{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T19:09:38Z","timestamp":1742929778136,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819980819"},{"type":"electronic","value":"9789819980826"}],"license":[{"start":{"date-parts":[[2023,11,15]],"date-time":"2023-11-15T00:00:00Z","timestamp":1700006400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,15]],"date-time":"2023-11-15T00:00:00Z","timestamp":1700006400000},"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\/978-981-99-8082-6_17","type":"book-chapter","created":{"date-parts":[[2023,11,14]],"date-time":"2023-11-14T16:08:09Z","timestamp":1699978089000},"page":"219-230","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Latent Causal Dynamics Model for\u00a0Model-Based Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Zhifeng","family":"Hao","sequence":"first","affiliation":[]},{"given":"Haipeng","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Ruichu","family":"Cai","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,11,15]]},"reference":[{"key":"17_CR1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-85729-398-5","volume-title":"Model Predictive Control","author":"EF Camacho","year":"2013","unstructured":"Camacho, E.F., Alba, C.B.: Model Predictive Control. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-0-85729-398-5"},{"issue":"7","key":"17_CR2","doi-asserted-by":"publisher","first-page":"2816","DOI":"10.1109\/TNNLS.2020.3045812","volume":"33","author":"W Chen","year":"2021","unstructured":"Chen, W., Cai, R., Zhang, K., Hao, Z.: Causal discovery in linear non-gaussian acyclic model with multiple latent confounders. IEEE Trans. Neural Netw. Learn. Syst. 33(7), 2816\u20132827 (2021)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"17_CR3","unstructured":"Chua, K., Calandra, R., McAllister, R., Levine, S.: Deep reinforcement learning in a handful of trials using probabilistic dynamics models. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Deisenroth, M.P., Rasmussen, C.E., Fox, D.: Learning to control a low-cost manipulator using data-efficient reinforcement learning. Robot. Sci. Syst. VII(7), 57\u201364 (2011)","DOI":"10.7551\/mitpress\/9481.003.0013"},{"key":"17_CR5","unstructured":"Ding, W., Lin, H., Li, B., Zhao, D.: Generalizing goal-conditioned reinforcement learning with variational causal reasoning. In: Advances in Neural Information Processing Systems (2022)"},{"key":"17_CR6","unstructured":"Ghugare, R., Bharadhwaj, H., Eysenbach, B., Levine, S., Salakhutdinov, R.: Simplifying model-based RL: learning representations, latent-space models, and policies with one objective. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"17_CR7","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861\u20131870. PMLR (2018)"},{"key":"17_CR8","unstructured":"Hafner, D., et al.: Learning latent dynamics for planning from pixels. In: International Conference on Machine Learning, pp. 2555\u20132565. PMLR (2019)"},{"key":"17_CR9","unstructured":"Hansen, N.A., Su, H., Wang, X.: Temporal difference learning for model predictive control. In: International Conference on Machine Learning, pp. 8387\u20138406. PMLR (2022)"},{"key":"17_CR10","unstructured":"Hu, A., et al.: Model-based imitation learning for urban driving. In: Advances in Neural Information Processing Systems, vol. 35, pp. 20703\u201320716 (2022)"},{"key":"17_CR11","unstructured":"Huang, B., et al.: Action-sufficient state representation learning for control with structural constraints. In: International Conference on Machine Learning, pp. 9260\u20139279. PMLR (2022)"},{"key":"17_CR12","unstructured":"Kurutach, T., Clavera, I., Duan, Y., Tamar, A., Abbeel, P.: Model-ensemble trust-region policy optimization. In: International Conference on Learning Representations (2018)"},{"key":"17_CR13","unstructured":"Lu, C.: Learning causal representations for generalization and adaptation in supervised, imitation, and reinforcement learning. Ph.D. thesis, University of Cambridge (2022)"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","DOI":"10.1038\/nature14236"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Nagabandi, A., Kahn, G., Fearing, R.S., Levine, S.: Neural network dynamics for model-based deep reinforcement learning with model-free fine-tuning. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 7559\u20137566. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Nguyen, H., La, H.: Review of deep reinforcement learning for robot manipulation. In: 2019 Third IEEE International Conference on Robotic Computing (IRC), pp. 590\u2013595. IEEE (2019)","DOI":"10.1109\/IRC.2019.00120"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Pearl, J.: Causality: Models, Reasoning, and Inference. Cambridge University Press, Cambridge (2009)","DOI":"10.1017\/CBO9780511803161"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Runge, J., Nowack, P., Kretschmer, M., Flaxman, S., Sejdinovic, D.: Detecting and quantifying causal associations in large nonlinear time series datasets. Sci. Adv. 5(11), eaau4996 (2019)","DOI":"10.1126\/sciadv.aau4996"},{"key":"17_CR19","unstructured":"Sikchi, H., Zhou, W., Held, D.: Learning off-policy with online planning. In: Conference on Robot Learning, pp. 1622\u20131633. PMLR (2022)"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Spirtes, P., Glymour, C.N., Scheines, R., Heckerman, D.: Causation, Prediction, and Search. MIT Press, Cambridge (2000)","DOI":"10.7551\/mitpress\/1754.001.0001"},{"key":"17_CR21","unstructured":"Tassa, Y., et al.: Deepmind control suite. arXiv preprint arXiv:1801.00690 (2018)"},{"key":"17_CR22","unstructured":"Williams, G., Aldrich, A., Theodorou, E.: Model predictive path integral control using covariance variable importance sampling. arXiv preprint arXiv:1509.01149 (2015)"},{"key":"17_CR23","unstructured":"Ye, W., Liu, S., Kurutach, T., Abbeel, P., Gao, Y.: Mastering Atari games with limited data. In: Advances in Neural Information Processing Systems, vol. 34, pp. 25476\u201325488 (2021)"},{"key":"17_CR24","unstructured":"Zhang, K., Peters, J., Janzing, D., Sch\u00f6lkopf, B.: Kernel-based conditional independence test and application in causal discovery. In: 27th Conference on Uncertainty in Artificial Intelligence (UAI 2011), pp. 804\u2013813. AUAI Press (2011)"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8082-6_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T17:07:17Z","timestamp":1710349637000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8082-6_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,15]]},"ISBN":["9789819980819","9789819980826"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8082-6_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,11,15]]},"assertion":[{"value":"15 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)"}}]}}