{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T10:09:38Z","timestamp":1764238178869,"version":"3.40.4"},"publisher-location":"Cham","reference-count":14,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030461324"},{"type":"electronic","value":"9783030461331"}],"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"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-46133-1_1","type":"book-chapter","created":{"date-parts":[[2020,4,30]],"date-time":"2020-04-30T07:08:58Z","timestamp":1588230538000},"page":"3-18","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Deep Ordinal Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Alexander","family":"Zap","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tobias","family":"Joppen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Johannes","family":"F\u00fcrnkranz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,4,30]]},"reference":[{"key":"1_CR1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14125-6","volume-title":"Preference Learning","year":"2011","unstructured":"F\u00fcrnkranz, J., H\u00fcllermeier, E. (eds.): Preference Learning. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-14125-6"},{"key":"1_CR2","unstructured":"Gilbert, H., Weng, P.: Quantile reinforcement learning. CoRR abs\/1611.00862 (2016)"},{"key":"1_CR3","unstructured":"Hasselt, H.V., Guez, A., Silver, D.: Deep reinforcement learning with double Q-learning. In: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, AAAI 2016, pp. 2094\u20132100. AAAI Press (2016)"},{"key":"1_CR4","unstructured":"Joppen, T., F\u00fcrnkranz, J.: Ordinal Monte Carlo tree search. CoRR abs\/1901.04274 (2019)"},{"key":"1_CR5","unstructured":"Lin, L.J.: Reinforcement learning for robots using neural networks. Ph.D. thesis, Carnegie Mellon University, Pittsburgh, PA, USA (1992). uMI Order No. GAX93-22750"},{"key":"1_CR6","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. CoRR abs\/1312.5602 (2013)"},{"issue":"7540","key":"1_CR7","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":"1_CR8","series-title":"Adaptive Computation and Machine Learning","volume-title":"Reinforcement Learning - An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning - An Introduction. Adaptive Computation and Machine Learning, 2nd edn. MIT Press, Cambridge (2018)","edition":"2"},{"key":"1_CR9","first-page":"279","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8, 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Weng, P.: Markov decision processes with ordinal rewards: reference point-based preferences. In: Proceedings of the 21st International Conference on Automated Planning and Scheduling (ICAPS 2011), Freiburg, Germany. AAAI Press (2011)","DOI":"10.1609\/icaps.v21i1.13448"},{"key":"1_CR11","unstructured":"Weng, P.: Ordinal decision models for Markov decision processes. In: Proceedings of the 20th European Conference on Artificial Intelligence (ECAI 2012), pp. 828\u2013833. IOS Press, Montpellier (2012)"},{"key":"1_CR12","unstructured":"Weng, P., Busa-Fekete, R., H\u00fcllermeier, E.: Interactive q-learning with ordinal rewards and unreliable tutor. In: Proceedings of the ECML\/PKDD-13 Workshop on Reinforcement Learning from Generalized Feedback: Beyond Numeric Rewards (2013)"},{"issue":"136","key":"1_CR13","first-page":"1","volume":"18","author":"C Wirth","year":"2017","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\u201346 (2017)","journal-title":"J. Mach. Learn. Res."},{"key":"1_CR14","unstructured":"Zap, A.: Ordinal reinforcement learning. Master\u2019s thesis, Technische Universit\u00e4t Darmstadt (2019, to appear)"}],"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\/978-3-030-46133-1_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T22:03:30Z","timestamp":1745964210000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-46133-1_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030461324","9783030461331"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-46133-1_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"30 April 2020","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":"W\u00fcrzburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ecmlpkdd2019.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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"733","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":"130","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":"18% - 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":"3.04","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":"5.3","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":"ECML PKDD Workshops Information: single-blind review, submissions: 200, full papers accepted: 70, short papers accepted: 46","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)"}}]}}