{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T21:07:23Z","timestamp":1761599243848,"version":"3.37.3"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100008940","name":"Center for Discrete Mathematics and Theoretical Computer Science (DIMACS) through NSF","doi-asserted-by":"publisher","award":["CCF-1445755"],"award-info":[{"award-number":["CCF-1445755"]}],"id":[{"id":"10.13039\/100008940","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3264264","type":"journal-article","created":{"date-parts":[[2023,4,3]],"date-time":"2023-04-03T17:37:37Z","timestamp":1680543457000},"page":"33812-33825","source":"Crossref","is-referenced-by-count":5,"title":["A Controllable Agent by Subgoals in Path Planning Using Goal-Conditioned Reinforcement Learning"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4316-3072","authenticated-orcid":false,"given":"Gyeong Taek","family":"Lee","sequence":"first","affiliation":[{"name":"Department of Industrial and Systems Engineering, Rutgers University, The State University of New Jersey, Piscataway, NJ, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3966-3309","authenticated-orcid":false,"given":"Kangjin","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Medicine, Channing Division of Network Medicine, Brigham and Women's Hospital and Harvard Medical School, Boston, MA, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2020.00063"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IC3A48958.2020.233289"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561151"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2018.11.557"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2943253"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2020.3027695"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3026638"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-020-09926-9"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2021.3081996"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3046284"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11030467"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/en12122342"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-020-01800-6"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3011211"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341496"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2021.106350"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3069497"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927869"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1002\/aisy.201900106"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3034800"},{"key":"ref21","first-page":"2661","article-title":"Weakly-supervised reinforcement learning for controllable behavior","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Lee"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3090364"},{"key":"ref23","first-page":"12611","article-title":"World model as a graph: Learning latent landmarks for planning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref24","first-page":"1430","article-title":"Goal-conditioned reinforcement learning with imagined subgoals","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chane-Sane"},{"key":"ref25","article-title":"Rethinking goal-conditioned supervised learning and its connection to offline RL","author":"Yang","year":"2022","journal-title":"arXiv:2202.04478"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.06.022"},{"key":"ref27","first-page":"7553","article-title":"Maximum entropy-regularized multi-goal reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhao"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1111\/j.1745-6924.2009.01140.x"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2011.08.004"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.concog.2014.09.019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1433-7"},{"key":"ref32","article-title":"Learning user-defined sub-goals using memory editing in reinforcement learning","author":"Lee","year":"2022","journal-title":"arXiv:2205.00399"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRAS.2018.8443226"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ITNEC48623.2020.9084806"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9020250"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001418590085"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1846\/1\/012007"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/2245\/1\/012013"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.53106\/160792642021072204003"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s40313-019-00549-9"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-06179-0"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/5781591"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-021-02303-8"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-019-01073-3"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2019.106299"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3390\/s20020426"},{"key":"ref47","first-page":"1","article-title":"Hindsight experience replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Andrychowicz"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2019.8850705"},{"key":"ref49","first-page":"1","article-title":"Curriculum-guided hindsight experience replay","volume-title":"Proc. Adv. neural Inf. Process. Syst.","volume":"32","author":"Fang"},{"key":"ref50","first-page":"690","article-title":"Hindsight planner","volume-title":"Proc. 19th Int. Conf. Auto. Agents MultiAgent Syst.","author":"Lai"},{"key":"ref51","first-page":"1","article-title":"Planning with goal-conditioned policies","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Nasiriany"},{"key":"ref52","article-title":"Learning to reach goals via iterated supervised learning","author":"Ghosh","year":"2019","journal-title":"arXiv:1912.06088"},{"key":"ref53","first-page":"1","article-title":"Visual reinforcement learning with imagined goals","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Nair"},{"key":"ref54","first-page":"1","article-title":"Search on the replay buffer: Bridging planning and reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Eysenbach"},{"key":"ref55","article-title":"C-learning: Learning to achieve goals via recursive classification","author":"Eysenbach","year":"2020","journal-title":"arXiv:2011.08909"},{"key":"ref56","first-page":"28336","article-title":"Landmark-guided subgoal generation in hierarchical reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Kim"},{"key":"ref57","first-page":"1","article-title":"Data-efficient hierarchical reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Nachum"},{"key":"ref58","first-page":"21732","article-title":"Hierarchical reinforcement learning with timed subgoals","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Gurtler"},{"key":"ref59","first-page":"3878","article-title":"Self-imitation learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Oh"},{"key":"ref60","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref61","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref63","article-title":"Prioritized experience replay","author":"Schaul","year":"2015","journal-title":"arXiv:1511.05952"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref65","article-title":"Exploration by random network distillation","author":"Burda","year":"2018","journal-title":"arXiv:1810.12894"},{"key":"ref66","first-page":"1","article-title":"Distral: Robust multitask reinforcement learning","volume-title":"Proc. Adv. neural Inf. Process. Syst.","volume":"30","author":"Teh"},{"key":"ref67","first-page":"7750","article-title":"Maximum entropy gain exploration for long horizon multi-goal reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pitis"},{"key":"ref68","article-title":"Unbiased methods for multi-goal reinforcement learning","author":"Blier","year":"2021","journal-title":"arXiv:2106.08863"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/770"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.09.071"},{"key":"ref71","article-title":"Variational empowerment as representation learning for goal-based reinforcement learning","author":"Choi","year":"2021","journal-title":"arXiv:2106.01404"},{"key":"ref72","first-page":"1","article-title":"Explainable reinforcement learning via reward decomposition","volume-title":"Proc. IJCAI\/ECAI Workshop Explainable Artif. Intell.","author":"Juozapaitis"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2019.8673198"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17235"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2018.2864504"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014561"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6287639\/10005208\/10091554-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10091554.pdf?arnumber=10091554","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T04:26:03Z","timestamp":1710390363000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10091554\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3264264","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2023]]}}}