乐胖代购免代理版

{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,13]],"date-time":"2024-09-13T11:55:27Z","timestamp":1726228527576},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031408779"},{"type":"electronic","value":"9783031408786"}],"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\/978-3-031-40878-6_10","type":"book-chapter","created":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T09:03:22Z","timestamp":1693818202000},"page":"160-179","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Inherently Interpretable Deep Reinforcement Learning Through Online Mimicking"],"prefix":"10.1007","author":[{"given":"Andreas","family":"Kontogiannis","sequence":"first","affiliation":[]},{"given":"George A.","family":"Vouros","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,5]]},"reference":[{"key":"10_CR1","unstructured":"Ba, J., Caruana, R.: Do deep nets really need to be deep? In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N., Weinberger, K. (eds.) Advances in Neural Information Processing Systems, vol. 27. Curran Associates, Inc. (2014). https:\/\/proceedings.neurips.cc\/paper\/2014\/file\/ea8fcd92d59581717e06eb187f10666d-Paper.pdf"},{"key":"10_CR2","unstructured":"Bastani, O., Pu, Y., Solar-Lezama, A.: Verifiable reinforcement learning via policy extraction. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, NIPS 2018, pp. 2499\u20132509. Curran Associates Inc., Red Hook, NY, USA (2018)"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Belle, V., Papantonis, I.: Principles and practice of explainable machine learning. Front. Big Data 4, 39 (2021)","DOI":"10.3389\/fdata.2021.688969"},{"key":"10_CR4","doi-asserted-by":"publisher","unstructured":"Boz, O.: Extracting decision trees from trained neural networks. In: KDD 2002, pp. 456\u2013461. Association for Computing Machinery, New York, NY, USA (2002). https:\/\/doi.org\/10.1145\/775047.775113","DOI":"10.1145\/775047.775113"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Boz, O.: Extracting decision trees from trained neural networks. In: Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 456\u2013461 (2002)","DOI":"10.1145\/775047.775113"},{"key":"10_CR6","unstructured":"Che, Z., Purushotham, S., Khemani, R., Liu, Y.: Interpretable deep models for ICU outcome prediction. In: AMIA Annual Symposium Proceedings 2016, pp. 371\u2013380, February 2017"},{"key":"10_CR7","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":"10_CR8","doi-asserted-by":"crossref","unstructured":"Dancey, D., Bandar, Z.A., McLean, D.: Logistic model tree extraction from artificial neural networks. IEEE Trans. Syst. Man Cybern. Part B (Cybern.) 37(4), 794\u2013802 (2007)","DOI":"10.1109\/TSMCB.2007.895334"},{"key":"10_CR9","doi-asserted-by":"publisher","unstructured":"Delgado-Panadero, \u00c1., Hern\u00e1ndez-Lorca, B., Garc\u00eda-Ord\u00e1s, M.T., Ben\u00edtez-Andrades, J.A.: Implementing local-explainability in gradient boosting trees: feature contribution. Inf. Sci. 589, 199\u2013212 (2022). https:\/\/doi.org\/10.1016\/j.ins.2021.12.111, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0020025521013323","DOI":"10.1016\/j.ins.2021.12.111"},{"key":"10_CR10","unstructured":"Frosst, N., Hinton, G.: Distilling a neural network into a soft decision tree. arXiv preprint arXiv:1711.09784 (2017)"},{"key":"10_CR11","doi-asserted-by":"publisher","unstructured":"Gu, S., Holly, E., Lillicrap, T., Levine, S.: Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 3389\u20133396 (2017). https:\/\/doi.org\/10.1109\/ICRA.2017.7989385","DOI":"10.1109\/ICRA.2017.7989385"},{"issue":"5","key":"10_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3236009","volume":"51","author":"R Guidotti","year":"2018","unstructured":"Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., Pedreschi, D.: A survey of methods for explaining black box models. ACM Comput. Surv. (CSUR) 51(5), 1\u201342 (2018)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Kravaris, T., et al.: Explaining deep reinforcement learning decisions in complex multiagent settings: towards enabling automation in air traffic flow management. Appl. Intell. (Dordrecht, Netherlands) 53, 4063\u20134098 (2022)","DOI":"10.1007\/s10489-022-03605-1"},{"key":"10_CR14","unstructured":"Kravaris, T., et al.: Resolving congestions in the air traffic management domain via multiagent reinforcement learning methods. arXiv:abs\/1912.06860 (2019)"},{"key":"10_CR15","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1007\/978-3-319-64798-2_15","volume-title":"Multiagent System Technologies","author":"T Kravaris","year":"2017","unstructured":"Kravaris, T., Vouros, G.A., Spatharis, C., Blekas, K., Chalkiadakis, G., Garcia, J.M.C.: Learning policies for resolving demand-capacity imbalances during pre-tactical air traffic management. In: Berndt, J.O., Petta, P., Unland, R. (eds.) MATES 2017. LNCS (LNAI), vol. 10413, pp. 238\u2013255. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-64798-2_15"},{"key":"10_CR16","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, Part II. LNCS (LNAI), vol. 11052, pp. 414\u2013429. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-10928-8_25"},{"key":"10_CR17","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":"10_CR18","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"},{"issue":"7540","key":"10_CR19","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"},{"issue":"44","key":"10_CR20","doi-asserted-by":"publisher","first-page":"22071","DOI":"10.1073\/pnas.1900654116","volume":"116","author":"WJ Murdoch","year":"2019","unstructured":"Murdoch, W.J., Singh, C., Kumbier, K., Abbasi-Asl, R., Yu, B.: Definitions, methods, and applications in interpretable machine learning. Proc. Nat. Acad. Sci. 116(44), 22071\u201322080 (2019)","journal-title":"Proc. Nat. Acad. Sci."},{"key":"10_CR21","doi-asserted-by":"publisher","unstructured":"Ribeiro, M.T., Singh, S., Guestrin, C.: \u201cWhy should i trust you?\u201d: Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2016, pp. 1135\u20131144. Association for Computing Machinery, New York, NY, USA (2016). https:\/\/doi.org\/10.1145\/2939672.2939778","DOI":"10.1145\/2939672.2939778"},{"key":"10_CR22","doi-asserted-by":"publisher","unstructured":"Rudin, C., Chen, C., Chen, Z., Huang, H., Semenova, L., Zhong, C.: Interpretable machine learning: fundamental principles and 10 grand challenges (2021). https:\/\/doi.org\/10.48550\/ARXIV.2103.11251, arXiv:2103.11251","DOI":"10.48550\/ARXIV.2103.11251"},{"key":"10_CR23","doi-asserted-by":"publisher","unstructured":"Rusu, A.A., et al.: Policy distillation (2015). https:\/\/doi.org\/10.48550\/ARXIV.1511.06295, arXiv:1511.06295","DOI":"10.48550\/ARXIV.1511.06295"},{"key":"10_CR24","doi-asserted-by":"publisher","unstructured":"Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay (2015). https:\/\/doi.org\/10.48550\/ARXIV.1511.05952, arXiv:1511.05952","DOI":"10.48550\/ARXIV.1511.05952"},{"key":"10_CR25","doi-asserted-by":"publisher","unstructured":"Spatharis, C., Bastas, A., Kravaris, T., Blekas, K., Vouros, G., Cordero Garcia, J.: Hierarchical multiagent reinforcement learning schemes for air traffic management. Neural Comput. Appl. 35, 147\u2013159 (2021). https:\/\/doi.org\/10.1007\/s00521-021-05748-7","DOI":"10.1007\/s00521-021-05748-7"},{"key":"10_CR26","doi-asserted-by":"publisher","unstructured":"Spatharis, C., et al.: Multiagent reinforcement learning methods to resolve demand capacity balance problems. In: Proceedings of the 10th Hellenic Conference on Artificial Intelligence, SETN 2018. Association for Computing Machinery, New York, NY, USA (2018). https:\/\/doi.org\/10.1145\/3200947.3201010","DOI":"10.1145\/3200947.3201010"},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"Tan, M.: Multi-agent reinforcement learning: Independent versus cooperative agents. In: ICML (1993)","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Topin, N., Veloso, M.: Generation of policy-level explanations for reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 2514\u20132521 (2019)","DOI":"10.1609\/aaai.v33i01.33012514"},{"key":"10_CR29","doi-asserted-by":"publisher","unstructured":"Vouros, G.A.: Explainable deep reinforcement learning: state of the art and challenges. ACM Comput. Surv. 55, 1\u201339 (2022). https:\/\/doi.org\/10.1145\/3527448,just Accepted","DOI":"10.1145\/3527448,"},{"key":"10_CR30","unstructured":"Zemel, R.S., Pitassi, T.: A gradient-based boosting algorithm for regression problems. In: Proceedings of the 13th International Conference on Neural Information Processing Systems, NIPS 2000, pp. 675\u2013681. MIT Press, Cambridge, MA, USA (2000)"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Zhao, X., et al.: DEAR: deep reinforcement learning for online advertising impression in recommender systems. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35(1), pp. 750\u2013758, May 2021. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/16156","DOI":"10.1609\/aaai.v35i1.16156"}],"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\/978-3-031-40878-6_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T09:04:32Z","timestamp":1693818272000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-40878-6_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031408779","9783031408786"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-40878-6_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"5 September 2023","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":"London","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","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":"29 May 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 May 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"extraamas2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/extraamas.ehealth.hevs.ch\/","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":"26","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":"15","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":"1","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":"58% - 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":"Between 3 and 5","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":"~1\/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)"}}]}}