{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T14:25:24Z","timestamp":1784643924288,"version":"3.55.0"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030316532","type":"print"},{"value":"9783030316549","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[[2019]]},"DOI":"10.1007\/978-3-030-31654-9_48","type":"book-chapter","created":{"date-parts":[[2019,10,31]],"date-time":"2019-10-31T00:05:31Z","timestamp":1572480331000},"page":"562-572","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Exponential Moving Averaged Q-Network for DDPG"],"prefix":"10.1007","author":[{"given":"Xiangxiang","family":"Shen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuanhuan","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yekun","family":"Chai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinwen","family":"Hou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,10,31]]},"reference":[{"key":"48_CR1","unstructured":"Anschel, O., Baram, N., Shimkin, N.: Averaged-DQN: variance reduction and stabilization for deep reinforcement learning. In: ICML (2017)"},{"key":"48_CR2","doi-asserted-by":"crossref","unstructured":"Awheda, M.D., Schwartz, H.M.: Exponential moving average Q-learning algorithm. In: 2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL), pp. 31\u201338. IEEE (2013)","DOI":"10.1109\/ADPRL.2013.6614986"},{"issue":"3","key":"48_CR3","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/s10462-015-9447-5","volume":"45","author":"MD Awheda","year":"2016","unstructured":"Awheda, M.D., Schwartz, H.M.: Exponential moving average based multiagent reinforcement learning algorithms. Artif. Intell. Rev. 45(3), 299\u2013332 (2016)","journal-title":"Artif. Intell. Rev."},{"key":"48_CR4","unstructured":"Brockman, G., et al.: Openai gym (2016)"},{"issue":"4","key":"48_CR5","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1016\/0921-8890(95)00026-C","volume":"15","author":"BJA Krose","year":"1995","unstructured":"Krose, B.J.A.: Learning from delayed rewards. Robot. Auton. Syst. 15(4), 233\u2013235 (1995)","journal-title":"Robot. Auton. Syst."},{"key":"48_CR6","unstructured":"Leibfried, F., Graumoya, J., Bouammar, H.: An information-theoretic optimality principle for deep reinforcement learning. arXiv Artificial Intelligence (2017)"},{"key":"48_CR7","unstructured":"Levine, N., Zahavy, T., Mankowitz, D.J., Tamar, A., Mannor, S.: Shallow updates for deep reinforcement learning. In: Neural Information Processing Systems, pp. 3135\u20133145 (2017)"},{"key":"48_CR8","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. In: International Conference on Learning Representations (2016)"},{"key":"48_CR9","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. arXiv Learning (2013)"},{"issue":"7540","key":"48_CR10","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"},{"key":"48_CR11","unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.A.: Deterministic policy gradient algorithms. In: ICML (2014)"},{"issue":"1","key":"48_CR12","first-page":"9","volume":"3","author":"RS Sutton","year":"1988","unstructured":"Sutton, R.S.: Learning to predict by the methods of temporal differences. Mach. Learn. 3(1), 9\u201344 (1988)","journal-title":"Mach. Learn."},{"key":"48_CR13","first-page":"285","volume":"16","author":"RS Sutton","year":"1988","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning: an introduction. IEEE Trans. Neural Netw. 16, 285\u2013286 (1988)","journal-title":"IEEE Trans. Neural Netw."},{"key":"48_CR14","unstructured":"Thrun, S., Schwartz, A.: Issues in using function approximation for reinforcement learning. In: Proceedings of the 1993 Connectionist Models Summer School Hillsdale, NJ. Lawrence Erlbaum (1993)"},{"issue":"5","key":"48_CR15","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1109\/9.580874","volume":"42","author":"JN Tsitsiklis","year":"1997","unstructured":"Tsitsiklis, J.N., Van Roy, B.: An analysis of temporal-difference learning with function approximation. IEEE Trans. Autom. Control 42(5), 674\u2013690 (1997)","journal-title":"IEEE Trans. Autom. Control"},{"key":"48_CR16","doi-asserted-by":"crossref","unstructured":"Van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double Q-learning. In: International Conference on Artificial Intelligence, pp. 2094\u20132100 (2016)","DOI":"10.1609\/aaai.v30i1.10295"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-31654-9_48","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:12:03Z","timestamp":1730333523000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-31654-9_48"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030316532","9783030316549"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-31654-9_48","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"31 October 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xi'an","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":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 November 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 November 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.prcv2019.com\/en\/index.html","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":"412","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":"165","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":"40% - 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":"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)"}}]}}