{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T07:37:11Z","timestamp":1743061031690,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":16,"publisher":"Springer Singapore","isbn-type":[{"type":"print","value":"9789811590306"},{"type":"electronic","value":"9789811590313"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","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":[[2020]]},"DOI":"10.1007\/978-981-15-9031-3_11","type":"book-chapter","created":{"date-parts":[[2020,9,25]],"date-time":"2020-09-25T07:04:29Z","timestamp":1601017469000},"page":"120-131","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Configurable off-Policy Evaluation with Key State-Based Bias Constraints in AI Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Shuoru","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiqiang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"He","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjia","family":"Niu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Endong","family":"Tong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Long","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minglu","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,9,22]]},"reference":[{"issue":"456","key":"11_CR1","doi-asserted-by":"publisher","first-page":"1410","DOI":"10.1198\/016214501753382327","volume":"96","author":"SA Murphy","year":"2001","unstructured":"Murphy, S.A., van der Laan, M.J., Robins, J.M.: Marginal mean models for dynamic regimes. J. Am. Stat. Assoc. 96(456), 1410\u20131423 (2001)","journal-title":"J. Am. Stat. Assoc."},{"issue":"2","key":"11_CR2","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1515\/jci-2013-0007","volume":"2","author":"M Petersen","year":"2014","unstructured":"Petersen, M., Schwan, J., Gruber, S., Blaser, N., Schomaker, M., van der Lan, M.: Targeted maximum likelihood estimation for dynamic and static longitudinal marginal structural working models. J. Causal Inference 2(2), 147\u2013185 (2014)","journal-title":"J. Causal Inference"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Theocharous, G., Thomas, P.S., Ghavamzadeh, M.: Personalized ad recommendation systems for life-time value optimization with guarantees. In: Proceedings of the 24th International Conference on Artificial Intelligence, IJCAI 2015, pp. 1806\u20131812. AAAI Press (2015)","DOI":"10.1145\/2740908.2741998"},{"key":"11_CR4","unstructured":"Hoiles, W., Van Der Schaar, M.: Bounded off-policy evaluation with missing data for course recommendation and curriculum design. In: Proceedings of the 33rd International Conference on International Conference on Machine Learning \u2013 Vol. 48, ICML2016, pp. 1596\u20131604. JMLR.org (2016)"},{"key":"11_CR5","unstructured":"Jiang, N., Li, L.: Doubly Robust Off-policy Value Evaluation for Reinforcement Learning. arXiv e-prints, art. arXiv:1511.03722 , (2015)"},{"issue":"2","key":"11_CR6","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1287\/mnsc.1060.0614","volume":"53","author":"S Mannor","year":"2007","unstructured":"Mannor, S., Simester, D., Sun, P., Tsitsiklis, J.N.: Bias and variance approximation in value function estimates. Manage. Sci. 53(2), 308\u2013322 (2007). https:\/\/doi.org\/10.1287\/mnsc.1060.0614","journal-title":"Manage. Sci."},{"issue":"1","key":"11_CR7","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1093\/biomet\/70.1.41","volume":"70","author":"PR Rosenbaum","year":"1983","unstructured":"Rosenbaum, P.R., Rubin, D.B.: The central role of the propensity score in observational studies for causal effects. Biometrika 70(1), 41\u201355 (1983). https:\/\/doi.org\/10.1093\/biomet\/70.1.41","journal-title":"Biometrika"},{"key":"11_CR8","unstructured":"Precup, D.: Temporal abstraction in reinforcement learning. PhD thesis, University of Massachusetts Amherst, 2000. https:\/\/scholarworks.umass.edu\/dissertations\/AAI9978540"},{"key":"11_CR9","unstructured":"Precup, D., Sutton, R.S., Singh, S.P.: Eligibility traces for off-policy policy evaluation. In: Proceedings of the Seventeenth International Conference on Machine Learning, ICML 2000, pp. 759\u2013766, San Francisco, CA, USA (2000). ISBN 1-55860-707-2"},{"key":"11_CR10","unstructured":"Farajtabar, M., Chow, Y., Ghavamzadeh, M.: More robust doubly robust off-policy evaluation. CoRR, abs\/1802.03493, 2018"},{"key":"11_CR11","unstructured":"Thomas, P., Brunskill, E.: Data-efficient off-policy policy evaluation for reinforcement learning. In: Balcan, M.F., Weinberger, K.Q., (eds.), Proceedings of The 33rd International Conference on Machine Learning, vol. 48 of Proceedings of Machine Learning Research, pp. 2139\u20132148, New York, USA (2016.)"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Thomas, Philip S., Theocharous, G., Ghavamzadeh, M.: High confidence off-policy evaluation. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), (2015)","DOI":"10.1609\/aaai.v29i1.9541"},{"key":"11_CR13","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"ML Puterman","year":"2014","unstructured":"Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. Wiley, New York (2014)"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Han, J., Pei, J., Yin, Y.: Mining frequent patterns without candidate generation. In: Chen, W., Naughton, J., Bernstein, P.A., editors, 2000 ACM SIGMOD International Conference on Management of Data, pp. 1\u201312. ACM Press (2000)","DOI":"10.1145\/335191.335372"},{"key":"11_CR15","unstructured":"Hanna, J.P, Niekum, S., Stone, P., et al.: Importance sampling policy evaluation with an estimated behavior policy[C]. In: International Conference on Machine Learning, pp. 2605\u20132613 (2019)"},{"key":"11_CR16","unstructured":"Bibaut, AF., Malenica, I., Vlassis, N., et al.: More efficient off-policy evaluation through regularized targeted learning.[C]. In: International Conference on Machine Learning, pp. 654\u2013663 (2019)"}],"container-title":["Communications in Computer and Information Science","Security and Privacy in Social Networks and Big Data"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-15-9031-3_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,20]],"date-time":"2022-11-20T11:15:21Z","timestamp":1668942921000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-981-15-9031-3_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9789811590306","9789811590313"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-981-15-9031-3_11","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"22 September 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SocialSec","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Security and Privacy in Social Networks and Big Data","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","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":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"socialsec2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/nsclab.org\/socialsec2020\/","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"111","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":"38","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":"34% - 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":"3","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":"5.6","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)"}}]}}