{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T18:23:17Z","timestamp":1744827797755,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030739584"},{"type":"electronic","value":"9783030739591"}],"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.springer.com\/tdm"},{"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.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-73959-1_15","type":"book-chapter","created":{"date-parts":[[2021,4,12]],"date-time":"2021-04-12T15:20:40Z","timestamp":1618240840000},"page":"163-179","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Synthesising Reinforcement Learning Policies Through Set-Valued Inductive Rule Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1124-0731","authenticated-orcid":false,"given":"Youri","family":"Coppens","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1521-8494","authenticated-orcid":false,"given":"Denis","family":"Steckelmacher","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4780-7461","authenticated-orcid":false,"given":"Catholijn M.","family":"Jonker","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6346-4564","authenticated-orcid":false,"given":"Ann","family":"Now\u00e9","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,4,13]]},"reference":[{"issue":"2","key":"15_CR1","doi-asserted-by":"publisher","first-page":"320","DOI":"10.1007\/s10458-008-9046-9","volume":"17","author":"AK Agogino","year":"2008","unstructured":"Agogino, A.K., Tumer, K.: Analyzing and visualizing multiagent rewards in dynamic and stochastic domains. Auton Agents Multi-Agent Syst. 17(2), 320\u2013338 (2008). https:\/\/doi.org\/10.1007\/s10458-008-9046-9","journal-title":"Auton Agents Multi-Agent Syst."},{"key":"15_CR2","doi-asserted-by":"publisher","first-page":"171058","DOI":"10.1109\/ACCESS.2020.3023394","volume":"8","author":"A Alharin","year":"2020","unstructured":"Alharin, A., Doan, T.N., Sartipi, M.: Reinforcement learning interpretation methods: a survey. IEEE Access 8, 171058\u2013171077 (2020). https:\/\/doi.org\/10.1109\/ACCESS.2020.3023394","journal-title":"IEEE Access"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Brys, T., Now\u00e9, A., Kudenko, D., Taylor, M.E.: Combining multiple correlated reward and shaping signals by measuring confidence. In: Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence, pp. 1687\u20131693. AAAI Press, Palo Alto (2014)","DOI":"10.1609\/aaai.v28i1.8998"},{"issue":"4","key":"15_CR4","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/BF00116835","volume":"3","author":"P Clark","year":"1989","unstructured":"Clark, P., Niblett, T.: The CN2 induction algorithm. Machine Learn. 3(4), 261\u2013283 (1989). https:\/\/doi.org\/10.1007\/BF00116835","journal-title":"Machine Learn."},{"key":"15_CR5","unstructured":"Coppens, Y., Efthymiadis, K., Lenaerts, T., Now\u00e9, A.: Distilling deep reinforcement learning policies in soft decision trees. In: Miller, T., Weber, R., Magazzeni, D. (eds.) Proceedings of the IJCAI 2019 Workshop on Explainable Artificial Intelligence, Macau, pp. 1\u20136 (2019)"},{"key":"15_CR6","doi-asserted-by":"publisher","unstructured":"De Giacomo, G., Iocchi, L., Favorito, M., Patrizi, F.: Restraining Bolts for reinforcement learning agents. In: Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence. vol. 9, pp. 13659\u201313662. AAAI Press, Palo Alto (2020). https:\/\/doi.org\/10.1609\/aaai.v34i09.7114","DOI":"10.1609\/aaai.v34i09.7114"},{"key":"15_CR7","unstructured":"Frosst, N., Hinton, G.: Distilling a neural network into a soft decision tree. In: Besold, T.R., Kutz, O. (eds.) Proceedings of the First International Workshop on Comprehensibility and Explanation in AI and ML 2017. AI*IA Series, vol. 2071. CEUR Workshop Proceedings, Aachen (2017)"},{"key":"15_CR8","doi-asserted-by":"publisher","unstructured":"F\u00fcrnkranz, J., Gamberger, D., Lavra\u010d, N.: Foundations of Rule Learning. Cognitive Technologies. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-540-75197-7","DOI":"10.1007\/978-3-540-75197-7"},{"key":"15_CR9","unstructured":"Gevaert, A., Peck, J., Saeys, Y.: Distillation of deep reinforcement learning models using fuzzy inference systems. In: Beuls, K., et\u00a0al. (eds.) Proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019), vol. 2491. CEUR Workshop Proceedings, Aachen (2019)"},{"key":"15_CR10","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv e-prints arXiv:1503.02531 (2015)"},{"key":"15_CR11","doi-asserted-by":"publisher","unstructured":"Huang, J., Angelov, P.P., Yin, C.: Interpretable policies for reinforcement learning by empirical fuzzy sets. Eng. Appl. Artif. Intell. 91 (2020). https:\/\/doi.org\/10.1016\/j.engappai.2020.103559","DOI":"10.1016\/j.engappai.2020.103559"},{"issue":"1","key":"15_CR12","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1109\/TCIAIG.2012.2188528","volume":"4","author":"S Karakovskiy","year":"2012","unstructured":"Karakovskiy, S., Togelius, J.: The Mario AI benchmark and competitions. IEEE Trans. Comput. Intell. AI Games 4(1), 55\u201367 (2012). https:\/\/doi.org\/10.1109\/TCIAIG.2012.2188528","journal-title":"IEEE Trans. Comput. Intell. AI Games"},{"key":"15_CR13","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1007\/3-540-48751-4_17","volume-title":"Inductive Logic Programming","author":"N Lavra\u010d","year":"1999","unstructured":"Lavra\u010d, N., Flach, P., Zupan, B.: Rule evaluation measures: a unifying view. In: D\u017eeroski, S., Flach, P. (eds.) ILP 1999. LNCS (LNAI), vol. 1634, pp. 174\u2013185. Springer, Heidelberg (1999). https:\/\/doi.org\/10.1007\/3-540-48751-4_17"},{"key":"15_CR14","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/978-3-030-67670-4_10","volume-title":"Machine Learning and Knowledge Discovery in Databases. Applied Data Science and Demo Track","author":"PJK Libin","year":"2021","unstructured":"Libin, P.J.K., et al.: Deep reinforcement learning for large-scale epidemic control. In: Dong, Y., Ifrim, G., Mladeni\u0107, D., Saunders, C., Van Hoecke, S. (eds.) ECML PKDD 2020. LNCS (LNAI), vol. 12461, pp. 155\u2013170. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-67670-4_10"},{"key":"15_CR15","doi-asserted-by":"publisher","unstructured":"Madumal, P., Miller, T., Sonenberg, L., Vetere, F.: Explainable reinforcement learning through a causal lens. In: Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, vol. 3, pp. 2493\u20132500. AAAI Press, Palo Alto (2020). https:\/\/doi.org\/10.1609\/aaai.v34i03.5631","DOI":"10.1609\/aaai.v34i03.5631"},{"key":"15_CR16","doi-asserted-by":"publisher","unstructured":"Maes, P.: Computational reflection. In: Morik, K. (ed.) GWAI-87 11th German Workshop on Artifical Intelligence. Informatik-Fachberichte, vol. 152, pp. 251\u2013265. Springer, Heidelberg (1987). https:\/\/doi.org\/10.1007\/978-3-642-73005-4_27","DOI":"10.1007\/978-3-642-73005-4_27"},{"key":"15_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.artint.2018.07.007","volume":"267","author":"T Miller","year":"2019","unstructured":"Miller, T.: Explanation in artificial intelligence: insights from the social sciences. Artif. Intell. 267, 1\u201338 (2019). https:\/\/doi.org\/10.1016\/j.artint.2018.07.007","journal-title":"Artif. Intell."},{"issue":"7540","key":"15_CR18","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). https:\/\/doi.org\/10.1038\/nature14236","journal-title":"Nature"},{"key":"15_CR19","unstructured":"Molnar, C.: Interpretable Machine Learning. Leanpub, Victoria (2019)"},{"key":"15_CR20","unstructured":"Rusu, A.A., et al.: Policy distillation. In: International Conference on Learning Representations (2016). arXiv:1511.06295"},{"key":"15_CR21","doi-asserted-by":"publisher","unstructured":"R\u00fcckstie\u00df, T., Sehnke, F., Schaul, T., Wierstra, D., Sun, Y., Schmidhuber, J.: Exploring parameter space in reinforcement learning. Paladyn, J. Behav. Robot. 1(1), 14\u201324 (2010). doi: https:\/\/doi.org\/10.2478\/s13230-010-0002-4","DOI":"10.2478\/s13230-010-0002-4"},{"key":"15_CR22","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/978-3-030-46133-1_2","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"D Steckelmacher","year":"2020","unstructured":"Steckelmacher, D., Plisnier, H., Roijers, D.M., Now\u00e9, A.: Sample-efficient model-free reinforcement learning with off-policy critics. In: Brefeld, U., Fromont, E., Hotho, A., Knobbe, A., Maathuis, M., Robardet, C. (eds.) ECML PKDD 2019. LNCS (LNAI), vol. 11908, pp. 19\u201334. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-46133-1_2"},{"key":"15_CR23","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, 2nd edn. MIT Press, Cambridge (2018)","edition":"2"},{"key":"15_CR24","unstructured":"Sutton, R.S., McAllester, D., Singh, S., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. In: Neural Information Processing Systems (NIPS), pp. 1057\u20131063 (2000)"},{"key":"15_CR25","unstructured":"Tadepalli, P., Givan, R., Driessens, K.: Relational reinforcement learning: an overview. In: Tadepalli, P., Givan, R., Driessens, K. (eds.) Proceedings of the ICML-2004 Workshop on Relational Reinforcement Learning, Banff, Canada, pp. 1\u20139 (2004)"},{"key":"15_CR26","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1007\/3-540-45372-5_25","volume-title":"Principles of Data Mining and Knowledge Discovery","author":"L Todorovski","year":"2000","unstructured":"Todorovski, L., Flach, P., Lavra\u010d, N.: Predictive performance of weighted relative accuracy. In: Zighed, D.A., Komorowski, J., \u017bytkow, J. (eds.) PKDD 2000. LNCS (LNAI), vol. 1910, pp. 255\u2013264. Springer, Heidelberg (2000). https:\/\/doi.org\/10.1007\/3-540-45372-5_25"},{"key":"15_CR27","unstructured":"Zambaldi, V., et al.: Deep reinforcement learning with relational inductive biases. In: International Conference on Learning Representations (2019)"}],"container-title":["Lecture Notes in Computer Science","Trustworthy AI - Integrating Learning, Optimization and Reasoning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-73959-1_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,24]],"date-time":"2022-12-24T02:59:43Z","timestamp":1671850783000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-73959-1_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030739584","9783030739591"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-73959-1_15","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":"13 April 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"TAILOR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on the Foundations of Trustworthy AI Integrating Learning, Optimization and Reasoning","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Santiago de Compestela","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":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 September 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 September 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tailor2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/tailor-network.eu\/activities\/tailor-workshop-2020\/","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":"52","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":"11","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":"6","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":"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":"3,5","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)"}}]}}