{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T01:42:10Z","timestamp":1765503730284,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3761326","type":"proceedings-article","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T00:18:04Z","timestamp":1762561084000},"page":"2305-2314","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Temporal Distance-aware Subgoal Generation for Offline Hierarchical Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7291-6992","authenticated-orcid":false,"given":"Taegeon","family":"Park","sequence":"first","affiliation":[{"name":"Sungkyunkwan University, Suwon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4322-7670","authenticated-orcid":false,"given":"Seungho","family":"Baek","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University, Suwon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6220-9034","authenticated-orcid":false,"given":"Jongchan","family":"Park","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University, Suwon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8743-8840","authenticated-orcid":false,"given":"Seungjun","family":"Oh","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University, Suwon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9306-8738","authenticated-orcid":false,"given":"Yusung","family":"Kim","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University, Suwon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning. arXiv:2010.13611 [cs.LG] https:\/\/arxiv.org\/abs\/2010.13611","author":"Ajay Anurag","year":"2021","unstructured":"Anurag Ajay, Aviral Kumar, Pulkit Agrawal, Sergey Levine, and Ofir Nachum. 2021. OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning. arXiv:2010.13611 [cs.LG] https:\/\/arxiv.org\/abs\/2010.13611"},{"key":"e_1_3_2_1_2_1","volume-title":"Graph-Assisted Stitching for Offline Hierarchical Reinforcement Learning. arXiv preprint arXiv:2506.07744","author":"Baek Seungho","year":"2025","unstructured":"Seungho Baek, Taegeon Park, Jongchan Park, Seungjun Oh, and Yusung Kim. 2025. Graph-Assisted Stitching for Offline Hierarchical Reinforcement Learning. arXiv preprint arXiv:2506.07744 (2025)."},{"key":"e_1_3_2_1_3_1","volume-title":"Recent advances in hierarchical reinforcement learning. Discrete event dynamic systems 13","author":"Barto Andrew G","year":"2003","unstructured":"Andrew G Barto and Sridhar Mahadevan. 2003. Recent advances in hierarchical reinforcement learning. Discrete event dynamic systems 13 (2003), 341--379."},{"key":"e_1_3_2_1_4_1","volume-title":"Openai gym. arXiv preprint arXiv:1606.01540","author":"Brockman Greg","year":"2016","unstructured":"Greg Brockman, Vicki Cheung, Ludwig Pettersson, Jonas Schneider, John Schulman, Jie Tang, and Wojciech Zaremba. 2016. Openai gym. arXiv preprint arXiv:1606.01540 (2016)."},{"key":"e_1_3_2_1_5_1","volume-title":"International conference on machine learning. PMLR, 1430--1440","author":"Chane-Sane Elliot","year":"2021","unstructured":"Elliot Chane-Sane, Cordelia Schmid, and Ivan Laptev. 2021. Goal-conditioned reinforcement learning with imagined subgoals. In International conference on machine learning. PMLR, 1430--1440."},{"key":"e_1_3_2_1_6_1","volume-title":"International conference on machine learning. PMLR, 1407--1416","author":"Espeholt Lasse","year":"2018","unstructured":"Lasse Espeholt, Hubert Soyer, Remi Munos, Karen Simonyan, Vlad Mnih, Tom Ward, Yotam Doron, Vlad Firoiu, Tim Harley, Iain Dunning, et al. 2018. Impala: Scalable distributed deep-rl with importanceweighted actor-learner architectures. In International conference on machine learning. PMLR, 1407--1416."},{"key":"e_1_3_2_1_7_1","volume-title":"D4rl: Datasets for deep data-driven reinforcement learning. arXiv preprint arXiv:2004.07219","author":"Fu Justin","year":"2020","unstructured":"Justin Fu, Aviral Kumar, Ofir Nachum, George Tucker, and Sergey Levine. 2020. D4rl: Datasets for deep data-driven reinforcement learning. arXiv preprint arXiv:2004.07219 (2020)."},{"key":"e_1_3_2_1_8_1","volume-title":"International Conference on Machine Learning. PMLR, 11321--11339","author":"Ghosh Dibya","year":"2023","unstructured":"Dibya Ghosh, Chethan Anand Bhateja, and Sergey Levine. 2023. Reinforcement learning from passive data via latent intentions. In International Conference on Machine Learning. PMLR, 11321--11339."},{"key":"e_1_3_2_1_9_1","volume-title":"Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning. arXiv preprint arXiv:1910.11956","author":"Gupta Abhishek","year":"2019","unstructured":"Abhishek Gupta, Vikash Kumar, Corey Lynch, Sergey Levine, and Karol Hausman. 2019. Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning. arXiv preprint arXiv:1910.11956 (2019)."},{"key":"e_1_3_2_1_10_1","volume-title":"Learning to Walk via Deep Reinforcement Learning. ArXiv abs\/1812.11103","author":"Haarnoja Tuomas","year":"2018","unstructured":"Tuomas Haarnoja, Aurick Zhou, Sehoon Ha, Jie Tan, G. Tucker, and Sergey Levine. 2018. Learning to Walk via Deep Reinforcement Learning. ArXiv abs\/1812.11103 (2018). https:\/\/api.semanticscholar.org\/CorpusID:57189150"},{"key":"e_1_3_2_1_11_1","volume-title":"Mastering atari with discrete world models. arXiv preprint arXiv:2010.02193","author":"Hafner Danijar","year":"2020","unstructured":"Danijar Hafner, Timothy Lillicrap, Mohammad Norouzi, and Jimmy Ba. 2020. Mastering atari with discrete world models. arXiv preprint arXiv:2010.02193 (2020)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-020-05938-9"},{"key":"e_1_3_2_1_13_1","unstructured":"Christopher Hoang Sungryull Sohn Jongwook Choi Wilka Carvalho and Honglak Lee. 2021. Successor Feature Landmarks for Long-Horizon Goal- Conditioned Reinforcement Learning. In Neural Information Processing Systems. https:\/\/api.semanticscholar.org\/CorpusID:244345800"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610189"},{"key":"e_1_3_2_1_15_1","volume-title":"Efficient planning in a compact latent action space. arXiv preprint arXiv:2208.10291","author":"Jiang Zhengyao","year":"2022","unstructured":"Zhengyao Jiang, Tianjun Zhang, Michael Janner, Yueying Li, Tim Rockt\u00e4schel, Edward Grefenstette, and Yuandong Tian. 2022. Efficient planning in a compact latent action space. arXiv preprint arXiv:2208.10291 (2022)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_1_17_1","volume-title":"Landmark-guided subgoal generation in hierarchical reinforcement learning. Advances in neural information processing systems 34","author":"Kim Junsu","year":"2021","unstructured":"Junsu Kim, Younggyo Seo, and Jinwoo Shin. 2021. Landmark-guided subgoal generation in hierarchical reinforcement learning. Advances in neural information processing systems 34 (2021), 28336--28349."},{"key":"e_1_3_2_1_18_1","volume-title":"Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114","author":"Kingma Diederik P","year":"2013","unstructured":"Diederik P Kingma. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)."},{"key":"e_1_3_2_1_19_1","volume-title":"International Conference on Machine Learning. PMLR, 5774--5783","author":"Kostrikov Ilya","year":"2021","unstructured":"Ilya Kostrikov, Rob Fergus, Jonathan Tompson, and Ofir Nachum. 2021. Offline reinforcement learning with fisher divergence critic regularization. In International Conference on Machine Learning. PMLR, 5774--5783."},{"key":"e_1_3_2_1_20_1","volume-title":"Stabilizing off-policy q-learning via bootstrapping error reduction. Advances in Neural Information Processing Systems 32","author":"Kumar Aviral","year":"2019","unstructured":"Aviral Kumar, Justin Fu, Matthew Soh, George Tucker, and Sergey Levine. 2019. Stabilizing off-policy q-learning via bootstrapping error reduction. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_1_21_1","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"Kumar Aviral","year":"2020","unstructured":"Aviral Kumar, Aurick Zhou, George Tucker, and Sergey Levine. 2020. Conservative q-learning for offline reinforcement learning. Advances in Neural Information Processing Systems 33 (2020), 1179--1191.","journal-title":"Advances in Neural Information Processing Systems"},{"volume-title":"Reinforcement learning: State-of-the-art","author":"Lange Sascha","key":"e_1_3_2_1_22_1","unstructured":"Sascha Lange, Thomas Gabel, and Martin Riedmiller. 2012. Batch reinforcement learning. In Reinforcement learning: State-of-the-art. Springer, 45--73."},{"key":"e_1_3_2_1_23_1","volume-title":"DHRL: A Graph- Based Approach for Long-Horizon and Sparse Hierarchical Reinforcement Learning. ArXiv abs\/2210.05150","author":"Lee Seungjae","year":"2022","unstructured":"Seungjae Lee, Jigang Kim, Inkyu Jang, and H. Jin Kim. 2022. DHRL: A Graph- Based Approach for Long-Horizon and Sparse Hierarchical Reinforcement Learning. ArXiv abs\/2210.05150 (2022). https:\/\/api.semanticscholar.org\/CorpusID:252815462"},{"key":"e_1_3_2_1_24_1","volume-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems. arXiv preprint arXiv:2005.01643","author":"Levine Sergey","year":"2020","unstructured":"Sergey Levine, Aviral Kumar, George Tucker, and Justin Fu. 2020. Offline reinforcement learning: Tutorial, review, and perspectives on open problems. arXiv preprint arXiv:2005.01643 (2020)."},{"key":"e_1_3_2_1_25_1","volume-title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems. ArXiv abs\/2005.01643","author":"Levine Sergey","year":"2020","unstructured":"Sergey Levine, Aviral Kumar, G. Tucker, and Justin Fu. 2020. Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems. ArXiv abs\/2005.01643 (2020). https:\/\/api.semanticscholar.org\/CorpusID:218486979"},{"key":"e_1_3_2_1_26_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Li Wenhao","year":"2023","unstructured":"Wenhao Li, Xiangfeng Wang, Bo Jin, and Hongyuan Zha. 2023. Hierarchical diffusion for offline decision making. In International Conference on Machine Learning. PMLR, 20035--20064."},{"key":"e_1_3_2_1_27_1","volume-title":"Conference on robot learning. PMLR, 1113--1132","author":"Lynch Corey","year":"2020","unstructured":"Corey Lynch, Mohi Khansari, Ted Xiao, Vikash Kumar, Jonathan Tompson, Sergey Levine, and Pierre Sermanet. 2020. Learning latent plans from play. In Conference on robot learning. PMLR, 1113--1132."},{"key":"e_1_3_2_1_28_1","unstructured":"Volodymyr Mnih Koray Kavukcuoglu David Silver Alex Graves Ioannis Antonoglou Daan Wierstra and Martin Riedmiller. 2013. Playing Atari with Deep Reinforcement Learning. arXiv:1312.5602 [cs.LG]"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_1_30_1","volume-title":"Why does hierarchy (sometimes) work so well in reinforcement learning? arXiv preprint arXiv:1909.10618","author":"Nachum Ofir","year":"2019","unstructured":"Ofir Nachum, Haoran Tang, Xingyu Lu, Shixiang Gu, Honglak Lee, and Sergey Levine. 2019. Why does hierarchy (sometimes) work so well in reinforcement learning? arXiv preprint arXiv:1909.10618 (2019)."},{"key":"e_1_3_2_1_31_1","volume-title":"AWAC: Accelerating Online Reinforcement Learning with Offline Datasets. arXiv:2006.09359 [cs.LG]","author":"Nair Ashvin","year":"2021","unstructured":"Ashvin Nair, Abhishek Gupta, Murtaza Dalal, and Sergey Levine. 2021. AWAC: Accelerating Online Reinforcement Learning with Offline Datasets. arXiv:2006.09359 [cs.LG]"},{"key":"e_1_3_2_1_32_1","volume-title":"Asymmetric least squares estimation and testing. Econometrica: Journal of the Econometric Society","author":"Newey Whitney K","year":"1987","unstructured":"Whitney K Newey and James L Powell. 1987. Asymmetric least squares estimation and testing. Econometrica: Journal of the Econometric Society (1987), 819--847."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679523"},{"key":"e_1_3_2_1_34_1","volume-title":"Hiql: Offline goal-conditioned rl with latent states as actions. arXiv preprint arXiv:2307.11949","author":"Park Seohong","year":"2023","unstructured":"Seohong Park, Dibya Ghosh, Benjamin Eysenbach, and Sergey Levine. 2023. Hiql: Offline goal-conditioned rl with latent states as actions. arXiv preprint arXiv:2307.11949 (2023)."},{"key":"e_1_3_2_1_35_1","volume-title":"Foundation policies with hilbert representations. arXiv preprint arXiv:2402.15567","author":"Park Seohong","year":"2024","unstructured":"Seohong Park, Tobias Kreiman, and Sergey Levine. 2024. Foundation policies with hilbert representations. arXiv preprint arXiv:2402.15567 (2024)."},{"key":"e_1_3_2_1_36_1","volume-title":"Advantageweighted regression: Simple and scalable off-policy reinforcement learning. arXiv preprint arXiv:1910.00177","author":"Peng Xue Bin","year":"2019","unstructured":"Xue Bin Peng, Aviral Kumar, Grace Zhang, and Sergey Levine. 2019. Advantageweighted regression: Simple and scalable off-policy reinforcement learning. arXiv preprint arXiv:1910.00177 (2019)."},{"key":"e_1_3_2_1_37_1","unstructured":"Matthias Plappert Marcin Andrychowicz Alex Ray Bob McGrew Bowen Baker Glenn Powell Jonas Schneider Josh Tobin Maciek Chociej Peter Welinder Vikash Kumar and Wojciech Zaremba. 2018. Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research. arXiv:arXiv:1802.09464"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/469"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"e_1_3_2_1_41_1","unstructured":"Aaron van den Oord Oriol Vinyals and Koray Kavukcuoglu. 2018. Neural Discrete Representation Learning. arXiv:1711.00937 [cs.LG] https:\/\/arxiv.org\/abs\/1711.00937"},{"volume-title":"DayDreamer: World Models for Physical Robot Learning. In Conference on Robot Learning. https:\/\/api.semanticscholar.org\/CorpusID:250088882","author":"Wu Philipp","key":"e_1_3_2_1_42_1","unstructured":"Philipp Wu, Alejandro Escontrela, Danijar Hafner, Ken Goldberg, and P. Abbeel. 2022. DayDreamer: World Models for Physical Robot Learning. In Conference on Robot Learning. https:\/\/api.semanticscholar.org\/CorpusID:250088882"},{"key":"e_1_3_2_1_43_1","volume-title":"Behavior regularized offline reinforcement learning. arXiv preprint arXiv:1911.11361","author":"Wu Yifan","year":"2019","unstructured":"Yifan Wu, George Tucker, and Ofir Nachum. 2019. Behavior regularized offline reinforcement learning. arXiv preprint arXiv:1911.11361 (2019)."},{"key":"e_1_3_2_1_44_1","volume-title":"International Conference on Machine Learning. PMLR, 11784--11794","author":"Yang Mengjiao","year":"2021","unstructured":"Mengjiao Yang and Ofir Nachum. 2021. Representation matters: Offline pretraining for sequential decision making. In International Conference on Machine Learning. PMLR, 11784--11794."},{"key":"e_1_3_2_1_45_1","volume-title":"Rethinking goal-conditioned supervised learning and its connection to offline rl. arXiv preprint arXiv:2202.04478","author":"Yang Rui","year":"2022","unstructured":"Rui Yang, Yiming Lu, Wenzhe Li, Hao Sun, Meng Fang, Yali Du, Xiu Li, Lei Han, and Chongjie Zhang. 2022. Rethinking goal-conditioned supervised learning and its connection to offline rl. arXiv preprint arXiv:2202.04478 (2022)."},{"key":"e_1_3_2_1_46_1","first-page":"14129","article-title":"Mopo: Model-based offline policy optimization","volume":"33","author":"Yu Tianhe","year":"2020","unstructured":"Tianhe Yu, Garrett Thomas, Lantao Yu, Stefano Ermon, James Y Zou, Sergey Levine, Chelsea Finn, and Tengyu Ma. 2020. Mopo: Model-based offline policy optimization. Advances in Neural Information Processing Systems 33 (2020), 14129--14142.","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Seoul Republic of Korea","acronym":"CIKM '25"},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3761326","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T01:40:29Z","timestamp":1765503629000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3761326"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":46,"alternative-id":["10.1145\/3746252.3761326","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3761326","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}