenticated-orcid":false,"given":"David L.","family":"Roberts","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8946-0211","authenticated-orcid":false,"given":"Matthew E.","family":"Taylor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-015-9283-7"},{"key":"ref32","first-page":"79","article-title":"A statistical approach to machine translation","volume":"16","author":"brown","year":"1990","journal-title":"Comput Linguistics"},{"key":"ref31","first-page":"957","article-title":"A need for speed: Adapting agent action speed to improve task learning from non-expert humans","author":"peng","year":"2016","journal-title":"Proc 1st Int Conf Autonomous Agents Multiagent Syst"},{"key":"ref30","article-title":"Language and policy learning from human-delivered feedback","author":"peng","year":"2015","journal-title":"Proc Mach Learn Soc Robot Workshop"},{"key":"ref37","volume":"19690","author":"wonnacott","year":"1972","journal-title":"Introductory Statistics"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2014.6926319"},{"key":"ref35","article-title":"Translating english to reward functions","author":"macglashan","year":"2014"},{"key":"ref34","first-page":"475","article-title":"Reinforcement learning from simultaneous human and MDP reward","volume":"1","author":"knox","year":"2012","journal-title":"Proc 11th Int Conf Auton Agents Multiagent Syst"},{"key":"ref10","first-page":"2590","article-title":"Automatic curriculum graph generation for reinforcement learning agents","author":"svetlik","year":"2016","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/72.508937"},{"key":"ref12","first-page":"182","article-title":"Evolving neural network agents in the nero video game","author":"stanley","year":"2005","journal-title":"Proc IEEE Symp Comput Intell Games"},{"key":"ref13","first-page":"2125","article-title":"transfer\n learning via inter-task mappings for temporal difference learning","volume":"8","author":"taylor","year":"2007","journal-title":"J Mach Learn Res"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1007\/978-3-642-30353-1_31","article-title":"Curriculum learning for motor skills","author":"karpathy","year":"2012","journal-title":"Adv Artif Intell"},{"key":"ref15","article-title":"Agent-agnostic\n human-in-the-loop reinforcement learning","author":"abel","year":"2017","journal-title":"arXiv 1701 04079"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206110"},{"key":"ref17","first-page":"1553","article-title":"A deep hierarchical approach to lifelong learning in minecraft","author":"tessler","year":"2017","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref18","article-title":"Training an agent to ground commands with reward and punishment","author":"macglashan","year":"2014","journal-title":"Proc AAAI Mach Learn Interactive Syst Workshop"},{"key":"ref19","first-page":"278","article-title":"Policy\n invariance under reward transformations: Theory and application to reward shaping","author":"ng","year":"1999","journal-title":"Proc 16th Int Conf Mach Learn"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2012.05.008"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2008.11.014"},{"key":"ref27","first-page":"580","article-title":"Using active relocation to aid reinforcement learning","author":"mihalkova","year":"2006","journal-title":"Proc the 19th Intl Conf on FLAIRS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1901\/jeab.2004.82-317"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2050205"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1037\/h0049039"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995523"},{"key":"ref7","first-page":"1189","article-title":"Self-paced\n learning for latent variable models","author":"kumar","year":"2010","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0277(93)90058-4"},{"key":"ref9","first-page":"566","article-title":"Source task creation for curriculum\n learning","author":"narvekar","year":"2016","journal-title":"Proc 10th Int Conf Auton Agents Multiagent Syst"},{"key":"ref1","article-title":"The behavior of organisms: An experimental analysis","author":"skinner","year":"1938"},{"key":"ref20","author":"vygotsky","year":"1978","journal-title":"Mind in Society Development of Higher Psychological Processes"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273624"},{"key":"ref21","first-page":"1449","article-title":"How do humans\n teach: On curriculum learning and teaching dimension","author":"khan","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273606"},{"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","doi-asserted-by":"publisher","DOI":"10.1613\/jair.295"},{"key":"ref25","first-page":"640","article-title":"Is learning the nth thing any easier than\n learning the first","volume":"8","author":"thrun","year":"1996","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Transactions on Emerging Topics in Computational Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7433297\/8416789\/08416799.pdf?arnumber=8416799","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T14:58:59Z","timestamp":1643209139000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8416799\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8]]},"references-count":37,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tetci.2018.2829980","relation":{},"ISSN":["2471-285X"],"issn-type":[{"value":"2471-285X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,8]]}}}