{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T10:47:17Z","timestamp":1778496437008,"version":"3.51.4"},"publisher-location":"Cham","reference-count":15,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031376153","type":"print"},{"value":"9783031376160","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-37616-0_27","type":"book-chapter","created":{"date-parts":[[2023,7,11]],"date-time":"2023-07-11T20:37:53Z","timestamp":1689107873000},"page":"320-332","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Integrating Policy Summaries with\u00a0Reward Decomposition for\u00a0Explaining Reinforcement Learning Agents"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2798-990X","authenticated-orcid":false,"given":"Yael","family":"Septon","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5010-4006","authenticated-orcid":false,"given":"Tobias","family":"Huber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2367-162X","authenticated-orcid":false,"given":"Elisabeth","family":"Andr\u00e9","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2303-3684","authenticated-orcid":false,"given":"Ofra","family":"Amir","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,7,12]]},"reference":[{"key":"27_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)"},{"issue":"5","key":"27_CR2","doi-asserted-by":"publisher","first-page":"628","DOI":"10.1007\/s10458-019-09418-w","volume":"33","author":"O Amir","year":"2019","unstructured":"Amir, O., Doshi-Velez, F., Sarne, D.: Summarizing agent strategies. Auton. Agent. Multi-Agent Syst. 33(5), 628\u2013644 (2019)","journal-title":"Auton. Agent. Multi-Agent Syst."},{"key":"27_CR3","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1613\/jair.3912","volume":"47","author":"MG Bellemare","year":"2013","unstructured":"Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents. J. Artif. Intell. Res. 47, 253\u2013279 (2013). https:\/\/doi.org\/10.1613\/jair.3912","journal-title":"J. Artif. Intell. Res."},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Booth, S., Muise, C., Shah, J.: Evaluating the interpretability of the knowledge compilation map: communicating logical statements effectively. In: IJCAI, pp. 5801\u20135807 (2019)","DOI":"10.24963\/ijcai.2019\/804"},{"key":"27_CR5","unstructured":"Dhariwal, P., et al.: OpenAI baselines. https:\/\/github.com\/openai\/baselines (2017)"},{"key":"27_CR6","unstructured":"Hoffman, R.R., Mueller, S.T., Klein, G., Litman, J.: Metrics for explainable AI: challenges and prospects. arXiv preprint arXiv:1812.04608 (2018)"},{"key":"27_CR7","doi-asserted-by":"publisher","unstructured":"Huber, T., Limmer, B., Andr\u00e9, E.: Benchmarking perturbation-based saliency maps for explaining Atari agents. Front. Artif. Intell. 5 (2022). https:\/\/doi.org\/10.3389\/frai.2022.903875, https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2022.903875","DOI":"10.3389\/frai.2022.903875"},{"key":"27_CR8","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1007\/978-3-030-30179-8_16","volume-title":"KI 2019: Advances in Artificial Intelligence","author":"T Huber","year":"2019","unstructured":"Huber, T., Schiller, D., Andr\u00e9, E.: Enhancing explainability of deep reinforcement learning through selective layer-wise relevance propagation. In: Benzm\u00fcller, C., Stuckenschmidt, H. (eds.) KI 2019. LNCS (LNAI), vol. 11793, pp. 188\u2013202. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-30179-8_16"},{"key":"27_CR9","doi-asserted-by":"publisher","first-page":"103571","DOI":"10.1016\/j.artint.2021.103571","volume":"301","author":"T Huber","year":"2021","unstructured":"Huber, T., Weitz, K., Andr\u00e9, E., Amir, O.: Local and global explanations of agent behavior: integrating strategy summaries with saliency maps. Artif. Intell. 301, 103571 (2021). https:\/\/doi.org\/10.1016\/j.artint.2021.103571","journal-title":"Artif. Intell."},{"key":"27_CR10","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 (2019)"},{"key":"27_CR11","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1007\/978-3-030-10928-8_25","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"G Liu","year":"2019","unstructured":"Liu, G., Schulte, O., Zhu, W., Li, Q.: Toward interpretable deep reinforcement learning with linear model U-Trees. In: Berlingerio, M., Bonchi, F., G\u00e4rtner, T., Hurley, N., Ifrim, G. (eds.) ECML PKDD 2018. LNCS (LNAI), Part II, vol. 11052, pp. 414\u2013429. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-10928-8_25"},{"issue":"7540","key":"27_CR12","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)","journal-title":"Nature"},{"issue":"5","key":"27_CR13","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1038\/s42256-019-0048-x","volume":"1","author":"C Rudin","year":"2019","unstructured":"Rudin, C.: Stop explaining black box machine learning models for high stakes decisions and use interpretable models instead. Nat. Mach. Intell. 1(5), 206\u2013215 (2019). https:\/\/doi.org\/10.1038\/s42256-019-0048-x","journal-title":"Nat. Mach. Intell."},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"Van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 2094\u20132100 (2016)","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"27_CR15","unstructured":"Van Seijen, H., Fatemi, M., Romoff, J., Laroche, R., Barnes, T., Tsang, J.: Hybrid reward architecture for reinforcement learning. arXiv preprint arXiv:1706.04208 (2017)"}],"container-title":["Lecture Notes in Computer Science","Advances in Practical Applications of Agents, Multi-Agent Systems, and Cognitive Mimetics. The PAAMS Collection"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-37616-0_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T15:04:52Z","timestamp":1693580692000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-37616-0_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031376153","9783031376160"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-37616-0_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"12 July 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAAMS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Practical Applications of Agents and Multi-Agent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Guimaraes","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":"12 July 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 July 2023","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":"paams2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.paams.net\/","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":"70","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":"32","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":"46% - 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)"}},{"value":"PAAMS 2023 Workshops: 26 submissions, 14 full papers accepted, 5 demonstration papers","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)"}}]}}