{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T02:31:54Z","timestamp":1742956314523,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":21,"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_15","type":"book-chapter","created":{"date-parts":[[2023,11,14]],"date-time":"2023-11-14T16:08:09Z","timestamp":1699978089000},"page":"191-203","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Impulsive Accelerated Reinforcement Learning for\u00a0$$H_\\infty $$ Control"],"prefix":"10.1007","author":[{"given":"Yan","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shixian","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,15]]},"reference":[{"issue":"7","key":"15_CR1","doi-asserted-by":"publisher","first-page":"4393","DOI":"10.1109\/TSMC.2023.3247888","volume":"53","author":"X Yang","year":"2023","unstructured":"Yang, X., Xu, M., Wei, Q.: Adaptive dynamic programming for nonlinear-constrained $$H_\\infty $$ control. IEEE Trans. Syst. Man Cybern. Syst. 53(7), 4393\u20134403 (2023)","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"issue":"1","key":"15_CR2","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1109\/TCYB.2014.2319577","volume":"45","author":"B Luo","year":"2014","unstructured":"Luo, B., Wu, H.N., Huang, T.: Off-policy reinforcement learning for $$H_\\infty $$ control design. IEEE Trans. Cybern. 45(1), 65\u201376 (2014)","journal-title":"IEEE Trans. Cybern."},{"issue":"4","key":"15_CR3","doi-asserted-by":"publisher","first-page":"993","DOI":"10.1109\/TNNLS.2016.2642128","volume":"29","author":"D Wang","year":"2017","unstructured":"Wang, D., Mu, C.X., Liu, D.R., Ma, H.W.: On mixed data and event driven design for adaptive-critic-based nonlinear $$ H_\\infty $$ control. IEEE Trans. Neural Networks Learn. Syst. 29(4), 993\u20131005 (2017)","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"issue":"6","key":"15_CR4","doi-asserted-by":"publisher","first-page":"2042","DOI":"10.1109\/TNNLS.2017.2773458","volume":"29","author":"B Kiumarsi","year":"2017","unstructured":"Kiumarsi, B., Vamvoudakis, K.G., Modares, H., Lewis, F.L.: Optimal and autonomous control using reinforcement learning: a survey. IEEE Trans. Neural Networks Learn. Syst. 29(6), 2042\u20132062 (2017)","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"15_CR5","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-8176-4757-5","volume-title":"$$H_\\infty $$ Optimal Control and Related Minimax Design Problems: A Dynamic Game Approach","author":"T Ba\u015far","year":"2008","unstructured":"Ba\u015far, T., Bernhard, P.: $$H_\\infty $$ Optimal Control and Related Minimax Design Problems: A Dynamic Game Approach. Springer, Boston (2008). https:\/\/doi.org\/10.1007\/978-0-8176-4757-5"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Liang, X., Liu, Y., Chen, T., Liu, M., Yang, Q.: Federated transfer reinforcement learning for autonomous driving. In: IFederated and Transfer Learning, pp. 357\u2013371 (2022)","DOI":"10.1007\/978-3-031-11748-0_15"},{"issue":"9","key":"15_CR7","doi-asserted-by":"publisher","first-page":"2250158","DOI":"10.1142\/S0218126622501584","volume":"31","author":"JJ Stanly","year":"2022","unstructured":"Stanly, J.J., Priyadarsini, M.J.P., Parameshachari, B.D., Karimi, H.R., Gurumoorthy, S.: Deep $$Q$$-network with reinforcement learning for fault detection in cyber-physical systems. J. Circuits, Syst. Comput. 31(9), 2250158 (2022)","journal-title":"J. Circuits, Syst. Comput."},{"key":"15_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2021.101360","volume":"49","author":"Q Liu","year":"2021","unstructured":"Liu, Q., Liu, Z., Xiong, B., Xu, W., Liu, Y.: Deep reinforcement learning-based safe interaction for industrial human-robot collaboration using intrinsic reward function. Adv. Eng. Inform. 49, 101360 (2021)","journal-title":"Adv. Eng. Inform."},{"issue":"1","key":"15_CR9","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1109\/LCSYS.2020.3001241","volume":"5","author":"Y Yang","year":"2020","unstructured":"Yang, Y., Wan, Y., Zhu, J., Lewis, F.L.: $$H_\\infty $$ tracking control for linear discrete-time systems: model-free $$Q$$-learning designs. IEEE Control Syst. Lett. 5(1), 175\u2013180 (2020)","journal-title":"IEEE Control Syst. Lett."},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Vamvoudakis, K.G., Ferraz, H.: Event-triggered $$H_\\infty $$ control for unknown continuous-time linear systems using $$Q$$-learning. In: 2016 IEEE 55th Conference on Decision and Control (CDC), pp. 1376\u20131381 (2016)","DOI":"10.1109\/CDC.2016.7798458"},{"issue":"1","key":"15_CR11","first-page":"5040","volume":"22","author":"AC Wilson","year":"2021","unstructured":"Wilson, A.C., Recht, B., Jordan, M.I.: A Lyapunov analysis of accelerated methods in optimization. J. Mach. Learn. Res. 22(1), 5040\u20135073 (2021)","journal-title":"J. Mach. Learn. Res."},{"key":"15_CR12","unstructured":"Pertsch, K., Lee, Y., Lim, J.: Accelerating reinforcement learning with learned skill priors. In: Conference on Robot Learning, pp. 188\u2013204 (2021)"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Poveda, J.I., Li, N.: Robust hybrid zero-order optimization algorithms with acceleration via averaging in time. Automatica, pp. 109361 (2021)","DOI":"10.1016\/j.automatica.2020.109361"},{"issue":"12","key":"15_CR14","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1016\/j.ifacol.2022.07.371","volume":"55","author":"DE Ochoa","year":"2022","unstructured":"Ochoa, D.E., Poveda, J.I.: Accelerated continuous-time approximate dynamic programming via data-assisted hybrid control. IFAC-PapersOnLine 55(12), 561\u2013566 (2022)","journal-title":"IFAC-PapersOnLine"},{"issue":"153","key":"15_CR15","first-page":"1","volume":"17","author":"W Su","year":"2016","unstructured":"Su, W., Boyd, S., Candes, E.: A differential equation for modeling Nesterov\u2019s accelerated gradient method: theory and insights. J. Mach. Learn. Res. 17(153), 1\u201343 (2016)","journal-title":"J. Mach. Learn. Res."},{"issue":"10","key":"15_CR16","doi-asserted-by":"publisher","first-page":"3429","DOI":"10.1109\/TCYB.2017.2712188","volume":"47","author":"D Wang","year":"2017","unstructured":"Wang, D., He, H.B., Liu, D.R.: Adaptive critic nonlinear robust control: a survey. IEEE Trans. Cybern. 47(10), 3429\u20133451 (2017)","journal-title":"IEEE Trans. Cybern."},{"key":"15_CR17","doi-asserted-by":"publisher","first-page":"715","DOI":"10.1007\/s10208-013-9150-3","volume":"15","author":"OD Brendan","year":"2015","unstructured":"Brendan, O.D., Candes, E.: Adaptive restart for accelerated gradient schemes. Found. Comput. Math. 15, 715\u2013732 (2015)","journal-title":"Found. Comput. Math."},{"key":"15_CR18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-78384-0","volume-title":"Reinforcement Learning for Optimal Feedback Control","author":"R Kamalapurkar","year":"2018","unstructured":"Kamalapurkar, R., Walters, P., Rosenfeld, J., Dixon, W.: Reinforcement Learning for Optimal Feedback Control. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-78384-0"},{"issue":"5","key":"15_CR19","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1016\/0893-6080(90)90005-6","volume":"3","author":"K Hornik","year":"1990","unstructured":"Hornik, K., Stinchcombe, M., White, H.: Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks. Neural Networks 3(5), 551\u2013560 (1990)","journal-title":"Neural Networks"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Chowdhary, G., Johnson, E.: Concurrent learning for convergence in adaptive control without persistency of excitation. In: 49th IEEE Conference on Decision and Control (CDC), pp. 3674\u20133679 (2010)","DOI":"10.1109\/CDC.2010.5717148"},{"key":"15_CR21","doi-asserted-by":"publisher","unstructured":"Kokolakis, N.M.T., Vamvoudakis, K.G.: Safety-aware pursuit-evasion games in unknown environments using gaussian processes and finite-time convergent reinforcement learning. IEEE Trans. Neural Networks Learn. Syst. (2022). https:\/\/doi.org\/10.1109\/TNNLS.2022.3203977","DOI":"10.1109\/TNNLS.2022.3203977"}],"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_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T17:06:15Z","timestamp":1710349575000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8082-6_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,15]]},"ISBN":["9789819980819","9789819980826"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8082-6_15","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)"}}]}}