{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T13:19:53Z","timestamp":1781529593091,"version":"3.54.1"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031155642","type":"print"},{"value":"9783031155659","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-15565-9_3","type":"book-chapter","created":{"date-parts":[[2022,9,22]],"date-time":"2022-09-22T10:15:45Z","timestamp":1663841745000},"page":"38-56","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["ReCCoVER: Detecting Causal Confusion for\u00a0Explainable Reinforcement Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8731-1236","authenticated-orcid":false,"given":"Jasmina","family":"Gajcin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0621-5400","authenticated-orcid":false,"given":"Ivana","family":"Dusparic","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,9,23]]},"reference":[{"key":"3_CR1","unstructured":"Amir, D., Amir, O.: Highlights: summarizing agent behavior to people. In: Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems, pp. 1168\u20131176 (2018)"},{"key":"3_CR2","unstructured":"Brockman, G., et al.: OpenAI Gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"3_CR3","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1613\/jair.1.12228","volume":"70","author":"N Burkart","year":"2021","unstructured":"Burkart, N., Huber, M.F.: A survey on the explainability of supervised machine learning. J. Artif. Intell. Res. 70, 245\u2013317 (2021)","journal-title":"J. Artif. Intell. Res."},{"issue":"8","key":"3_CR4","doi-asserted-by":"publisher","first-page":"832","DOI":"10.3390\/electronics8080832","volume":"8","author":"DV Carvalho","year":"2019","unstructured":"Carvalho, D.V., Pereira, E.M., Cardoso, J.S.: Machine learning interpretability: a survey on methods and metrics. Electronics 8(8), 832 (2019)","journal-title":"Electronics"},{"key":"3_CR5","unstructured":"Chevalier-Boisvert, M., Willems, L., Pal, S.: Minimalistic gridworld environment for OpenAI Gym (2018). https:\/\/github.com\/maximecb\/gym-minigrid"},{"key":"3_CR6","unstructured":"Coppens, Y., et al.: Distilling deep reinforcement learning policies in soft decision trees. In: Proceedings of the IJCAI 2019 Workshop on Explainable Artificial Intelligence, pp. 1\u20136 (2019)"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Dethise, A., Canini, M., Kandula, S.: Cracking open the black box: what observations can tell us about reinforcement learning agents. In: Proceedings of the 2019 Workshop on Network Meets AI & ML, pp. 29\u201336 (2019)","DOI":"10.1145\/3341216.3342210"},{"key":"3_CR8","unstructured":"Gajcin, J., Nair, R., Pedapati, T., Marinescu, R., Daly, E., Dusparic, I.: Contrastive explanations for comparing preferences of reinforcement learning agents. arXiv preprint arXiv:2112.09462 (2021)"},{"key":"3_CR9","unstructured":"Greydanus, S., Koul, A., Dodge, J., Fern, A.: Visualizing and understanding Atari agents. In: International Conference on Machine Learning, pp. 1792\u20131801. PMLR (2018)"},{"key":"3_CR10","unstructured":"de Haan, P., Jayaraman, D., Levine, S.: Causal confusion in imitation learning. In: Advances Neural Information Processing Systems, vol. 32, pp. 11698\u201311709 (2019)"},{"key":"3_CR11","unstructured":"Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"3_CR12","unstructured":"Lyle, C., Zhang, A., Jiang, M., Pineau, J., Gal, Y.: Resolving causal confusion in reinforcement learning via robust exploration. In: Self-Supervision for Reinforcement Learning Workshop, ICLR 2021 (2021)"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Madumal, P., Miller, T., Sonenberg, L., Vetere, F.: Explainable reinforcement learning through a causal lens. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 2493\u20132500 (2020)","DOI":"10.1609\/aaai.v34i03.5631"},{"key":"3_CR14","unstructured":"Mnih, V., et al.: Playing Atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"key":"3_CR15","unstructured":"Olson, M.L., Neal, L., Li, F., Wong, W.K.: Counterfactual states for Atari agents via generative deep learning. arXiv preprint arXiv:1909.12969 (2019)"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Pearl, J.: Causality. Cambridge University Press (2009)","DOI":"10.1017\/CBO9780511803161"},{"key":"3_CR17","unstructured":"Peters, J., Janzing, D., Sch\u00f6lkopf, B.: Elements of Causal Inference: Foundations and Learning Algorithms. The MIT Press (2017)"},{"key":"3_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1007\/978-3-030-57321-8_5","volume-title":"Machine Learning and Knowledge Extraction","author":"E Puiutta","year":"2020","unstructured":"Puiutta, E., Veith, E.M.S.P.: Explainable reinforcement learning: a survey. In: Holzinger, A., Kieseberg, P., Tjoa, A.M., Weippl, E. (eds.) CD-MAKE 2020. LNCS, vol. 12279, pp. 77\u201395. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-57321-8_5"},{"key":"3_CR19","unstructured":"Puri, N., et al.: Explain your move: understanding agent actions using specific and relevant feature attribution. arXiv preprint arXiv:1912.12191 (2019)"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Sequeira, P., Gervasio, M.: Interestingness elements for explainable reinforcement learning: understanding agents\u2019 capabilities and limitations. Artif. Intell. 288, 103367 (2020)","DOI":"10.1016\/j.artint.2020.103367"},{"key":"3_CR21","unstructured":"Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034 (2013)"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"\u015eim\u015fek, \u00d6., Barto, A.G.: Using relative novelty to identify useful temporal abstractions in reinforcement learning. In: Proceedings of the Twenty-First International Conference on Machine Learning, p. 95 (2004)","DOI":"10.1145\/1015330.1015353"},{"key":"3_CR23","unstructured":"Verma, A., Murali, V., Singh, R., Kohli, P., Chaudhuri, S.: Programmatically interpretable reinforcement learning. In: International Conference on Machine Learning, pp. 5045\u20135054. PMLR (2018)"},{"key":"3_CR24","unstructured":"van der Waa, J., van Diggelen, J., van den Bosch, K., Neerincx, M.: Contrastive explanations for reinforcement learning in terms of expected consequences. arXiv preprint arXiv:1807.08706 (2018)"}],"container-title":["Lecture Notes in Computer Science","Explainable and Transparent AI and Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-15565-9_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,22]],"date-time":"2022-09-22T10:18:13Z","timestamp":1663841893000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-15565-9_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031155642","9783031155659"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-15565-9_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"23 September 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"EXTRAAMAS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Explainable, Transparent Autonomous Agents and Multi-Agent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 May 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 May 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"extraamas2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/extraamas.ehealth.hevs.ch\/index.html","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":"25","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":"14","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":"56% - 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":"2","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)"}}]}}