{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T16:02:51Z","timestamp":1743004971312,"version":"3.40.3"},"publisher-location":"Cham","reference-count":13,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031199066"},{"type":"electronic","value":"9783031199073"}],"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\/978-3-031-19907-3_33","type":"book-chapter","created":{"date-parts":[[2023,1,13]],"date-time":"2023-01-13T06:07:32Z","timestamp":1673590052000},"page":"343-352","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Monte Carlo Bias Correction in\u00a0Q-Learning"],"prefix":"10.1007","author":[{"given":"Dimitris","family":"Papadimitriou","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,1,14]]},"reference":[{"key":"33_CR1","unstructured":"D\u2019Eramo, C., Restelli, M., Nuara, A.: Estimating maximum expected value through gaussian approximation. In: International Conference on Machine Learning, pp. 1032\u20131040 (2016)"},{"key":"33_CR2","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1613\/jair.639","volume":"13","author":"TG Dietterich","year":"2000","unstructured":"Dietterich, T.G.: Hierarchical reinforcement learning with the MAXQ value function decomposition. J. Artif. Intell. Res. 13, 227\u2013303 (2000)","journal-title":"J. Artif. Intell. Res."},{"key":"33_CR3","unstructured":"S. Fujimoto, H. Hoof, and D. Meger. Addressing function approximation error in actor-critic methods. In International Conference on Machine Learning, pages 1587\u20131596. PMLR, 2018"},{"key":"33_CR4","doi-asserted-by":"publisher","DOI":"10.7312\/gumb92958","volume-title":"Statistics of Extremes","author":"EJ Gumbel","year":"1958","unstructured":"Gumbel, E.J.: Statistics of Extremes. Columbia University Press, New York (1958)"},{"issue":"6","key":"33_CR5","doi-asserted-by":"publisher","first-page":"1267","DOI":"10.1007\/s10994-020-05938-9","volume":"110","author":"JP Hanna","year":"2021","unstructured":"Hanna, J.P., Niekum, S., Stone, P.: Importance sampling in reinforcement learning with an estimated behavior policy. Mach. Learn. 110(6), 1267\u20131317 (2021). https:\/\/doi.org\/10.1007\/s10994-020-05938-9","journal-title":"Mach. Learn."},{"key":"33_CR6","unstructured":"Hasselt, H.V.: Double Q-learning. In: Advances in Neural Information Processing Systems, pp. 2613\u20132621 (2010)"},{"key":"33_CR7","unstructured":"Lan, Q., Pan, Y., Fyshe, A., White, M.: Maxmin Q-learning: controlling the estimation bias of Q-learning. arXiv preprint arXiv:2002.06487 (2020)"},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Lee, D., Defourny, B., Powell, W.B.: Bias-corrected q-learning to control max-operator bias in q-learning. In: 2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL), pp. 93\u201399. IEEE (2013)","DOI":"10.1109\/ADPRL.2013.6614994"},{"issue":"3","key":"33_CR9","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1287\/mnsc.1050.0451","volume":"52","author":"JE Smith","year":"2006","unstructured":"Smith, J.E., Winkler, R.L.: The optimizer\u2019s curse: skepticism and postdecision surprise in decision analysis. Manage. Sci. 52(3), 311\u2013322 (2006)","journal-title":"Manage. Sci."},{"key":"33_CR10","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT press, Cambridge (2018)"},{"key":"33_CR11","unstructured":"Thrun, S., Schwartz, A.: Issues in using function approximation for reinforcement learning. In: Proceedings of the Fourth Connectionist Models Summer School, pp. 255\u2013263. Hillsdale, NJ (1993)"},{"issue":"3\u20134","key":"33_CR12","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF00992698","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8(3\u20134), 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"key":"33_CR13","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","Artificial General Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19907-3_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,13]],"date-time":"2023-01-13T07:07:27Z","timestamp":1673593647000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19907-3_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031199066","9783031199073"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19907-3_33","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":"14 January 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AGI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial General Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Seattle, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","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 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"agi2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/agi-conf.org\/2022\/","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":"61","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":"31","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":"2,54","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":"3,6","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"13 additional posters were included","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)"}}]}}