{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T19:46:36Z","timestamp":1775245596775,"version":"3.50.1"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030017705","type":"print"},{"value":"9783030017712","type":"electronic"}],"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\/978-3-030-01771-2_11","type":"book-chapter","created":{"date-parts":[[2018,10,6]],"date-time":"2018-10-06T12:43:04Z","timestamp":1538829784000},"page":"161-175","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Preference-Based Reinforcement Learning Using Dyad Ranking"],"prefix":"10.1007","author":[{"given":"Dirk","family":"Sch\u00e4fer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eyke","family":"H\u00fcllermeier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,10,7]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Akrour, R., Schoenauer, M., Sebag, M.: Preference-based policy learning. In: Proceedings of ECML\/PKDD-2011, Athens, Greece (2011)","DOI":"10.1007\/978-3-642-23780-5_11"},{"issue":"1","key":"11_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10994-017-5692-y","volume":"107","author":"P Brazdil","year":"2018","unstructured":"Brazdil, P., Giraud-Carrier, C.G.: Metalearning and algorithm selection: progress, state of the art and introduction to the 2018 special issue. Mach. Learn. 107(1), 1\u201314 (2018)","journal-title":"Mach. Learn."},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Cheng, W., F\u00fcrnkranz, J., H\u00fcllermeier, E., Park, S.H.: Preference-based policy iteration: leveraging preference learning for reinforcement learning. In: Proceedings of ECML\/PKDD-2011, Athens, Greece (2011)","DOI":"10.1007\/978-3-642-23780-5_30"},{"issue":"3","key":"11_CR4","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/s10994-008-5069-3","volume":"72","author":"C Dimitrakakis","year":"2008","unstructured":"Dimitrakakis, C., Lagoudakis, M.G.: Rollout sampling approximate policy iteration. Mach. Learn. 72(3), 157\u2013171 (2008)","journal-title":"Mach. Learn."},{"issue":"1\u20132","key":"11_CR5","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/s10994-012-5313-8","volume":"89","author":"J F\u00fcrnkranz","year":"2012","unstructured":"F\u00fcrnkranz, J., H\u00fcllermeier, E., Cheng, W., Park, S.H.: Preference-based reinforcement learning: a formal framework and a policy iteration algorithm. Mach. Learn. 89(1\u20132), 123\u2013156 (2012)","journal-title":"Mach. Learn."},{"key":"11_CR6","volume-title":"Digital Image Processing","author":"RC Gonzalez","year":"2002","unstructured":"Gonzalez, R.C., Woods, R.E.: Digital Image Processing, 2nd edn. Prentice Hall, Englewood Cliffs (2002)","edition":"2"},{"key":"11_CR7","doi-asserted-by":"publisher","first-page":"1897","DOI":"10.1016\/j.artint.2008.08.002","volume":"172","author":"E H\u00fcllermeier","year":"2008","unstructured":"H\u00fcllermeier, E., F\u00fcrnkranz, J., Cheng, W., Brinker, K.: Label ranking by learning pairwise preferences. Artif. Intell. 172, 1897\u20131917 (2008)","journal-title":"Artif. Intell."},{"key":"11_CR8","unstructured":"Lagoudakis, M., Parr, R.: Reinforcement learning as classification: leveraging modern classifiers. In: Proceedings of ICML, 20th International Conference on Machine Learning, vol. 20, pp. 424\u2013431. AAAI Press (2003)"},{"key":"11_CR9","unstructured":"Sch\u00e4fer, D., H\u00fcllermeier, E.: Plackett-Luce networks for dyad ranking. In: Workshop LWDA, Lernen, Wissen, Daten, Analysen, Potsdam, Germany (2016)"},{"key":"11_CR10","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1007\/978-3-319-23525-7_14","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"D Sch\u00e4fer","year":"2015","unstructured":"Sch\u00e4fer, D., H\u00fcllermeier, E.: Dyad ranking using a bilinear Plackett-Luce model. In: Appice, A., Rodrigues, P.P., Santos Costa, V., Gama, J., Jorge, A., Soares, C. (eds.) ECML PKDD 2015. LNCS (LNAI), vol. 9285, pp. 227\u2013242. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-23525-7_14"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Sch\u00e4fer, D., H\u00fcllermeier, E.: Dyad ranking using Plackett-Luce models based on joint feature representations. Mach. Learn. (2018)","DOI":"10.1007\/s10994-017-5694-9"},{"key":"11_CR12","unstructured":"Settles, B.: Active learning literature survey. Technical Report 1648, University of Wisconsin-Madison (2008)"},{"issue":"1","key":"11_CR13","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1023\/A:1022633531479","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":"11_CR14","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"key":"11_CR15","first-page":"1453","volume":"6","author":"I Tsochantaridis","year":"2005","unstructured":"Tsochantaridis, I., Joachims, T., Hofmann, T., Altun, Y.: Large margin methods for structured and interdependent output variables. J. Mach. Learn. Res. 6, 1453\u20131484 (2005)","journal-title":"J. Mach. Learn. Res."},{"key":"11_CR16","unstructured":"Vembu, S., G\u00e4rtner, T.: Label ranking: a survey. In: F\u00fcrnkranz, J., H\u00fcllermeier, E., (eds.) Preference Learning. Springer (2010)"},{"issue":"4","key":"11_CR17","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"issue":"3","key":"11_CR18","first-page":"272","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8(3), 272\u2013292 (1992)","journal-title":"Mach. Learn."},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Wirth, C., Akrour, R., Neumann, G., F\u00fcrnkranz, J.: A survey of preference-based reinforcement learning methods. J. Mach. Learn. Res. 18, 136:1\u2013136:46 (2017)","DOI":"10.1609\/aaai.v30i1.10269"},{"key":"11_CR20","unstructured":"Xiao, H., Rasul, K., Vollgraf, R.: Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms (2017), arXiv:1708.07747"},{"issue":"15","key":"11_CR21","doi-asserted-by":"publisher","first-page":"1982","DOI":"10.1002\/sim.3618","volume":"28","author":"Y Zhao","year":"2009","unstructured":"Zhao, Y., Kosorok, M.R., Zeng, D.: Reinforcement learning design for cancer clinical trials. Stat. Med. 28(15), 1982\u20131998 (2009)","journal-title":"Stat. Med."}],"container-title":["Lecture Notes in Computer Science","Discovery Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01771-2_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T18:47:50Z","timestamp":1775242070000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01771-2_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030017705","9783030017712"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01771-2_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"7 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Discovery Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Limassol","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cyprus","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":"29 October 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 October 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dis2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.cyprusconferences.org\/ds2018\/","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":"71","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":"30","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":"42% - 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":"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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}