{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T18:14:43Z","timestamp":1742926483353,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":18,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819916382"},{"type":"electronic","value":"9789819916399"}],"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\/978-981-99-1639-9_53","type":"book-chapter","created":{"date-parts":[[2023,4,14]],"date-time":"2023-04-14T07:02:39Z","timestamp":1681455759000},"page":"634-646","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Variance Reduction for\u00a0Deep Q-Learning Using Stochastic Recursive Gradient"],"prefix":"10.1007","author":[{"given":"Haonan","family":"Jia","sequence":"first","affiliation":[]},{"given":"Xiao","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Zeng","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Xiaohui","family":"Yan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,4,15]]},"reference":[{"key":"53_CR1","unstructured":"Agarwal, A., Bottou, L.: A lower bound for the optimization of finite sums. In: Proceedings of the 32nd International Conference on Machine Learning, pp. 78\u201386 (2015)"},{"key":"53_CR2","unstructured":"Anschel, O., Baram, N., Shimkin, N.: Averaged-DQN: variance reduction and sta- bilization for deep reinforcement learning. In: Proceedings of the 34th International Conference on Machine Learning, pp. 176\u2013185 (2017)"},{"key":"53_CR3","unstructured":"Defazio, A., Bach, F., Lacoste-Julien, S.: SAGA: a fast incremental gradient method with support for non-strongly convex composite objectives. In: Advances in Neural Information Processing Systems, vol. 27, pp. 1646\u20131654 (2014)"},{"key":"53_CR4","unstructured":"Du, S.S., Chen, J., Li, L., Xiao, L., Zhou, D.: Stochastic variance reduction methods for policy evaluation. In: Proceedings of the 34th International Conference on Machine Learning, pp. 1049\u20131058 (2017)"},{"key":"53_CR5","unstructured":"Johnson, R., Zhang, T.: Accelerating stochastic gradient descent using predictive variance reduction. In: Advances in Neural Information Processing Systems, vol. 26, pp. 315\u2013323 (2013)"},{"key":"53_CR6","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"53_CR7","unstructured":"Li, B., Ma, M., Giannakis, G.B.: On the convergence of SARAH and beyond. arXiv:1906.02351 (2019)"},{"key":"53_CR8","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. arXiv:1312.5602 (2013)"},{"issue":"7540","key":"53_CR9","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":"53_CR10","unstructured":"Nguyen, L.M., Liu, J., Scheinberg, K., Tak\u00e1\u010d: SARAH: a novel method for machine learning problems using stochastic recursive gradient. In: Proceedings of the 34th International Conference on Machine Learning, pp. 2613\u20132621 (2017)"},{"key":"53_CR11","unstructured":"Papini, M., Binaghi, D., Canonaco, G., Pirotta, M., Restelli, M.: Stochastic variance-reduced policy gradient. In: Proceedings of the 35th International Conference on Machine Learning, pp. 4023\u20134032 (2018)"},{"key":"53_CR12","unstructured":"Romoff, J., Henderson, P., Pich\u00e9, A., Francois-Lavet, V., Pineau, J.: Reward estimation for variance reduction in deep reinforcement learning. arXiv preprint arXiv:1805.03359 (2018)"},{"key":"53_CR13","unstructured":"Roux, N.L., Schmidt, M., Bach, F.R.: A stochastic gradient method with an exponential convergence rate for finite training sets. In: Advances in Neural Information Processing Systems, vol. 25, pp. 2663\u20132671 (2012)"},{"key":"53_CR14","unstructured":"Sabry, M., Khalifa, A.M.A.: On the reduction of variance and overestimation of deep Q-learning. arXiv preprint arXiv:1910.05983 (2019)"},{"key":"53_CR15","unstructured":"Xu, P., Gao, F., Gu, Q.: An improved convergence analysis of stochastic variance reduced policy gradient. In: Proceedings of the 35th Conference on Uncertainty in Artificial Intelligence, p. 191 (2019)"},{"key":"53_CR16","unstructured":"Xu, P., Gao, F., Gu, Q.: Sample efficient policy gradient methods with recursive variance reduction. In: Proceedings of the 8th International Conference on Learning Representations (2020)"},{"key":"53_CR17","unstructured":"Xu, T., Liu, Q., Peng, J.: Stochastic variance reduction for policy gradient estimation. arXiv:1710.06034 (2017)"},{"key":"53_CR18","unstructured":"Zhao, W.Y., Peng, J.: Stochastic variance reduction for deep Q-learning. In: Proceedings of the 18th International Conference on Autonomous Agents and Multi- Agent Systems, pp. 2318\u20132320 (2019)"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-1639-9_53","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,14]],"date-time":"2023-04-14T07:43:50Z","timestamp":1681458230000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-1639-9_53"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819916382","9789819916399"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-1639-9_53","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"15 April 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":"New Delhi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"22 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2022.apnns.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":"Easy Chair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"810","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":"359","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":"44% - 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":"2.65","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"ICONIP 2022 consists of a two-volume set, LNCS & CCIS, which includes 146 and 213 papers","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)"}}]}}