{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T01:54:22Z","timestamp":1743040462289,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030676636"},{"type":"electronic","value":"9783030676643"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-67664-3_28","type":"book-chapter","created":{"date-parts":[[2021,2,24]],"date-time":"2021-02-24T07:06:46Z","timestamp":1614150406000},"page":"463-478","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Interactive Multi-objective Reinforcement Learning in Multi-armed Bandits with Gaussian Process Utility Models"],"prefix":"10.1007","author":[{"given":"Diederik M.","family":"Roijers","sequence":"first","affiliation":[]},{"given":"Luisa M.","family":"Zintgraf","sequence":"additional","affiliation":[]},{"given":"Pieter","family":"Libin","sequence":"additional","affiliation":[]},{"given":"Mathieu","family":"Reymond","sequence":"additional","affiliation":[]},{"given":"Eugenio","family":"Bargiacchi","sequence":"additional","affiliation":[]},{"given":"Ann","family":"Now\u00e9","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,2,25]]},"reference":[{"key":"28_CR1","unstructured":"Agrawal, S., Goyal, N.: Analysis of Thompson sampling for the multi-armed bandit problem. In: COLT, pp. 39\u20131 (2012)"},{"issue":"2\u20133","key":"28_CR2","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1023\/A:1013689704352","volume":"47","author":"P Auer","year":"2002","unstructured":"Auer, P., Cesa-Bianchi, N., Fischer, P.: Finite-time analysis of the multiarmed bandit problem. Mach. Learn. 47(2\u20133), 235\u2013256 (2002)","journal-title":"Mach. Learn."},{"key":"28_CR3","unstructured":"Auer, P., Chiang, C.K., Ortner, R., Drugan, M.M.: Pareto front identification from stochastic bandit feedback. In: AISTATS, pp. 939\u2013947 (2016)"},{"key":"28_CR4","unstructured":"Bishop, C.M.: Pattern Recognition and Machine Learning (2006)"},{"key":"28_CR5","unstructured":"Brochu, E., Cora, V.M., De Freitas, N.: A tutorial on Bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning. arXiv:1012.2599 (2010)"},{"key":"28_CR6","doi-asserted-by":"crossref","unstructured":"Chu, W., Ghahramani, Z.: Preference learning with Gaussian processes. In: ICML, pp. 137\u2013144 (2005)","DOI":"10.1145\/1102351.1102369"},{"key":"28_CR7","doi-asserted-by":"crossref","unstructured":"Drugan, M.M., Now\u00e9, A.: Designing multi-objective multi-armed bandits algorithms: a study. In: IJCNN, pp. 1\u20138. IEEE (2013)","DOI":"10.1109\/IJCNN.2013.6707036"},{"key":"28_CR8","doi-asserted-by":"crossref","unstructured":"Drugan, M.M.: PAC models in stochastic multi-objective multi-armed bandits. In: GEC, pp. 409\u2013416 (2017)","DOI":"10.1145\/3071178.3071337"},{"issue":"1","key":"28_CR9","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1037\/0033-2909.117.1.39","volume":"117","author":"JP Forgas","year":"1995","unstructured":"Forgas, J.P.: Mood and judgment: the affect infusion model (aim). Psychol. Bull. 117(1), 39 (1995)","journal-title":"Psychol. Bull."},{"key":"28_CR10","doi-asserted-by":"crossref","unstructured":"Hotelling, H.: The generalization of Student\u2019s ratio. In: Annals of Mathematical Statistics ii, pp. 360\u2013378 (1931)","DOI":"10.1214\/aoms\/1177732979"},{"key":"28_CR11","unstructured":"Lampinen, J.: Gaussian processes with monotonicity constraint for big data (2014)"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Libin, P., Verstraeten, T., Roijers, D.M., Wang, W., Theys, K., Now\u00e9, A.: Bayesian anytime m-top exploration. In: ICTAI, pp. 1422\u20131428 (2019)","DOI":"10.1109\/ICTAI.2019.00201"},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Libin, P.J., et al.: Bayesian best-arm identification for selecting influenza mitigation strategies. In: ECML-PKDD, pp. 456\u2013471 (2018)","DOI":"10.1007\/978-3-030-10997-4_28"},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Lunn, D., Jackson, C., Best, N., Thomas, A., Spiegelhalter, D.: The BUGS Book: A Practical Introduction to Bayesian Analysis. CRC Press, Boca Raton (2012)","DOI":"10.1201\/b13613"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Rasmussen, C.E.: Gaussian processes for machine learning (2006)","DOI":"10.7551\/mitpress\/3206.001.0001"},{"key":"28_CR16","unstructured":"Riihim\u00e4ki, J., Vehtari, A.: Gaussian processes with monotonicity information. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 645\u2013652 (2010)"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Roijers, D.M.: Multi-Objective Decision-Theoretic Planning. Ph.D. thesis, University of Amsterdam (2016)","DOI":"10.1145\/3008665.3008670"},{"key":"28_CR18","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1613\/jair.3987","volume":"48","author":"DM Roijers","year":"2013","unstructured":"Roijers, D.M., Vamplew, P., Whiteson, S., Dazeley, R.: A survey of multi-objective sequential decision-making. JAIR 48, 67\u2013113 (2013)","journal-title":"JAIR"},{"key":"28_CR19","doi-asserted-by":"crossref","unstructured":"Roijers, D.M., Zintgraf, L.M., Now\u00e9, A.: Interactive Thompson sampling for multi-objective multi-armed bandits. In: Algorithmic Decision Theory, pp. 18\u201334 (2017)","DOI":"10.1007\/978-3-319-67504-6_2"},{"key":"28_CR20","unstructured":"Roijers, D.M., Zintgraf, L.M., Libin, P., Now\u00e9, A.: Interactive multi-objective reinforcement learning in multi-armed bandits for any utility function. In: ALA workshop at FAIM (2018)"},{"key":"28_CR21","unstructured":"Siegel, S.: Nonparametric statistics for the behavioral sciences (1956)"},{"issue":"3","key":"28_CR22","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1016\/j.annals.2004.01.009","volume":"31","author":"E Sirakaya","year":"2004","unstructured":"Sirakaya, E., Petrick, J., Choi, H.S.: The role of mood on tourism product evaluations. Ann. Tourism Res. 31(3), 517\u2013539 (2004)","journal-title":"Ann. Tourism Res."},{"issue":"5","key":"28_CR23","doi-asserted-by":"publisher","first-page":"832","DOI":"10.1111\/j.2041-210X.2012.00227.x","volume":"3","author":"RL Soulsby","year":"2012","unstructured":"Soulsby, R.L., Thomas, J.A.: Insect population curves: modelling and application to butterfly transect data. Methods Ecol. Evol. 3(5), 832\u2013841 (2012)","journal-title":"Methods Ecol. Evol."},{"key":"28_CR24","first-page":"99","volume":"1","author":"G Tesauro","year":"1988","unstructured":"Tesauro, G.: Connectionist learning of expert preferences by comparison training. NeurIPS 1, 99\u2013106 (1988)","journal-title":"NeurIPS"},{"issue":"3\/4","key":"28_CR25","doi-asserted-by":"publisher","first-page":"285","DOI":"10.2307\/2332286","volume":"25","author":"WR Thompson","year":"1933","unstructured":"Thompson, W.R.: On the likelihood that one unknown probability exceeds another in view of the evidence of two samples. Biometrika 25(3\/4), 285\u2013294 (1933)","journal-title":"Biometrika"},{"key":"28_CR26","unstructured":"Ustyuzhaninov, I., Kazlauskaite, I., Ek, C.H., Campbell, N.D.: Monotonic Gaussian process flow. arXiv preprint arXiv:1905.12930 (2019)"},{"key":"28_CR27","unstructured":"Wu, H., Liu, X.: Double thompson sampling for dueling bandits. In: NeurIPS, pp. 649\u2013657 (2016)"},{"key":"28_CR28","doi-asserted-by":"crossref","unstructured":"Yahyaa, S.Q., Drugan, M.M., Manderick, B.: Thompson sampling in the adaptive linear scalarized multi objective multi armed bandit. In: ICAART, pp. 55\u201365 (2015)","DOI":"10.5220\/0005184400550065"},{"key":"28_CR29","unstructured":"Zintgraf, L.M., Roijers, D.M., Linders, S., Jonker, C.M., Now\u00e9, A.: Ordered preference elicitation strategies for supporting multi-objective decision making. In: AAMAS, pp. 1477\u20131485 (2018)"},{"key":"28_CR30","unstructured":"Zoghi, M., Whiteson, S., Munos, R., De Rijke, M.: Relative upper confidence bound for the k-armed dueling bandit problem. In: ICML, pp. 10\u201318 (2014)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-67664-3_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,23]],"date-time":"2025-02-23T23:08:41Z","timestamp":1740352121000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-67664-3_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030676636","9783030676643"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-67664-3_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"25 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ghent","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Belgium","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":"14 September 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd2020.net\/","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":"945","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":"195","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":"21% - 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":"4,5","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":"4,4","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)"}},{"value":"The conference took place virtually due to the COVID-19 pandemic","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)"}}]}}