{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T14:10:11Z","timestamp":1755871811431,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,1,4]],"date-time":"2024-01-04T00:00:00Z","timestamp":1704326400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,1,4]]},"DOI":"10.1145\/3632410.3632443","type":"proceedings-article","created":{"date-parts":[[2024,1,3]],"date-time":"2024-01-03T18:15:16Z","timestamp":1704305716000},"page":"91-99","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Cost-Sensitive Trees for Interpretable Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4229-5922","authenticated-orcid":false,"given":"Siddharth","family":"Nishtala","sequence":"first","affiliation":[{"name":"Robert Bosch Centre for Data Science and AI, Indian Institute of Technology Madras, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5364-7639","authenticated-orcid":false,"given":"Balaraman","family":"Ravindran","sequence":"additional","affiliation":[{"name":"Robert Bosch Centre for Data Science and AI, Indian Institute of Technology Madras, India"}]}],"member":"320","published-online":{"date-parts":[[2024,1,4]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Advances in Neural Information Processing Systems, S.\u00a0Bengio, H.\u00a0Wallach, H.\u00a0Larochelle, K.\u00a0Grauman, N.\u00a0Cesa-Bianchi, and R.\u00a0Garnett (Eds.). Vol.\u00a031. Curran Associates","author":"Bastani Osbert","year":"2018","unstructured":"Osbert Bastani, Yewen Pu, and Armando Solar-Lezama. 2018. Verifiable Reinforcement Learning via Policy Extraction. In Advances in Neural Information Processing Systems, S.\u00a0Bengio, H.\u00a0Wallach, H.\u00a0Larochelle, K.\u00a0Grauman, N.\u00a0Cesa-Bianchi, and R.\u00a0Garnett (Eds.). Vol.\u00a031. Curran Associates, Inc.https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2018\/file\/e6d8545daa42d5ced125a4bf747b3688-Paper.pdf"},{"volume-title":"Classification and Regression Trees","author":"Breiman Leo","key":"e_1_3_2_1_2_1","unstructured":"Leo Breiman, Jerome Friedman, Charles\u00a0J Stone, and RA Olshen. 1984. Classification and Regression Trees. CRC Press."},{"key":"e_1_3_2_1_3_1","volume-title":"CoRR abs\/1606.01540","author":"Brockman Greg","year":"2016","unstructured":"Greg Brockman, Vicki Cheung, Ludwig Pettersson, Jonas Schneider, John Schulman, Jie Tang, and Wojciech Zaremba. 2016. OpenAI Gym. CoRR abs\/1606.01540 (2016). arXiv:1606.01540http:\/\/arxiv.org\/abs\/1606.01540"},{"key":"e_1_3_2_1_4_1","unstructured":"David Chapman and Leslie\u00a0Pack Kaelbling. 1991. Input Generalization in Delayed Reinforcement Learning: An Algorithm and Performance Comparisons.. In Ijcai Vol.\u00a091. 726\u2013731."},{"key":"e_1_3_2_1_5_1","volume-title":"Distilling Deep Reinforcement Learning Policies in Soft Decision Trees. In International Joint Conference on Artificial Intelligence.","author":"Coppens Youri","year":"2019","unstructured":"Youri Coppens, Kyriakos Efthymiadis, Tom Lenaerts, and Ann Now\u00e9. 2019. Distilling Deep Reinforcement Learning Policies in Soft Decision Trees. In International Joint Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2015.04.042"},{"key":"e_1_3_2_1_7_1","volume-title":"CDT: Cascading Decision Trees for Explainable Reinforcement Learning. CoRR abs\/2011.07553","author":"Ding Zihan","year":"2020","unstructured":"Zihan Ding, Pablo Hernandez-Leal, Gavin\u00a0Weiguang Ding, Changjian Li, and Ruitong Huang. 2020. CDT: Cascading Decision Trees for Explainable Reinforcement Learning. CoRR abs\/2011.07553 (2020). arXiv:2011.07553https:\/\/arxiv.org\/abs\/2011.07553"},{"volume-title":"International joint conference on artificial intelligence, Vol.\u00a017","author":"Elkan Charles","key":"e_1_3_2_1_8_1","unstructured":"Charles Elkan. 2001. The foundations of cost-sensitive learning. In International joint conference on artificial intelligence, Vol.\u00a017. Lawrence Erlbaum Associates Ltd, 973\u2013978."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2010.12.003"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(95)00014-3"},{"key":"e_1_3_2_1_12_1","unstructured":"Edouard Leurent. 2018. An Environment for Autonomous Driving Decision-Making. https:\/\/github.com\/eleurent\/highway-env."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015369"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-10928-8_25"},{"volume-title":"From Animals to Animats 4: Proceedings of the fourth international conference on simulation of adaptive behavior, Vol.\u00a04","author":"Andrew\u00a0Kachites","key":"e_1_3_2_1_15_1","unstructured":"Andrew\u00a0Kachites McCallum 1996. Learning to use selective attention and short-term memory in sequential tasks. In From Animals to Animats 4: Proceedings of the fourth international conference on simulation of adaptive behavior, Vol.\u00a04. MIT Press Cambridge, 315."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50055-4"},{"key":"e_1_3_2_1_17_1","volume-title":"Human-level control through deep reinforcement learning. nature 518, 7540","author":"Mnih Volodymyr","year":"2015","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei\u00a0A Rusu, Joel Veness, Marc\u00a0G Bellemare, Alex Graves, Martin Riedmiller, Andreas\u00a0K Fidjeland, Georg Ostrovski, 2015. Human-level control through deep reinforcement learning. nature 518, 7540 (2015), 529\u2013533."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50034-9"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"e_1_3_2_1_20_1","first-page":"1","article-title":"Stable-Baselines3: Reliable Reinforcement Learning Implementations","volume":"22","author":"Raffin Antonin","year":"2021","unstructured":"Antonin Raffin, Ashley Hill, Adam Gleave, Anssi Kanervisto, Maximilian Ernestus, and Noah Dormann. 2021. Stable-Baselines3: Reliable Reinforcement Learning Implementations. Journal of Machine Learning Research 22, 268 (2021), 1\u20138. http:\/\/jmlr.org\/papers\/v22\/20-1364.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics(Proceedings of Machine Learning Research, Vol.\u00a015)","author":"Ross Stephane","year":"2011","unstructured":"Stephane Ross, Geoffrey Gordon, and Drew Bagnell. 2011. A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning. In Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics(Proceedings of Machine Learning Research, Vol.\u00a015), Geoffrey Gordon, David Dunson, and Miroslav Dud\u00edk (Eds.). PMLR, Fort Lauderdale, FL, USA, 627\u2013635. https:\/\/proceedings.mlr.press\/v15\/ross11a.html"},{"key":"e_1_3_2_1_22_1","volume-title":"Conservative q-improvement: Reinforcement learning for an interpretable decision-tree policy. arXiv preprint arXiv:1907.01180","author":"Roth M","year":"2019","unstructured":"Aaron\u00a0M Roth, Nicholay Topin, Pooyan Jamshidi, and Manuela Veloso. 2019. Conservative q-improvement: Reinforcement learning for an interpretable decision-tree policy. arXiv preprint arXiv:1907.01180 (2019)."},{"key":"e_1_3_2_1_23_1","volume-title":"International conference on artificial intelligence and statistics. PMLR","author":"Silva Andrew","year":"2020","unstructured":"Andrew Silva, Matthew Gombolay, Taylor Killian, Ivan Jimenez, and Sung-Hyun Son. 2020. Optimization methods for interpretable differentiable decision trees applied to reinforcement learning. In International conference on artificial intelligence and statistics. PMLR, 1855\u20131865."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2002.1000348"},{"key":"e_1_3_2_1_26_1","first-page":"769","article-title":"Tree based discretization for continuous state space reinforcement learning","volume":"98","author":"Uther TB","year":"1998","unstructured":"William\u00a0TB Uther and Manuela\u00a0M Veloso. 1998. Tree based discretization for continuous state space reinforcement learning. AAAI\/IAAI 98 (1998), 769\u2013774.","journal-title":"AAAI\/IAAI"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.03.022"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2003.1250950"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2006.17"}],"event":{"name":"CODS-COMAD 2024: 7th Joint International Conference on Data Science & Management of Data (11th ACM IKDD CODS and 29th COMAD)","acronym":"CODS-COMAD 2024","location":"Bangalore India"},"container-title":["Proceedings of the 7th Joint International Conference on Data Science & Management of Data (11th ACM IKDD CODS and 29th COMAD)"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3632410.3632443","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3632410.3632443","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T13:37:17Z","timestamp":1755869837000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3632410.3632443"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,4]]},"references-count":29,"alternative-id":["10.1145\/3632410.3632443","10.1145\/3632410"],"URL":"https:\/\/doi.org\/10.1145\/3632410.3632443","relation":{},"subject":[],"published":{"date-parts":[[2024,1,4]]},"assertion":[{"value":"2024-01-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}