{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T16:18:21Z","timestamp":1774628301223,"version":"3.50.1"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002920","name":"Research Grants Council (RGC) of Hong Kong","doi-asserted-by":"publisher","award":["C4042-23GF"],"award-info":[{"award-number":["C4042-23GF"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005950","name":"The Hong Kong Polytechnic University (PolyU)\u2019Eastern Institute of Technology (EIT) Collaborative Ph.D. Training Program","doi-asserted-by":"publisher","award":["220724983"],"award-info":[{"award-number":["220724983"]}],"id":[{"id":"10.13039\/501100005950","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tase.2025.3574162","type":"journal-article","created":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T17:28:42Z","timestamp":1748366922000},"page":"16038-16049","source":"Crossref","is-referenced-by-count":3,"title":["Explicit-Implicit Subgoal Planning for Long-Horizon Tasks With Sparse Rewards"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7492-632X","authenticated-orcid":false,"given":"Fangyuan","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9666-018X","authenticated-orcid":false,"given":"Anqing","family":"Duan","sequence":"additional","affiliation":[{"name":"Robotics Department, Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, United Arab Emirates"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7020-0943","authenticated-orcid":false,"given":"Peng","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Advanced Engineering, Great Bay University, Dongguan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7652-8958","authenticated-orcid":false,"given":"Shengzeng","family":"Huo","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9583-0055","authenticated-orcid":false,"given":"Guodong","family":"Guo","sequence":"additional","affiliation":[{"name":"Ningbo Institute of Digital Twin and Zhejiang Key Laboratory of Industrial Intelligence and Digital Twin, Eastern Institute of Technology (EIT), Ningbo, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5255-5559","authenticated-orcid":false,"given":"Chenguang","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Liverpool, Liverpool, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3426-6638","authenticated-orcid":false,"given":"David","family":"Navarro-Alarcon","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3198020"},{"key":"ref2","first-page":"690","article-title":"Hindsight planner","volume-title":"Proc. 19th Int. Conf. Auto. Agents MultiAgent Syst.","author":"Lai"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2022.104691"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3298195"},{"key":"ref5","article-title":"Meta reinforcement learning with autonomous inference of subtask dependencies","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Sohn"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812096"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2012.2210294"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2986921"},{"key":"ref9","article-title":"Learning from trajectories via subgoal discovery","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paul"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3632860"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611483"},{"key":"ref12","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":"ref13","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/770"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981999"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611663"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-023-06503-w"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341773"},{"key":"ref18","article-title":"Comparison of model-free and model-based learning-informed planning for PointGoal navigation","author":"Li","year":"2022","journal-title":"arXiv:2212.08801"},{"key":"ref19","first-page":"213","article-title":"Learning over subgoals for efficient navigation of structured, unknown environments","volume-title":"Proc. Conf. Robot Learn.","author":"Stein"},{"key":"ref20","first-page":"158","article-title":"Implicit behavioral cloning","volume-title":"Proc. Conf. Robot Learn.","author":"Florence"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3191592"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.25951"},{"key":"ref23","first-page":"9191","article-title":"Visual reinforcement learning with imagined goals","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Nair"},{"key":"ref24","article-title":"Unsupervised control through non-parametric discriminative rewards","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Warde-Farley"},{"key":"ref25","first-page":"1430","article-title":"Goal-conditioned reinforcement learning with imagined subgoals","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chane-Sane"},{"key":"ref26","article-title":"Planning with goal-conditioned policies","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Nasiriany"},{"key":"ref27","article-title":"Zero-shot robotic manipulation with pre-trained image-editing diffusion models","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Black"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01558"},{"key":"ref29","article-title":"Learning multi-level hierarchies with hindsight","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Levy"},{"key":"ref30","article-title":"Data-efficient hierarchical reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Nachum"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref32","article-title":"Exploration via hindsight goal generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Ren"},{"key":"ref33","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref34","article-title":"Hindsight experience replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Andrychowicz"},{"key":"ref35","first-page":"7156","article-title":"Hierarchical reinforcement learning for zero-shot generalization with subtask dependencies","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Sohn"},{"key":"ref36","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Sohn"},{"key":"ref37","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2017.1285773"},{"key":"ref39","first-page":"1214","article-title":"VAE with a VampPrior","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Tomczak"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1002\/9781118771075"},{"key":"ref41","first-page":"1312","article-title":"Universal value function approximators","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schaul"},{"key":"ref42","volume-title":"Gymnasium Robotics","author":"De Lazcano","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref44","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Fu"},{"key":"ref45","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"van den Oord"},{"issue":"11","key":"ref46","first-page":"1","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/SII.2019.8700380"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/10839176\/11016126.pdf?arnumber=11016126","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T17:39:33Z","timestamp":1749145173000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11016126\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/tase.2025.3574162","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}