{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T07:17:12Z","timestamp":1756192632309,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819981250"},{"type":"electronic","value":"9789819981267"}],"license":[{"start":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T00:00:00Z","timestamp":1699833600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T00:00:00Z","timestamp":1699833600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-981-99-8126-7_6","type":"book-chapter","created":{"date-parts":[[2023,11,24]],"date-time":"2023-11-24T08:05:19Z","timestamp":1700813119000},"page":"76-87","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Efficient Hierarchical Reinforcement Learning via\u00a0Mutual Information Constrained Subgoal Discovery"],"prefix":"10.1007","author":[{"given":"Kaishen","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingqing","family":"Ruan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingyang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dengpeng","family":"Xing","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,13]]},"reference":[{"key":"6_CR1","unstructured":"Andrychowicz, M., et al.: Hindsight experience replay. In: Advances in Neural Information Processing Systems, vol. 30, pp. 5048\u20135058. Curran Associates, Inc. (2017)"},{"key":"6_CR2","unstructured":"Duan, Y., Chen, X., Houthooft, R., Schulman, J., Abbeel, P.: Benchmarking deep reinforcement learning for continuous control. In: Proceedings of The 33rd International Conference on Machine Learning, vol. 48, pp. 1329\u20131338. PMLR (2016)"},{"key":"6_CR3","unstructured":"Eysenbach, B., Gupta, A., Ibarz, J., Levine, S.: Diversity is all you need: learning skills without a reward function. In: International Conference on Learning Representations (2018)"},{"key":"6_CR4","unstructured":"Eysenbach, B., Zhang, T., Levine, S., Salakhutdinov, R.R.: Contrastive learning as goal-conditioned reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 35, pp. 35603\u201335620. Curran Associates, Inc. (2022)"},{"key":"6_CR5","unstructured":"Hafner, D., Lee, K.H., Fischer, I., Abbeel, P.: Deep hierarchical planning from pixels. In: Advances in Neural Information Processing Systems. vol. 35, pp. 26091\u201326104. Curran Associates, Inc. (2022)"},{"key":"6_CR6","unstructured":"Hartikainen, K., Geng, X., Haarnoja, T., Levine, S.: Dynamical distance learning for semi-supervised and unsupervised skill discovery. In: International Conference on Learning Representations (2020)"},{"key":"6_CR7","unstructured":"Huang, Z., Liu, F., Su, H.: Mapping state space using landmarks for universal goal reaching. In: Advances in Neural Information Processing Systems, vol. 32, p. 1942\u20131952. Curran Associates, Inc. (2019)"},{"key":"6_CR8","unstructured":"Kim, J., Seo, Y., Shin, J.: Landmark-guided subgoal generation in hierarchical reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 34, pp. 28336\u201328349. Curran Associates, Inc. (2021)"},{"key":"6_CR9","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, vol. 29, pp. 3675\u20133683. Curran Associates, Inc. (2016)"},{"key":"6_CR10","unstructured":"Laskin, M., Srinivas, A., Abbeel, P.: CURL: Contrastive unsupervised representations for reinforcement learning. In: Proceedings of the 37th International Conference on Machine Learning, vol. 119, pp. 5639\u20135650. PMLR (2020)"},{"key":"6_CR11","unstructured":"Levy, A., Konidaris, G., Platt, R., Saenko, K.: Learning multi-level hierarchies with hindsight. In: International Conference on Learning Representations (2019)"},{"key":"6_CR12","unstructured":"Nachum, O., Gu, S.S., Lee, H., Levine, S.: Data-efficient hierarchical reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 31, p. 3303\u20133313. Curran Associates, Inc. (2018)"},{"key":"6_CR13","unstructured":"Nasiriany, S., Pong, V., Lin, S., Levine, S.: Planning with goal-conditioned policies. In: Advances in Neural Information Processing Systems, vol. 32, p. 14843\u201314854. Curran Associates, Inc. (2019)"},{"key":"6_CR14","unstructured":"Van Den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"issue":"6","key":"6_CR15","doi-asserted-by":"publisher","first-page":"1191","DOI":"10.1162\/089976603321780272","volume":"15","author":"L Paninski","year":"2003","unstructured":"Paninski, L.: Estimation of entropy and mutual information. Neural Comput. 15(6), 1191\u20131253 (2003)","journal-title":"Neural Comput."},{"key":"6_CR16","unstructured":"Pong, V., Gu, S., Dalal, M., Levine, S.: Temporal difference models: model-free deep RL for model-based control. In: International Conference on Learning Representations (2018)"},{"key":"6_CR17","unstructured":"Poole, B., Ozair, S., Van Den Oord, A., Alemi, A., Tucker, G.: On variational bounds of mutual information. In: Proceedings of the 36th International Conference on Machine Learning, vol. 97, pp. 5171\u20135180. PMLR (2019)"},{"key":"6_CR18","unstructured":"Sharma, A., Gu, S., Levine, S., Kumar, V., Hausman, K.: Dynamics-aware unsupervised discovery of skills. In: International Conference on Learning Representations (2020)"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Yang, Y., Ruan, J., Xiong, X., Xing, D., Xu, B.: Balancing exploration and exploitation in hierarchical reinforcement learning via latent landmark graphs. In: 2023 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138. IEEE (2023)","DOI":"10.1109\/IJCNN54540.2023.10190993"},{"key":"6_CR20","unstructured":"Zhang, T., Guo, S., Tan, T., Hu, X., Chen, F.: Generating adjacency-constrained subgoals in hierarchical reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 33, pp. 21579\u201321590. Curran Associates, Inc. (2020)"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8126-7_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T11:31:32Z","timestamp":1709811092000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8126-7_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,13]]},"ISBN":["9789819981250","9789819981267"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8126-7_6","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023,11,13]]},"assertion":[{"value":"13 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Changsha","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2023.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1274","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":"650","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":"51% - 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":"4.14","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":"2.46","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)"}}]}}