{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T01:59:08Z","timestamp":1774663148314,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":19,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819698936","type":"print"},{"value":"9789819698943","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-9894-3_13","type":"book-chapter","created":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T19:57:17Z","timestamp":1753473437000},"page":"145-155","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimizing Landmark Graphs in DHRL: A Dual Approach of Attention and Weighted Sampling"],"prefix":"10.1007","author":[{"given":"Zhenchun","family":"Wei","sequence":"first","affiliation":[]},{"given":"Cheng","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Zengwei","family":"Lyu","sequence":"additional","affiliation":[]},{"given":"Xiaohui","family":"Yuan","sequence":"additional","affiliation":[]},{"given":"Li","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Chi","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,26]]},"reference":[{"key":"13_CR1","first-page":"13668","volume":"35","author":"S Lee","year":"2022","unstructured":"Lee, S., Kim, J., Jang, I., Kim, H.J.: DHRL: a graph-based approach for long-horizon and sparse hierarchical reinforcement learning. Adv. Neural. Inf. Process. Syst. 35, 13668\u201313678 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR2","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":"13_CR3","doi-asserted-by":"crossref","unstructured":"Shin, W., Kim, Y.: Guide to control: offline hierarchical reinforcement learning using subgoal generation for long-horizon and sparse-reward tasks. In: IJCAI, pp. 4217\u20134225 (2023)","DOI":"10.24963\/ijcai.2023\/469"},{"key":"13_CR4","first-page":"28336","volume":"34","author":"J Kim","year":"2021","unstructured":"Kim, J., Seo, Y., Shin, J.: Landmark-guided subgoal generation in hierarchical reinforcement learning. Adv. Neural. Inf. Process. Syst. 34, 28336\u201328349 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR5","doi-asserted-by":"publisher","first-page":"1127642","DOI":"10.3389\/fnbot.2023.1127642","volume":"17","author":"MB Hafez","year":"2023","unstructured":"Hafez, M.B., Immisch, T., Weber, T., Wermter, S.: Map-based experience replay: a memory-efficient solution to catastrophic forgetting in reinforcement learning. Front. Neurorobot. 17, 1127642 (2023)","journal-title":"Front. Neurorobot."},{"key":"13_CR6","unstructured":"Eysenbach, B., Salakhutdinov, R.R., Levine, S.: Search on the replay buffer: bridging planning and reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Hafez, M.B., Weber, C., Kerzel, M., Wermter, S.: Efficient Intrinsically motivated robotic grasping with learning-adaptive imagination in latent space. In: 2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (icdl-epirob), pp. 1\u20137. IEEE (2019)","DOI":"10.1109\/DEVLRN.2019.8850723"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Zhang, J., Hao, B., Chen, B., Li, C., Chen, H., Sun, J.: Hierarchical reinforcement learning for course recommendation in MOOCs. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 435\u2013442 (2019)","DOI":"10.1609\/aaai.v33i01.3301435"},{"key":"13_CR9","unstructured":"Waradpande, V., Kudenko, D., Khosla, M.: Graph-based State Representation for Deep Reinforcement Learning. arXiv preprint arXiv:2004.13965. (2020)"},{"key":"13_CR10","unstructured":"Zhang, L., Yang, G., Stadie, B.C.: World model as a graph: learning latent landmarks for planning. In: International Conference on Machine Learning, pp. 12611\u201312620. PMLR (2021)"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Chen, Y., Dong, C., Palanisamy, P., Mudalige, P., Muelling, K., Dolan, J.M.: Attention-based hierarchical deep reinforcement learning for lane change behaviors in autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (2019)","DOI":"10.1109\/CVPRW.2019.00172"},{"key":"13_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123356","volume":"248","author":"Y Sun","year":"2024","unstructured":"Sun, Y., Plato\u0161, J.: Abstractive text summarization model combining a hierarchical attention mechanism and multiobjective reinforcement learning. Expert Syst. Appl. 248, 123356 (2024)","journal-title":"Expert Syst. Appl."},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Wang, R., Zhao, D., Gupte, A., Min, B.-C.: initial task allocation in multi-human multi-robot teams: an attention-enhanced hierarchical reinforcement learning approach. IEEE Robot. Autom. Lett. (2024)","DOI":"10.1109\/LRA.2024.3366414"},{"key":"13_CR14","unstructured":"Christiano, P., et al.: Transfer from simulation to real world through learning deep inverse dynamics model. arXiv preprint arXiv:1610.03518. (2016)"},{"key":"13_CR15","doi-asserted-by":"publisher","first-page":"1369","DOI":"10.1016\/0021-9290(94)00185-7","volume":"28","author":"B Koopman","year":"1995","unstructured":"Koopman, B., Grootenboer, H.J., De Jongh, H.J.: An inverse dynamics model for the analysis, reconstruction and prediction of bipedal walking. J. Biomech. 28, 1369\u20131376 (1995)","journal-title":"J. Biomech."},{"key":"13_CR16","doi-asserted-by":"publisher","first-page":"1493","DOI":"10.1007\/s00707-023-03532-3","volume":"235","author":"P Milicevic","year":"2024","unstructured":"Milicevic, P., Altay, O.: Data generation framework for inverse modeling of nonlinear systems in structural dynamics applications. Acta Mech. 235, 1493\u20131515 (2024)","journal-title":"Acta Mech."},{"key":"13_CR17","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":"13_CR18","doi-asserted-by":"crossref","unstructured":"Wang, H., Tang, Z., Sun, Y., Wang, F., Zhang, S., Chen, Y.: Guided cooperation in hierarchical reinforcement learning via model-based rollout. IEEE Trans. Neural Netw. Learn. Syst. (2024)","DOI":"10.1109\/TNNLS.2024.3425809"},{"key":"13_CR19","first-page":"21579","volume":"33","author":"T Zhang","year":"2020","unstructured":"Zhang, T., Guo, S., Tan, T., Hu, X., Chen, F.: Generating adjacency-constrained subgoals in hierarchical reinforcement learning. Adv. Neural. Inf. Process. Syst. 33, 21579\u201321590 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-9894-3_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T01:35:28Z","timestamp":1774661728000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9894-3_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819698936","9789819698943"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9894-3_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"26 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}