{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:58:23Z","timestamp":1778083103872,"version":"3.51.4"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Institute of Information & communications Technology Planning & Evaluation"},{"DOI":"10.13039\/501100003621","name":"Korea government (MSIT)","doi-asserted-by":"publisher","award":["2017-0-00162"],"award-info":[{"award-number":["2017-0-00162"]}],"id":[{"id":"10.13039\/501100003621","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3015245","type":"journal-article","created":{"date-parts":[[2020,8,10]],"date-time":"2020-08-10T21:30:18Z","timestamp":1597095018000},"page":"147790-147807","source":"Crossref","is-referenced-by-count":11,"title":["Reinforcement Learning-Based Path Generation Using Sequential Pattern Reduction and Self-Directed Curriculum Learning"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7750-3736","authenticated-orcid":false,"given":"Taewoo","family":"Kim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joo-Haeng","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-53806-7_1"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/38.156018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-015-0310-2"},{"key":"ref32","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487173"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3099564.3099567"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/0010-4485(78)90110-0"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594452"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793979"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461096"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref62","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref61","article-title":"Emergent complexity via multi-agent competition","author":"bansal","year":"2017","journal-title":"arXiv 1710 03748"},{"key":"ref63","first-page":"5279","article-title":"Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation","author":"wu","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1109\/JAS.2016.7471613","article-title":"Where does AlphaGo go: From church-turing thesis to AlphaGo thesis and beyond","volume":"3","author":"wang","year":"2016","journal-title":"IEEE\/CAA Journal of Automatica Sinica"},{"key":"ref64","article-title":"Learning to reinforcement learn","author":"wang","year":"2016","journal-title":"arXiv 1611 05763"},{"key":"ref27","first-page":"2140","article-title":"Playing FPS games with deep reinforcement learning","author":"lample","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696520"},{"key":"ref66","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"ref67","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"arXiv 1506 02438 [cs]"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2408351"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759133"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1561\/1100000005"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0109663"},{"key":"ref22","first-page":"1","article-title":"Robot path generation by viewing a static scene from a single camera","author":"aristos","year":"2002","journal-title":"Proc IEEE Int Symp Robot Autom (ISRA)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-006-9076-y"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2019.101847"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.846442"},{"key":"ref26","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2872693"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2017.8081267"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2563981"},{"key":"ref59","author":"gonzales","year":"2002","journal-title":"Digital Image Processing"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.3732\/ajb.90.3.333"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/566570.566636"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/353"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2790981"},{"key":"ref54","first-page":"2590","article-title":"Automatic curriculum graph generation for reinforcement learning agents","author":"svetlik","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref53","article-title":"Reverse curriculum generation for reinforcement learning","author":"florensa","year":"2017","journal-title":"arXiv 1707 05300"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2014.11.004"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2016.08.002"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2013.09.004"},{"key":"ref40","first-page":"377","article-title":"Optimizing production manufacturing using reinforcement learning","volume":"372","author":"mahadevan","year":"1998","journal-title":"Proc FLAIRS Conf"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/36.193786"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1115\/MSEC2018-6314"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2014.07.076"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s00170-005-0081-2"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2006.11.004"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/S0010-4485(02)00070-2"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE-Asia.2016.7804794"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2017.10.044"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.4218\/etrij.16.0115.0610"},{"key":"ref5","article-title":"Robot and method of providing guidance service by the robot","author":"lee","year":"2020"},{"key":"ref8","article-title":"Intelligent automated assistant","author":"saddler","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-8406-6_38"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1258\/135763306775321362"},{"key":"ref46","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref45","article-title":"Asymmetric actor critic for image-based robot learning","author":"pinto","year":"2017","journal-title":"arXiv 1710 06542"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793864"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.009"},{"key":"ref42","volume":"135","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref41","author":"paul","year":"1981","journal-title":"Robot Manipulators Mathematics Programming and Control The Computer Control of Robot Manipulators"},{"key":"ref44","first-page":"1008","article-title":"Actor-critic algorithms","volume":"2000","author":"konda","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref43","first-page":"345","article-title":"Reinforcement learning algorithm for partially observable Markov decision problems","author":"jaakkola","year":"1995","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09162635.pdf?arnumber=9162635","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:55:04Z","timestamp":1639770904000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9162635\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3015245","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}