{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:27:18Z","timestamp":1767338838589,"version":"3.44.0"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030864859"},{"type":"electronic","value":"9783030864866"}],"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\/978-3-030-86486-6_3","type":"book-chapter","created":{"date-parts":[[2021,9,9]],"date-time":"2021-09-09T15:25:48Z","timestamp":1631201148000},"page":"35-50","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Knowledge Infused Policy Gradients with\u00a0Upper Confidence Bound for\u00a0Relational Bandits"],"prefix":"10.1007","author":[{"given":"Kaushik","family":"Roy","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manas","family":"Gaur","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amit","family":"Sheth","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,10]]},"reference":[{"key":"3_CR1","unstructured":"Langford, J., Zhang, T.: The epoch-greedy algorithm for multi-armed bandits with side information. In: Advances in Neural Information Processing Systems, vol. 20, pp. 817\u2013824 (2007)"},{"key":"3_CR2","unstructured":"Zhou, L.: A survey on contextual multi-armed bandits. arXiv preprint arXiv:1508.03326 (2015)"},{"issue":"1","key":"3_CR3","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/0196-8858(85)90002-8","volume":"6","author":"TL Lai","year":"1985","unstructured":"Lai, T.L., Robbins, H.: Asymptotically efficient adaptive allocation rules. Adv. Appl. Math. 6(1), 4\u201322 (1985)","journal-title":"Adv. Appl. Math."},{"issue":"3\/4","key":"3_CR4","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":"3_CR5","unstructured":"Chapelle, O., Li, L.: An empirical evaluation of Thompson sampling. In: Advances in Neural Information Processing Systems, pp. 2249\u20132257 (2011)"},{"issue":"11","key":"3_CR6","doi-asserted-by":"publisher","first-page":"3698","DOI":"10.4249\/scholarpedia.3698","volume":"5","author":"J Peters","year":"2010","unstructured":"Peters, J., Bagnell, J.A.: Policy gradient methods. Scholarpedia 5(11), 3698 (2010)","journal-title":"Scholarpedia"},{"key":"3_CR7","unstructured":"Roy, K., Zhang, Q., Gaur, M., Sheth, A.: Knowledge infused policy gradients for adaptive pandemic control. arXiv preprint arXiv:2102.06245 (2021)"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Kakadiya, A., Natarajan, S., Ravindran, B.: Relational boosted bandits (2020)","DOI":"10.1609\/aaai.v35i13.17439"},{"issue":"1","key":"3_CR9","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1137\/S0097539701398375","volume":"32","author":"P Auer","year":"2002","unstructured":"Auer, P., Cesa-Bianchi, N., Freund, Y., Schapire, R.E.: The nonstochastic multiarmed bandit problem. SIAM J. Comput. 32(1), 48\u201377 (2002)","journal-title":"SIAM J. Comput."},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Kersting, K., Driessens, K.: Non-parametric policy gradients: a unified treatment of propositional and relational domains. In: Proceedings of the 25th International Conference on Machine Learning, pp. 456\u2013463 (2008)","DOI":"10.1145\/1390156.1390214"},{"issue":"1\u20132","key":"3_CR11","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1016\/S0004-3702(98)00034-4","volume":"101","author":"H Blockeel","year":"1998","unstructured":"Blockeel, H., De Raedt, L.: Top-down induction of first-order logical decision trees. Artif. Intell. 101(1\u20132), 285\u2013297 (1998)","journal-title":"Artif. Intell."},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Odom, P., Khot, T., Porter, R., Natarajan, S.: Knowledge-based probabilistic logic learning. In: Twenty-Ninth AAAI Conference on Artificial Intelligence (2015)","DOI":"10.1609\/aaai.v29i1.9690"},{"key":"3_CR13","unstructured":"Hazan, E., Rakhlin, A., Bartlett, P.L.: Adaptive online gradient descent. In: Advances in Neural Information Processing Systems, pp. 65\u201372 (2008)"},{"issue":"324","key":"3_CR14","first-page":"1416","volume":"63","author":"DB Peizer","year":"1968","unstructured":"Peizer, D.B., Pratt, J.W.: A normal approximation for binomial, F, beta, and other common, related tail probabilities, I. J. Am. Stat. Assoc. 63(324), 1416\u20131456 (1968)","journal-title":"J. Am. Stat. Assoc."},{"issue":"6","key":"3_CR15","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/BF01087176","volume":"32","author":"VV Buldygin","year":"1980","unstructured":"Buldygin, V.V., Kozachenko, Y.V.: Sub-Gaussian random variables. Ukr. Math. J. 32(6), 483\u2013489 (1980)","journal-title":"Ukr. Math. J."},{"issue":"1","key":"3_CR16","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1080\/00031305.2014.975842","volume":"69","author":"JE Cohen","year":"2015","unstructured":"Cohen, J.E.: Markov\u2019s inequality and Chebyshev\u2019s inequality for tail probabilities: a sharper image. Am. Stat. 69(1), 5\u20137 (2015)","journal-title":"Am. Stat."},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Hayes, A.L., Das, M., Odom, P., Natarajan, S.: User friendly automatic construction of background knowledge: mode construction from ER diagrams. In: Proceedings of the Knowledge Capture Conference, pp. 1\u20138 (2017)","DOI":"10.1145\/3148011.3148027"},{"key":"3_CR18","unstructured":"Motl, J., Schulte, O.: The CTU prague relational learning repository. arXiv preprint arXiv:1511.03086 (2015)"},{"key":"3_CR19","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.smhl.2018.07.007","volume":"9","author":"DS Dhami","year":"2018","unstructured":"Dhami, D.S., Kunapuli, G., Das, M., Page, D., Natarajan, S.: Drug-drug interaction discovery: kernel learning from heterogeneous similarities. Smart Health 9, 88\u2013100 (2018)","journal-title":"Smart Health"},{"key":"3_CR20","unstructured":"Dhami, D.S., Yan, S., Kunapuli, G., Natarajan, S.: Non-parametric learning of Gaifman models. arXiv preprint arXiv:2001.00528 (2020)"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Mihalkova, L., Mooney, R.J.: Bottom-up learning of Markov logic network structure. In: Proceedings of the 24th International Conference on Machine Learning, pp. 625\u2013632 (2007)","DOI":"10.1145\/1273496.1273575"},{"issue":"5","key":"3_CR22","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1145\/3191513","volume":"61","author":"T Mitchell","year":"2018","unstructured":"Mitchell, T., et al.: Never-ending learning. Commun. ACM 61(5), 103\u2013115 (2018)","journal-title":"Commun. ACM"},{"key":"3_CR23","unstructured":"Chung, W., Thomas, V., Machado, M.C., Roux, N.L.: Beyond variance reduction: understanding the true impact of baselines on policy optimization. arXiv preprint arXiv:2008.13773 (2020)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86486-6_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T22:04:55Z","timestamp":1757369095000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86486-6_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030864859","9783030864866"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86486-6_3","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":"10 September 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":"Bilbao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2021","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":"ecml2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2021.ecmlpkdd.org\/","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":"869","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":"210","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":"24% - 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":"3-4","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":"3-9","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":"The conference was held online 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)"}}]}}