{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T06:59:03Z","timestamp":1743145143859,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031264115"},{"type":"electronic","value":"9783031264122"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-26412-2_9","type":"book-chapter","created":{"date-parts":[[2023,3,16]],"date-time":"2023-03-16T10:03:54Z","timestamp":1678961034000},"page":"132-147","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Safe Exploration Method for\u00a0Reinforcement Learning Under Existence of\u00a0Disturbance"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5095-4927","authenticated-orcid":false,"given":"Yoshihiro","family":"Okawa","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3376-2779","authenticated-orcid":false,"given":"Tomotake","family":"Sasaki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hitoshi","family":"Yanami","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9907-4234","authenticated-orcid":false,"given":"Toru","family":"Namerikawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,17]]},"reference":[{"key":"9_CR1","unstructured":"Achiam, J., Held, D., Tamar, A., Abbeel, P.: Constrained policy optimization. In: Proceedings of the 34th International Conference on Machine Learning, pp. 22\u201331 (2017)"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Ames, A.D., Coogan, S., Egerstedt, M., Notomista, G., Sreenath, K., Tabuada, P.: Control barrier functions: theory and applications. In: Proceedings of the 18th European Control Conference, pp. 3420\u20133431 (2019)","DOI":"10.23919\/ECC.2019.8796030"},{"key":"9_CR3","unstructured":"Berkenkamp, F., Turchetta, M., Schoellig, A., Krause, A.: Safe model-based reinforcement learning with stability guarantees. In: Advances in Neural Information Processing Systems 30, pp. 908\u2013919 (2017)"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Biyik, E., Margoliash, J., Alimo, S.R., Sadigh, D.: Efficient and safe exploration in deterministic Markov decision processes with unknown transition models. In: Proceedings of the 2019 American Control Conference, pp. 1792\u20131799 (2019)","DOI":"10.23919\/ACC.2019.8815276"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Boyd, S., Vandenberghe, L.: Convex Optimization. Cambridge University Press (2004)","DOI":"10.1017\/CBO9780511804441"},{"key":"9_CR6","unstructured":"Brockman, G., et al.: OpenAI Gym. arXiv preprint. arXiv:1606.01540 (2016). The code is available at https:\/\/github.com\/openai\/gym with the MIT License"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, R., Orosz, G., Murray, R.M., Burdick, J.W.: End-to-end safe reinforcement learning through barrier functions for safety-critical continuous control tasks. In: Proceedings of the 33rd AAAI Conference on Artificial Intelligence, pp. 3387\u20133395 (2019)","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"9_CR8","unstructured":"Chow, Y., Nachum, O., Faust, A., Duenez-Guzman, E., Ghavamzadeh, M.: Lyapunov-based safe policy optimization for continuous control. arXiv preprint. arXiv:1901.10031 (2019)"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Fan, D.D., Nguyen, J., Thakker, R., Alatur, N., Agha-mohammadi, A.A., Theodorou, E.A.: Bayesian learning-based adaptive control for safety critical systems. In: Proceedings of the 2020 IEEE International Conference on Robotics and Automation, pp. 4093\u20134099 (2020)","DOI":"10.1109\/ICRA40945.2020.9196709"},{"key":"9_CR10","first-page":"1437","volume":"16","author":"J Garc\u00eda","year":"2015","unstructured":"Garc\u00eda, J., Fern\u00e1ndez, F.: A comprehensive survey on safe reinforcement learning. J. Mach. Learn. Res. 16, 1437\u20131480 (2015)","journal-title":"J. Mach. Learn. Res."},{"key":"9_CR11","doi-asserted-by":"publisher","first-page":"165007","DOI":"10.1109\/ACCESS.2019.2952651","volume":"7","author":"Y Ge","year":"2019","unstructured":"Ge, Y., Zhu, F., Ling, X., Liu, Q.: Safe Q-learning method based on constrained Markov decision processes. IEEE Access 7, 165007\u2013165017 (2019)","journal-title":"IEEE Access"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Glavic, M., Fonteneau, R., Ernst, D.: Reinforcement learning for electric power system decision and control: past considerations and perspectives. In: Proceedings of the 20th IFAC World Congress, pp. 6918\u20136927 (2017)","DOI":"10.1016\/j.ifacol.2017.08.1217"},{"key":"9_CR13","unstructured":"Khojasteh, M.J., Dhiman, V., Franceschetti, M., Atanasov, N.: Probabilistic safety constraints for learned high relative degree system dynamics. In: Proceedings of the 2nd Conference on Learning for Dynamics and Control, pp. 781\u2013792 (2020)"},{"key":"9_CR14","unstructured":"Kiran, B.R., et al.: Deep reinforcement learning for autonomous driving: a survey. IEEE Transactions on Intelligent Transportation Systems (2021). (Early Access)"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Koller, T., Berkenkamp, F., Turchetta, M., Boedecker, J., Krause, A.: Learning-based model predictive control for safe exploration and reinforcement learning. arXiv preprint. arXiv:1906.12189 (2019)","DOI":"10.1109\/CDC.2018.8619572"},{"key":"9_CR16","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint. arXiv:1509.02971 (2015)"},{"key":"9_CR17","unstructured":"Liu, Z., Zhou, H., Chen, B., Zhong, S., Hebert, M., Zhao, D.: Safe model-based reinforcement learning with robust cross-entropy method. ICLR 2021 Workshop on Security and Safety in Machine Learning Systems (2021)"},{"key":"9_CR18","unstructured":"Namerikawa, T., Matsumura, F., Fujita, M.: Robust trajectory following for an uncertain robot manipulator using H$$_{\\infty }$$ synthesis. In: Proceedings of the 3rd European Control Conference, pp. 3474\u20133479 (1995)"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"Okawa, Y., Sasaki, T., Iwane, H.: Automatic exploration process adjustment for safe reinforcement learning with joint chance constraint satisfaction. In: Proceedings of the 21st IFAC World Congress, pp. 1588\u20131595 (2020)","DOI":"10.1016\/j.ifacol.2020.12.2198"},{"key":"9_CR20","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, 2nd edn. MIT Press (2018)"},{"issue":"3","key":"9_CR21","doi-asserted-by":"publisher","first-page":"4915","DOI":"10.1109\/LRA.2021.3070252","volume":"6","author":"B Thananjeyan","year":"2021","unstructured":"Thananjeyan, B., et al.: Recovery RL: safe reinforcement learning with learned recovery zones. IEEE Robot. Autom. Lett. 6(3), 4915\u20134922 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"9_CR22","unstructured":"Yang, T.Y., Rosca, J., Narasimhan, K., Ramadge, P.J.: Projection-based constrained policy optimization. In: Proceedings of the 8th International Conference on Learning Representations (2020)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26412-2_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,16]],"date-time":"2023-03-16T10:06:35Z","timestamp":1678961195000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26412-2_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031264115","9783031264122"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26412-2_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"17 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Grenoble","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","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":"19 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2022.ecmlpkdd.org\/","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":"1060","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":"236","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":"3-4","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":"3-4","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)"}},{"value":"17 demo track papers have been accepted from 28 submissions","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}