{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T13:49:30Z","timestamp":1742996970115,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":22,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789811692468"},{"type":"electronic","value":"9789811692475"}],"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\/978-981-16-9247-5_28","type":"book-chapter","created":{"date-parts":[[2022,1,11]],"date-time":"2022-01-11T21:25:33Z","timestamp":1641936333000},"page":"360-373","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Sample-Efficient Reinforcement Learning Based on Dynamics Models via Meta-policy Optimization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7624-4728","authenticated-orcid":false,"given":"Guoyu","family":"Zuo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhipeng","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuai","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daoxiong","family":"Gong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,1,11]]},"reference":[{"issue":"7540","key":"28_CR1","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"issue":"7676","key":"28_CR2","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., et al.: Mastering the game of go without human knowledge. Nature 550(7676), 354\u2013359 (2017)","journal-title":"Nature"},{"key":"28_CR3","unstructured":"Deisenroth, M., Rasmussen, C.E.: PILCO: a model-based and data-efficient approach to policy search. In: Proceedings of the 28th International Conference on machine learning (ICML 2011), pp. 465\u2013472 (2011)"},{"key":"28_CR4","unstructured":"Depeweg, S., Hern\u00e1ndez-Lobato, J.M., Doshi-Velez, F., Udluft, S.: Learning and policy search in stochastic dynamical systems with Bayesian neural networks, arXiv preprint arXiv:1605.07127 (2016)"},{"key":"28_CR5","unstructured":"Farahmand, A.-M.: Iterative value-aware model learning. In: NeurIPS, pp. 9090\u20139101 (2018)"},{"key":"28_CR6","unstructured":"Wu, Y.-H., Fan, T.-H., Ramadge, P.J., Su, H.: Model imitation for model-based reinforcement learning, arXiv preprint arXiv:1909.11821 (2019)"},{"key":"28_CR7","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":"28_CR8","unstructured":"Moerland, T.M., Broekens, J., Jonker, C.M.: Model-based reinforcement learning: a survey, arXiv preprint arXiv:2006.16712 (2020)"},{"key":"28_CR9","unstructured":"Kurutach, T., Clavera, I., Duan, Y., Tamar, A., Abbeel, P.: Model-ensemble trust-region policy optimization, arXiv preprint arXiv:1802.10592 (2018)"},{"key":"28_CR10","unstructured":"Gal, Y., McAllister, R., Rasmussen, C.E.: Improving PILCO with Bayesian neural network dynamics models. In: Data-Efficient Machine Learning Workshop, ICML, vol. 4, no. 34, p. 25 (2016)"},{"key":"28_CR11","unstructured":"Wang, T., et al.: Benchmarking model-based reinforcement learning, arXiv preprint arXiv:1907.02057 (2019)"},{"key":"28_CR12","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms, arXiv preprint arXiv:1707.06347 (2017)"},{"key":"28_CR13","unstructured":"Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: International Conference on Machine Learning, pp. 1126\u20131135. PMLR (2017)"},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Peters, J., Schaal, S.: Policy gradient methods for robotics. In: 2006 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 2219\u20132225. IEEE (2006)","DOI":"10.1109\/IROS.2006.282564"},{"key":"28_CR15","unstructured":"Janner, M., Fu, J., Zhang, M., Levine, S.: When to trust your model: Model-based policy optimization, arXiv preprint arXiv:1906.08253 (2019)"},{"key":"28_CR16","unstructured":"Brockman, G., et al.: OpenAI gym. https:\/\/github.com\/openai\/gym"},{"key":"28_CR17","unstructured":"Plappert, M., Andrychowicz, M., Ray, A., Mcgrew, B., Zaremba, W.: Multi-goal reinforcement learning: challenging robotics environments and request for research, arXiv preprint arXiv:1802.09464 (2018)"},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y.: Mujoco: a physics engine for model-based control. In: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 5026\u20135033. IEEE (2012)","DOI":"10.1109\/IROS.2012.6386109"},{"key":"28_CR19","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning, arXiv preprint arXiv:1509.02971 (2015)"},{"key":"28_CR20","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: International Conference on Machine Learning, pp. 1889\u20131897. PMLR (2015)"},{"key":"28_CR21","unstructured":"Wu, Y., Mansimov, E., Liao, S., Grosse, R., Ba, J.: Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation, arXiv preprint arXiv:1708.05144 (2017)"},{"key":"28_CR22","unstructured":"Clavera, I., Rothfuss, J., Schulman, J., Fujita, Y., Asfour, T., Abbeel, P.: Model-based reinforcement learning via meta-policy optimization. In: Conference on Robot Learning, pp. 617\u2013629. PMLR (2018)"}],"container-title":["Communications in Computer and Information Science","Cognitive Systems and Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-16-9247-5_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,7]],"date-time":"2022-05-07T02:17:01Z","timestamp":1651889821000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-16-9247-5_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9789811692468","9789811692475"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-981-16-9247-5_28","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"11 January 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCSIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Cognitive Systems and Signal Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Suzhou","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":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 November 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccsip2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iccsip2021.tsingzhan.com\/#\/","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":"105","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":"41","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":"39% - 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","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":"3","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}