{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T15:36:26Z","timestamp":1743003386450,"version":"3.40.3"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030041816"},{"type":"electronic","value":"9783030041823"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-04182-3_49","type":"book-chapter","created":{"date-parts":[[2018,11,17]],"date-time":"2018-11-17T10:19:48Z","timestamp":1542449988000},"page":"560-570","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Accurate Q-Learning"],"prefix":"10.1007","author":[{"given":"Zhihui","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yubin","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinghong","family":"Ling","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,11,18]]},"reference":[{"issue":"2\u20133","key":"49_CR1","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1023\/A:1013689704352","volume":"47","author":"P Auer","year":"2002","unstructured":"Auer, P., Cesa-Bianchi, N., Fischer, P.: Finite-time analysis of the multiarmed bandit problem. Mach. Learn. 47(2\u20133), 235\u2013256 (2002)","journal-title":"Mach. Learn."},{"key":"49_CR2","unstructured":"Azar, M.G., Munos, R., Ghavamzadeh, M., Kappen, H.J.: Speedy Q-learning. In: Proceedings of the 24th International Conference on Neural Information Processing Systems, pp. 2411\u20132419. Curran Associates Inc. (2011)"},{"key":"49_CR3","volume-title":"Dynamic Programming","author":"R Bellman","year":"2013","unstructured":"Bellman, R.: Dynamic Programming. Courier Corporation, North Chelmsford (2013)"},{"issue":"1","key":"49_CR4","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1137\/17M1122815","volume":"56","author":"DP Bertsekas","year":"2018","unstructured":"Bertsekas, D.P.: Stable optimal control and semicontractive dynamic programming. SIAM J. Control Optim. 56(1), 231\u2013252 (2018)","journal-title":"SIAM J. Control Optim."},{"key":"49_CR5","unstructured":"DEramo, C., Restelli, M., Nuara, A.: Estimating maximum expected value through gaussian approximation. In: ICML, pp. 1032\u20131040 (2016)"},{"key":"49_CR6","first-page":"1","volume":"5","author":"E Even-Dar","year":"2003","unstructured":"Even-Dar, E., Mansour, Y.: Learning rates for Q-learning. JMLR 5, 1\u201325 (2003)","journal-title":"JMLR"},{"key":"49_CR7","unstructured":"van Hasselt, H.P.: Double Q-learning. In: NIPS, pp. 2613\u20132621 (2010)"},{"key":"49_CR8","unstructured":"van Hasselt, H.P.: Insights in reinforcement learning: formal analysis and empirical evaluation of temporal-difference learning algorithms. Ph.D. thesis, Utrecht University, Netherlands (2011)"},{"key":"49_CR9","unstructured":"Kearns, M., Singh, S.: Finite-sample convergence rates for Q-learning and indirect algorithms. In: NIPS, pp. 996\u20131002 (1999)"},{"key":"49_CR10","doi-asserted-by":"crossref","unstructured":"Lee, D., Powell, W.B.: An intelligent battery controller using bias-corrected Q-learning. In: Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence, 22\u201326 July 2012, Toronto, Ontario, Canada, pp. 316\u2013322 (2012)","DOI":"10.1609\/aaai.v26i1.8164"},{"key":"49_CR11","unstructured":"Littman, M.L., Szepesv\u00e1ri, C.: A generalized reinforcement-learning model: convergence and applications. In: ICML, vol. 96, pp. 310\u2013318 (1996)"},{"key":"49_CR12","doi-asserted-by":"crossref","unstructured":"Pandey, S., Chakrabarti, D., Agarwal, D.: Multi-armed bandit problems with dependent arms. In: Proceedings of the 24th International Conference on Machine Learning, pp. 721\u2013728. ACM (2007)","DOI":"10.1145\/1273496.1273587"},{"issue":"3","key":"49_CR13","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1023\/A:1007678930559","volume":"38","author":"S Singh","year":"2000","unstructured":"Singh, S., Jaakkola, T., Littman, M.L., Szepesv\u00e1ri, C.: Convergence results for single-step on-policy reinforcement-learning algorithms. Mach. Learn. 38(3), 287\u2013308 (2000)","journal-title":"Mach. Learn."},{"key":"49_CR14","volume-title":"Reinforcement Learning: An introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An introduction, vol. 1. MIT Press, Cambridge (1998)"},{"key":"49_CR15","unstructured":"Szepesv\u00e1ri, C.: The asymptotic convergence-rate of Q-learning. In: NIPS, pp. 1064\u20131070 (1997)"},{"issue":"4","key":"49_CR16","first-page":"233","volume":"15","author":"CJ Watkins","year":"1989","unstructured":"Watkins, C.J.: Learning from delayed rewards. Robot. Auton. Syst. 15(4), 233\u2013235 (1989)","journal-title":"Robot. Auton. Syst."},{"key":"49_CR17","series-title":"Adaptation, Learning, and Optimization","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3","volume-title":"Reinforcement Learning","author":"M Wiering","year":"2012","unstructured":"Wiering, M., Van Otterlo, M.: Reinforcement Learning. Adaptation, Learning, and Optimization, vol. 12. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-27645-3"},{"issue":"1","key":"49_CR18","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1007\/s10479-012-1128-z","volume":"208","author":"H Yu","year":"2013","unstructured":"Yu, H., Bertsekas, D.P.: Q-learning and policy iteration algorithms for stochastic shortest path problems. Ann. Oper. Res. 208(1), 95\u2013132 (2013)","journal-title":"Ann. Oper. Res."},{"key":"49_CR19","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Pan, Z., Kochenderfer, M.J.: Weighted double Q-learning. In: IJCAI, pp. 3455\u20133461 (2017)","DOI":"10.24963\/ijcai.2017\/483"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-04182-3_49","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T15:23:55Z","timestamp":1709825035000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-04182-3_49"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030041816","9783030041823"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-04182-3_49","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"18 November 2018","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":"Siem Reap","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cambodia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 December 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conference.cs.cityu.edu.hk\/iconip\/","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":"575","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":"401","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":"70% - 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","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":"6","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)"}}]}}