{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T15:43:14Z","timestamp":1787067794962,"version":"3.56.0"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030598532","type":"print"},{"value":"9783030598549","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-59854-9_2","type":"book-chapter","created":{"date-parts":[[2020,11,2]],"date-time":"2020-11-02T18:02:42Z","timestamp":1604340162000},"page":"11-17","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Tracking the Race Between Deep Reinforcement Learning and Imitation Learning"],"prefix":"10.1007","author":[{"given":"Timo P.","family":"Gros","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"H\u00f6ller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J\u00f6rg","family":"Hoffmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Verena","family":"Wolf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,3]]},"reference":[{"issue":"8","key":"2_CR1","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1038\/s42256-019-0070-z","volume":"1","author":"F Agostinelli","year":"2019","unstructured":"Agostinelli, F., McAleer, S., Shmakov, A., Baldi, P.: Solving the Rubik\u2019s Cube with deep reinforcement learning and search. Nat. Mach. Intell. 1(8), 356\u2013363 (2019)","journal-title":"Nat. Mach. Intell."},{"issue":"1\u20132","key":"2_CR2","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/0004-3702(94)00011-O","volume":"72","author":"AG Barto","year":"1995","unstructured":"Barto, A.G., Bradtke, S.J., Singh, S.P.: Learning to act using real-time dynamic programming. Artif. Intell. 72(1\u20132), 81\u2013138 (1995)","journal-title":"Artif. Intell."},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Bonet, B., Geffner, H.: GPT: a tool for planning with uncertainty and partial information. In: Proceedings of the IJCAI Workshop on Planning with Uncertainty and Incomplete Information, pp. 82\u201387 (2001)","DOI":"10.1007\/3-540-44652-4_2"},{"key":"2_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1007\/978-3-030-50086-3_6","volume-title":"Formal Techniques for Distributed Objects, Components, and Systems","author":"TP Gros","year":"2020","unstructured":"Gros, T.P., Hermanns, H., Hoffmann, J., Klauck, M., Steinmetz, M.: Deep statistical model checking. In: Gotsman, A., Sokolova, A. (eds.) FORTE 2020. LNCS, vol. 12136, pp. 96\u2013114. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-50086-3_6"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Gros, T.P., H\u00f6ller, D., Hoffmann, J., Wolf, V.: Tracking the race between deep reinforcement learning and imitation learning \u2013 extended version. arXiv preprint arXiv:2008.00766 (2020)","DOI":"10.1007\/978-3-030-59854-9_2"},{"key":"2_CR6","unstructured":"Judah, K., Fern, A.P., Dietterich, T.G., Tadepalli, P.: Active imitation learning: formal and practical reductions to I.I.D. learning. J. Mach. Learn. Res. 15(120), 4105\u20134143 (2014)"},{"key":"2_CR7","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1007\/978-1-4842-2766-4_12","volume-title":"Deep Learning with Python","author":"N Ketkar","year":"2017","unstructured":"Ketkar, N.: Introduction to PyTorch. In: Ketkar, N. (ed.) Deep Learning with Python, pp. 195\u2013208. Apress, Berkeley (2017). https:\/\/doi.org\/10.1007\/978-1-4842-2766-4_12"},{"key":"2_CR8","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., Riedmiller, M.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"issue":"7540","key":"2_CR9","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"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Pineda, L.E., Zilberstein, S.: Planning under uncertainty using reduced models: revisiting determinization. In: Proceedings of the 24th International Conference on Automated Planning and Scheduling (ICAPS), pp. 217\u2013225. AAAI Press (2014)","DOI":"10.1609\/icaps.v24i1.13636"},{"key":"2_CR11","unstructured":"Ross, S., Gordon, G.J., Bagnell, D.: A reduction of imitation learning and structured prediction to no-regret online learning. In: Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS). JMLR Proceedings, vol. 15, pp. 627\u2013635. JMLR.org (2011)"},{"issue":"6","key":"2_CR12","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1016\/S1364-6613(99)01327-3","volume":"3","author":"S Schaal","year":"1999","unstructured":"Schaal, S.: Is imitation learning the route to humanoid robots? Trends Cogn. Sci. 3(6), 233\u2013242 (1999)","journal-title":"Trends Cogn. Sci."},{"key":"2_CR13","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., et al.: Mastering the game of Go with deep neural networks and tree search. Nature 529, 484\u2013503 (2016)","journal-title":"Nature"},{"issue":"6419","key":"2_CR14","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1126\/science.aar6404","volume":"362","author":"D Silver","year":"2018","unstructured":"Silver, D., et al.: A general reinforcement learning algorithm that masters Chess, Shogi, and Go through self-play. Science 362(6419), 1140\u20131144 (2018)","journal-title":"Science"},{"key":"2_CR15","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., et al.: Mastering the game of Go without human knowledge. Nature 550, 354\u2013359 (2017)","journal-title":"Nature"},{"key":"2_CR16","series-title":"Adaptive Computation and Machine Learning","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. Adaptive Computation and Machine Learning, 2nd edn. The MIT Press, Cambridge (2018)","edition":"2"}],"container-title":["Lecture Notes in Computer Science","Quantitative Evaluation of Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-59854-9_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,26]],"date-time":"2022-11-26T03:00:57Z","timestamp":1669431657000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-59854-9_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030598532","9783030598549"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-59854-9_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"3 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"QEST","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Quantitative Evaluation of Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vienna","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Austria","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 September 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"qest2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.qest.org\/qest2020\/","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":"42","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":"12","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":"7","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":"29% - 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":"3,10","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":"4,06","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}