{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T03:04:25Z","timestamp":1743131065732,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031059353"},{"type":"electronic","value":"9783031059360"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-05936-0_30","type":"book-chapter","created":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:07:09Z","timestamp":1652198829000},"page":"380-391","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Safe Offline Reinforcement Learning Through Hierarchical Policies"],"prefix":"10.1007","author":[{"given":"Shaofan","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiliang","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,5,11]]},"reference":[{"key":"30_CR1","unstructured":"Achiam, J., Held, D., Tamar, A., Abbeel, P.: Constrained policy optimization. In: International Conference on Machine Learning, pp. 22\u201331. PMLR (2017)"},{"key":"30_CR2","unstructured":"Agarwal, R., Schuurmans, D., Norouzi, M.: An optimistic perspective on offline reinforcement learning. In: International Conference on Machine Learning, pp. 104\u2013114. PMLR (2020)"},{"key":"30_CR3","doi-asserted-by":"crossref","unstructured":"Bacon, P.L., Harb, J., Precup, D.: The option-critic architecture. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 1726\u20131734 (2017)","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"30_CR4","doi-asserted-by":"crossref","unstructured":"Bi, J., Dhiman, V., Xiao, T., Xu, C.: Learning from interventions using hierarchical policies for safe learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 10352\u201310360 (2020)","DOI":"10.1609\/aaai.v34i06.6602"},{"key":"30_CR5","unstructured":"Brockman, G., et al.: OpenAI Gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"30_CR6","unstructured":"Dalal, G., Dvijotham, K., Vecerik, M., Hester, T., Paduraru, C., Tassa, Y.: Safe exploration in continuous action spaces. arXiv preprint arXiv:1801.08757 (2018)"},{"key":"30_CR7","unstructured":"Fujimoto, S., Conti, E., Ghavamzadeh, M., Pineau, J.: Benchmarking batch deep reinforcement learning algorithms. arXiv preprint arXiv:1910.01708 (2019)"},{"key":"30_CR8","unstructured":"Fujimoto, S., Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: International Conference on Machine Learning, pp. 1587\u20131596. PMLR (2018)"},{"key":"30_CR9","unstructured":"Fujimoto, S., Meger, D., Precup, D.: Off-policy deep reinforcement learning without exploration. In: International Conference on Machine Learning, pp. 2052\u20132062 (2019)"},{"key":"30_CR10","unstructured":"Gulcehre, C., et al.: RL unplugged: a suite of benchmarks for offline reinforcement learning. arXiv preprint arXiv:2006.13888 (2020)"},{"issue":"8","key":"30_CR11","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"30_CR12","unstructured":"Kulkarni, T.D., Narasimhan, K., Saeedi, A., Tenenbaum, J.: Hierarchical deep reinforcement learning: integrating temporal abstraction and intrinsic motivation. In: Advances in Neural Information Processing Systems, pp. 3675\u20133683 (2016)"},{"key":"30_CR13","unstructured":"Kumar, A., Zhou, A., Tucker, G., Levine, S.: Conservative q-learning for offline reinforcement learning. arXiv preprint arXiv:2006.04779 (2020)"},{"key":"30_CR14","doi-asserted-by":"publisher","unstructured":"Lange, S., Gabel, T., Riedmiller, M.: Batch reinforcement learning. In: Wiering, M., van Otterlo, M. (eds.) Reinforcement Learning. Adaptation, Learning, and Optimization, vol. 12, pp. 45\u201373. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-27645-3_2","DOI":"10.1007\/978-3-642-27645-3_2"},{"key":"30_CR15","unstructured":"Levine, S., Kumar, A., Tucker, G., Fu, J.: Offline reinforcement learning: tutorial, review, and perspectives on open problems. arXiv preprint arXiv:2005.01643 (2020)"},{"key":"30_CR16","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"30_CR17","doi-asserted-by":"crossref","unstructured":"Ma, J., Zhao, Z., Yi, X., Chen, J., Hong, L., Chi, E.H.: Modeling task relationships in multi-task learning with multi-gate mixture-of-experts. In: International Conference on Knowledge Discovery & Data Mining, pp. 1930\u20131939 (2018)","DOI":"10.1145\/3219819.3220007"},{"key":"30_CR18","unstructured":"Nachum, O., Gu, S., Lee, H., Levine, S.: Near-optimal representation learning for hierarchical reinforcement learning. In: International Conference on Learning Representations, pp. 1\u201318 (2018)"},{"key":"30_CR19","unstructured":"Nachum, O., Gu, S.S., Lee, H., Levine, S.: Data-efficient hierarchical reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 3303\u20133313 (2018)"},{"key":"30_CR20","unstructured":"Ray, A., Achiam, J., Amodei, D.: Benchmarking safe exploration in deep reinforcement learning. arXiv preprint arXiv:1910.01708 (2019)"},{"key":"30_CR21","unstructured":"Srinivasan, K., Eysenbach, B., Ha, S., Tan, J., Finn, C.: Learning to be safe: deep reinforcement learning with a safety critic. arXiv preprint arXiv:2010.14603 (2020)"},{"issue":"1","key":"30_CR22","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"RS Sutton","year":"1999","unstructured":"Sutton, R.S., Precup, D., Singh, S.: Between MDPS and semi-MDPS: a framework for temporal abstraction in reinforcement learning. Artif. Intell. 112(1), 181\u2013211 (1999)","journal-title":"Artif. Intell."},{"key":"30_CR23","doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y.: MUJOCO: a physics engine for model-based control. In: International Conference on Intelligent Robots and Systems, pp. 5026\u20135033. IEEE (2012)","DOI":"10.1109\/IROS.2012.6386109"},{"key":"30_CR24","unstructured":"Vezhnevets, A.S., et al.: Feudal networks for hierarchical reinforcement learning. In: International Conference on Machine Learning, pp. 3540\u20133549. PMLR (2017)"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-05936-0_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,4]],"date-time":"2023-02-04T21:00:58Z","timestamp":1675544458000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-05936-0_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031059353","9783031059360"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-05936-0_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"11 May 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chengdu","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 May 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 May 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/pakdd.net\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"558","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"121","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"22% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.75","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"6.45","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}