{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T22:20:31Z","timestamp":1766269231100,"version":"3.37.3"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62073244"],"award-info":[{"award-number":["62073244"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Innovation Action Plan","award":["20511100500"],"award-info":[{"award-number":["20511100500"]}]},{"name":"Innovation Program of Shanghai Municipal Education Commission","award":["202101070007E00098"],"award-info":[{"award-number":["202101070007E00098"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1109\/lra.2023.3287362","type":"journal-article","created":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T18:19:56Z","timestamp":1687198796000},"page":"4721-4728","source":"Crossref","is-referenced-by-count":6,"title":["Goal-Conditioned Reinforcement Learning With Disentanglement-Based Reachability Planning"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9724-6928","authenticated-orcid":false,"given":"Zhifeng","family":"Qian","sequence":"first","affiliation":[{"name":"College of Electronic and Information Engineering, Frontiers Science Center for Intelligent Autonomous Systems, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2758-167X","authenticated-orcid":false,"given":"Mingyu","family":"You","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Frontiers Science Center for Intelligent Autonomous Systems, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6256-2485","authenticated-orcid":false,"given":"Hongjun","family":"Zhou","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Frontiers Science Center for Intelligent Autonomous Systems, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0394-8713","authenticated-orcid":false,"given":"Xuanhui","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Frontiers Science Center for Intelligent Autonomous Systems, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3193-6269","authenticated-orcid":false,"given":"Bin","family":"He","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Frontiers Science Center for Intelligent Autonomous Systems, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"2466","article-title":"Hindsight task relabelling: Experience replay for sparse reward meta-RL","author":"packer","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","first-page":"5055","article-title":"Hindsight experience replay","author":"andrychowicz","year":"0","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref15","first-page":"1","article-title":"Temporal difference models: Model-free deep RL for model-based control","author":"pong","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref14","first-page":"12611","article-title":"World model as a graph: Learning latent landmarks for planning","author":"zhang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"article-title":"Robosuite: A modular simulation framework and benchmark for robot learning","year":"2020","author":"zhu","key":"ref31"},{"key":"ref30","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13554"},{"key":"ref33","first-page":"2579","article-title":"Visualizing data using T-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref10","first-page":"1094","article-title":"Learning to achieve goals","volume":"2","author":"kaelbling","year":"0","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref2","first-page":"14843","article-title":"Planning with goal-conditioned policies","author":"nasiriany","year":"0","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561936"},{"key":"ref17","first-page":"9209","article-title":"Visual reinforcement learning with imagined goals","author":"nair","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","first-page":"15639","article-title":"CURL: Contrastive unsupervised representations for reinforcement learning","author":"srinivas","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref19","first-page":"148","article-title":"SorNet: Spatial object-centric representations for sequential manipulation","author":"yuan","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561692"},{"key":"ref24","first-page":"30432","article-title":"Leco: Learnable episodic count for task-specific intrinsic reward","author":"jo","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","first-page":"2750","article-title":"# Exploration: A study of count-based exploration for deep reinforcement learning","author":"tang","year":"0","journal-title":"Proc 31st Int Conf Adv Neural Inf Process Syst"},{"key":"ref26","first-page":"1","article-title":"SPACE: Unsupervised object-oriented scene representation via spatial attention and decomposition","author":"lin","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref25","first-page":"1","article-title":"Episodic curiosity through reachability","author":"savinov","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref20","first-page":"1030","article-title":"Roll: Visual self-supervised reinforcement learning with object reasoning","author":"wang","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref22","first-page":"1","article-title":"Exploration by random network distillation","author":"burda","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref28","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"0","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref27","first-page":"1","article-title":"SCALOR: Generative world models with scalable object representations","author":"jiang","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5724-z"},{"key":"ref8","first-page":"15246","article-title":"Search on the replay buffer: Bridging planning and reinforcement learning","author":"eysenbach","year":"0","journal-title":"Proc 33rd Int Conf Adv Neural Inf Process Syst"},{"key":"ref7","first-page":"1","article-title":"C-planning: An automatic curriculum for learning goal-reaching tasks","author":"zhang","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref9","first-page":"1","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01437"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3141148"},{"key":"ref6","first-page":"1430","article-title":"Goal-conditioned reinforcement learning with imagined subgoals","author":"chane-sane","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/770"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10153452\/10155203.pdf?arnumber=10155203","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,17]],"date-time":"2023-07-17T17:54:07Z","timestamp":1689616447000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10155203\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":33,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/lra.2023.3287362","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"type":"electronic","value":"2377-3766"},{"type":"electronic","value":"2377-3774"}],"subject":[],"published":{"date-parts":[[2023,8]]}}}