{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T08:51:59Z","timestamp":1743065519626,"version":"3.40.3"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031553257"},{"type":"electronic","value":"9783031553264"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-55326-4_6","type":"book-chapter","created":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T08:46:10Z","timestamp":1710405970000},"page":"115-140","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Predictive Explanations for\u00a0and by\u00a0Reinforcement Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4800-9181","authenticated-orcid":false,"given":"L\u00e9o","family":"Sauli\u00e8res","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4853-053X","authenticated-orcid":false,"given":"Martin C.","family":"Cooper","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7891-9920","authenticated-orcid":false,"given":"Florence Dupin","family":"de Saint-Cyr","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,3,15]]},"reference":[{"key":"6_CR1","unstructured":"Amir, D., Amir, O.: HIGHLIGHTS: summarizing agent behavior to people. In: Andr\u00e9, E., Koenig, S., Dastani, M., Sukthankar, G. (eds.) Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems, AAMAS, pp. 1168\u20131176. International Foundation for Autonomous Agents and Multiagent Systems\/ACM (2018). http:\/\/dl.acm.org\/citation.cfm?id=3237869"},{"key":"6_CR2","unstructured":"Bastani, O., Pu, Y., Solar-Lezama, A.: Verifiable reinforcement learning via policy extraction. In: Bengio, S., Wallach, H.M., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) NeurIPS, pp. 2499\u20132509 (2018). https:\/\/proceedings.neurips.cc\/paper\/2018\/hash\/e6d8545daa42d5ced125a4bf747b3688-Abstract.html"},{"key":"6_CR3","unstructured":"Brockman, G., et al.: OpenAI gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"6_CR4","unstructured":"Clouse, J.A.: On integrating apprentice learning and reinforcement learning. University of Massachusetts Amherst (1996)"},{"key":"6_CR5","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1007\/978-3-030-35288-2_6","volume-title":"AI 2019: Advances in Artificial Intelligence","author":"F Cruz","year":"2019","unstructured":"Cruz, F., Dazeley, R., Vamplew, P.: Memory-based explainable reinforcement learning. In: Liu, J., Bailey, J. (eds.) AI 2019. LNCS (LNAI), vol. 11919, pp. 66\u201377. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-35288-2_6"},{"key":"6_CR6","unstructured":"Danesh, M.H., Koul, A., Fern, A., Khorram, S.: Re-understanding finite-state representations of recurrent policy networks. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18\u201324 July 2021, Virtual Event. Proceedings of Machine Learning Research, vol. 139, pp. 2388\u20132397. PMLR (2021). http:\/\/proceedings.mlr.press\/v139\/danesh21a.html"},{"issue":"10","key":"6_CR7","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1145\/3271625","volume":"61","author":"A Darwiche","year":"2018","unstructured":"Darwiche, A.: Human-level intelligence or animal-like abilities? Commun. ACM 61(10), 56\u201367 (2018). https:\/\/doi.org\/10.1145\/3271625","journal-title":"Commun. ACM"},{"key":"6_CR8","unstructured":"European Commission: Artificial Intelligence Act (2021). https:\/\/eur-lex.europa.eu\/legal-content\/EN\/TXT\/?qid=1623335154975 &uri=CELEX%3A52021PC0206"},{"key":"6_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/978-3-031-15565-9_3","volume-title":"Explainable and Transparent AI and Multi-Agent Systems","author":"J Gajcin","year":"2022","unstructured":"Gajcin, J., Dusparic, I.: ReCCoVER: detecting causal confusion for explainable reinforcement learning. In: Calvaresi, D., Najjar, A., Winikoff, M., Fr\u00e4mling, K. (eds.) EXTRAAMAS 2022. LNCS, vol. 13283, pp. 38\u201356. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-15565-9_3"},{"key":"6_CR10","unstructured":"Greydanus, S., Koul, A., Dodge, J., Fern, A.: Visualizing and understanding Atari agents. In: Dy, J.G., Krause, A. (eds.) ICML. Proceedings of Machine Learning Research, vol. 80, pp. 1787\u20131796. PMLR (2018). http:\/\/proceedings.mlr.press\/v80\/greydanus18a.html"},{"key":"6_CR11","unstructured":"Guo, W., Wu, X., Khan, U., Xing, X.: EDGE: explaining deep reinforcement learning policies. In: Ranzato, M., Beygelzimer, A., Dauphin, Y.N., Liang, P., Vaughan, J.W. (eds.) NeurIPS, pp. 12222\u201312236 (2021). https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/65c89f5a9501a04c073b354f03791b1f-Abstract.html"},{"key":"6_CR12","unstructured":"Hasselt, H.: Double Q-learning. In: Advances in Neural Information Processing Systems, vol. 23 (2010)"},{"key":"6_CR13","unstructured":"Huber, T., Demmler, M., Mertes, S., Olson, M.L., Andr\u00e9, E.: GANterfactual-RL: understanding reinforcement learning agents\u2019 strategies through visual counterfactual explanations. CoRR abs\/2302.12689 (2023). https:\/\/doi.org\/10.48550\/arXiv.2302.12689"},{"key":"6_CR14","doi-asserted-by":"publisher","unstructured":"Iyer, R., Li, Y., Li, H., Lewis, M., Sundar, R., Sycara, K.P.: Transparency and explanation in deep reinforcement learning neural networks. In: Furman, J., Marchant, G.E., Price, H., Rossi, F. (eds.) Proceedings of the 2018 AAAI\/ACM Conference on AI, Ethics, and Society, AIES, pp. 144\u2013150. ACM (2018). https:\/\/doi.org\/10.1145\/3278721.3278776","DOI":"10.1145\/3278721.3278776"},{"key":"6_CR15","unstructured":"Juozapaitis, Z., Koul, A., Fern, A., Erwig, M., Doshi-Velez, F.: Explainable reinforcement learning via reward decomposition. In: IJCAI\/ECAI Workshop on Explainable Artificial Intelligence, p. 7 (2019)"},{"issue":"10","key":"6_CR16","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1145\/3233231","volume":"61","author":"ZC Lipton","year":"2018","unstructured":"Lipton, Z.C.: The mythos of model interpretability. Commun. ACM 61(10), 36\u201343 (2018). https:\/\/doi.org\/10.1145\/3233231","journal-title":"Commun. ACM"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Madumal, P., Miller, T., Sonenberg, L., Vetere, F.: Explainable reinforcement learning through a causal lens. In: The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, pp. 2493\u20132500. AAAI Press (2020). https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/5631","DOI":"10.1609\/aaai.v34i03.5631"},{"key":"6_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1007\/978-3-540-71496-5_51","volume-title":"Advances in Information Retrieval","author":"R McDonald","year":"2007","unstructured":"McDonald, R.: A study of global inference algorithms in multi-document summarization. In: Amati, G., Carpineto, C., Romano, G. (eds.) ECIR 2007. LNCS, vol. 4425, pp. 557\u2013564. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-71496-5_51"},{"key":"6_CR19","unstructured":"Milani, S., Topin, N., Veloso, M., Fang, F.: A survey of explainable reinforcement learning. CoRR abs\/2202.08434 (2022). https:\/\/arxiv.org\/abs\/2202.08434"},{"key":"6_CR20","unstructured":"Mishra, A., Soni, U., Huang, J., Bryan, C.: Why? Why not? When? Visual explanations of agent behavior in reinforcement learning. CoRR abs\/2104.02818 (2021). https:\/\/arxiv.org\/abs\/2104.02818"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015). http:\/\/www.nature.com\/articles\/nature14236","DOI":"10.1038\/nature14236"},{"key":"6_CR22","unstructured":"Olson, M.L., Neal, L., Li, F., Wong, W.: Counterfactual states for Atari agents via generative deep learning. CoRR abs\/1909.12969 (2019). http:\/\/arxiv.org\/abs\/1909.12969"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Sauli\u00e8res, L., Cooper, M.C., Dupin de Saint Cyr, F.: Reinforcement learning explained via reinforcement learning: towards explainable policies through predictive explanation. In: 15th International Conference on Agents and Artificial Intelligence (ICAART 2023), pp. 35\u201344 (2023)","DOI":"10.5220\/0011619600003393"},{"key":"6_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2020.103367","volume":"288","author":"P Sequeira","year":"2020","unstructured":"Sequeira, P., Gervasio, M.T.: Interestingness elements for explainable reinforcement learning: understanding agents\u2019 capabilities and limitations. Artif. Intell. 288, 103367 (2020). https:\/\/doi.org\/10.1016\/j.artint.2020.103367","journal-title":"Artif. Intell."},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Shu, T., Xiong, C., Socher, R.: Hierarchical and interpretable skill acquisition in multi-task reinforcement learning. CoRR abs\/1712.07294 (2017). http:\/\/arxiv.org\/abs\/1712.07294","DOI":"10.1007\/978-981-287-588-4_100717"},{"key":"6_CR26","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"key":"6_CR27","unstructured":"Tsirtsis, S., De, A., Rodriguez, M.: Counterfactual explanations in sequential decision making under uncertainty. In: Ranzato, M., Beygelzimer, A., Dauphin, Y.N., Liang, P., Vaughan, J.W. (eds.) NeurIPS 2021, pp. 30127\u201330139 (2021). https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/fd0a5a5e367a0955d81278062ef37429-Abstract.html"},{"key":"6_CR28","unstructured":"Verma, A., Murali, V., Singh, R., Kohli, P., Chaudhuri, S.: Programmatically interpretable reinforcement learning. In: Dy, J.G., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning, ICML 2018. Proceedings of Machine Learning Research, vol. 80, pp. 5052\u20135061. PMLR (2018). http:\/\/proceedings.mlr.press\/v80\/verma18a.html"},{"key":"6_CR29","unstructured":"van der Waa, J., van Diggelen, J., van den Bosch, K., Neerincx, M.A.: Contrastive explanations for reinforcement learning in terms of expected consequences. CoRR abs\/1807.08706 (2018). http:\/\/arxiv.org\/abs\/1807.08706"},{"issue":"3","key":"6_CR30","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF00992698","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8(3), 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"key":"6_CR31","unstructured":"Yau, H., Russell, C., Hadfield, S.: What did you think would happen? Explaining agent behaviour through intended outcomes. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) NeurIPS (2020). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/d5ab8dc7ef67ca92e41d730982c5c602-Abstract.html"},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"Yu, Z., Ruan, J., Xing, D.: Explainable reinforcement learning via a causal world model. CoRR abs\/2305.02749 (2023). https:\/\/doi.org\/10.48550\/arXiv.2305.02749","DOI":"10.24963\/ijcai.2023\/505"},{"key":"6_CR33","unstructured":"Zahavy, T., Ben-Zrihem, N., Mannor, S.: Graying the black box: understanding DQNs. In: Balcan, M., Weinberger, K.Q. (eds.) Proceedings of the 33nd International Conference on Machine Learning, ICML 2016. JMLR Workshop and Conference Proceedings, vol. 48, pp. 1899\u20131908. JMLR.org (2016). http:\/\/proceedings.mlr.press\/v48\/zahavy16.html"}],"container-title":["Lecture Notes in Computer Science","Agents and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-55326-4_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T08:47:13Z","timestamp":1710406033000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-55326-4_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031553257","9783031553264"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-55326-4_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"15 March 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICAART","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Agents and Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lisbon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 February 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 February 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icaart2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icaart.scitevents.org\/?y=2023","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":"PRIMORIS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"306","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":"23","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":"111","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":"8% - 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":"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)"}}]}}