{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T20:35:21Z","timestamp":1742934921252,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030851712"},{"type":"electronic","value":"9783030851729"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-85172-9_13","type":"book-chapter","created":{"date-parts":[[2021,8,18]],"date-time":"2021-08-18T23:04:46Z","timestamp":1629327886000},"page":"235-254","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Safe Learning for Near-Optimal Scheduling"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7266-0927","authenticated-orcid":false,"given":"Damien","family":"Busatto-Gaston","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0978-4457","authenticated-orcid":false,"given":"Debraj","family":"Chakraborty","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9814-6651","authenticated-orcid":false,"given":"Shibashis","family":"Guha","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1200-4952","authenticated-orcid":false,"given":"Guillermo A.","family":"P\u00e9rez","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3673-1097","authenticated-orcid":false,"given":"Jean-Fran\u00e7ois","family":"Raskin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,8,19]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Alshiekh, M., Bloem, R., Ehlers, R., K\u00f6nighofer, B., Niekum, S., Topcu, U.: Safe reinforcement learning via shielding. In: AAAI, pp. 2669\u20132678. AAAI Press (2018)","DOI":"10.1609\/aaai.v32i1.11797"},{"issue":"6","key":"13_CR2","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1109\/MSP.2017.2743240","volume":"34","author":"K Arulkumaran","year":"2017","unstructured":"Arulkumaran, K., Deisenroth, M.P., Brundage, M., Bharath, A.A.: Deep reinforcement learning: a brief survey. IEEE Signal Process. Mag. 34(6), 26\u201338 (2017)","journal-title":"IEEE Signal Process. Mag."},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Avni, G., Bloem, R., Chatterjee, K., Henzinger, T.A., K\u00f6nighofer, B., Pranger, S.: Run-time optimization for learned controllers through quantitative games. In: CAV, pp. 630\u2013649 (2019)","DOI":"10.1007\/978-3-030-25540-4_36"},{"issue":"1","key":"13_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TCIAIG.2012.2186810","volume":"4","author":"C Browne","year":"2012","unstructured":"Browne, C., et al.: A survey of Monte Carlo tree search methods. IEEE Trans. Comput. Intell. AI Games 4(1), 1\u201343 (2012). https:\/\/doi.org\/10.1109\/TCIAIG.2012.2186810","journal-title":"IEEE Trans. Comput. Intell. AI Games"},{"key":"13_CR5","doi-asserted-by":"publisher","unstructured":"Busatto-Gaston, D., Chakraborty, D., Raskin, J.: Monte carlo tree search guided by symbolic advice for MDPs. In: CONCUR, pp. 40:1\u201340:24 (2020). https:\/\/doi.org\/10.4230\/LIPIcs.CONCUR.2020.40","DOI":"10.4230\/LIPIcs.CONCUR.2020.40"},{"key":"13_CR6","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-0676-1","volume-title":"Hard Real-Time Computing Systems: Predictable Scheduling Algorithms and Applications","author":"GC Buttazzo","year":"2011","unstructured":"Buttazzo, G.C.: Hard Real-Time Computing Systems: Predictable Scheduling Algorithms and Applications, vol. 24. Springer, Boston (2011). https:\/\/doi.org\/10.1007\/978-1-4614-0676-1"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Chatterjee, K.: Robustness of structurally equivalent concurrent parity games. In: FOSSACS, pp. 270\u2013285 (2012)","DOI":"10.1007\/978-3-642-28729-9_18"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Chatterjee, K., Novotn\u00fd, P., P\u00e9rez, G.A., Raskin, J.F., Zikelic, D.: Optimizing expectation with guarantees in pomdps. In: AAAI, pp. 3725\u20133732 (2017)","DOI":"10.1609\/aaai.v31i1.11046"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Dehnert, C., Junges, S., Katoen, J., Volk, M.: A storm is coming: a modern probabilistic model checker. In: CAV (2017)","DOI":"10.1007\/978-3-319-63390-9_31"},{"key":"13_CR10","unstructured":"Dhariwal, P., et al.: Openai baselines (2017). https:\/\/github.com\/openai\/baselines"},{"key":"13_CR11","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4054-9","volume-title":"Competitive Markov Decision Processes","author":"J Filar","year":"1997","unstructured":"Filar, J., Vrieze, K.: Competitive Markov Decision Processes. Springer, New York (1997). https:\/\/doi.org\/10.1007\/978-1-4612-4054-9"},{"key":"13_CR12","doi-asserted-by":"publisher","unstructured":"Fu, J., Topcu, U.: Probably approximately correct MDP learning and control with temporal logic constraints. In: Fox, D., Kavraki, L.E., Kurniawati, H. (eds.) Robotics: Science and Systems X, University of California, Berkeley, USA, July 12\u201316, 2014 (2014). https:\/\/doi.org\/10.15607\/RSS.2014.X.039, http:\/\/www.roboticsproceedings.org\/rss10\/p39.html","DOI":"10.15607\/RSS.2014.X.039"},{"key":"13_CR13","unstructured":"Geeraerts, G., Guha, S., Raskin, J.F.: Safe and optimal scheduling for hard and soft tasks. In: FSTTCS. LIPIcs, vol. 122, pp. 36:1\u201336:22 (2018)"},{"issue":"2\u20133","key":"13_CR14","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1023\/A:1017932429737","volume":"49","author":"MJ Kearns","year":"2002","unstructured":"Kearns, M.J., Mansour, Y., Ng, A.Y.: A sparse sampling algorithm for near-optimal planning in large Markov decision processes. Mach. Learn. 49(2\u20133), 193\u2013208 (2002). https:\/\/doi.org\/10.1023\/A:1017932429737","journal-title":"Mach. Learn."},{"key":"13_CR15","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"13_CR16","unstructured":"Kret\u00ednsk\u00fd, J., P\u00e9rez, G.A., Raskin, J.F.: Learning-based mean-payoff optimization in an unknown MDP under omega-regular constraints. In: CONCUR. LIPIcs (2018)"},{"issue":"2","key":"13_CR17","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/BF01769259","volume":"10","author":"JF Mertens","year":"1981","unstructured":"Mertens, J.F., Neyman, A.: Stochastic games. Int. J. Game Theory 10(2), 53\u201366 (1981)","journal-title":"Int. J. Game Theory"},{"issue":"7540","key":"13_CR18","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":"1","key":"13_CR19","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1137\/0325013","volume":"25","author":"PJ Ramadge","year":"1987","unstructured":"Ramadge, P.J., Wonham, W.M.: Supervisory control of a class of discrete event processes. SIAM J. Control Opt. 25(1), 206\u2013230 (1987)","journal-title":"SIAM J. Control Opt."},{"issue":"7587","key":"13_CR20","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(7587), 484\u2013489 (2016). https:\/\/doi.org\/10.1038\/nature16961","journal-title":"Nature"},{"key":"13_CR21","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1023\/B:JOTP.0000011995.28536.ef","volume":"16","author":"E Solan","year":"2003","unstructured":"Solan, E.: Continuity of the value of competitive Markov decision processes. J. Theoret. Prob. 16, 831\u2013845 (2003)","journal-title":"J. Theoret. Prob."},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Thomas, W.: On the synthesis of strategies in infinite games. In: STACS, pp. 1\u201313 (1995)","DOI":"10.1007\/3-540-59042-0_57"},{"issue":"11","key":"13_CR23","doi-asserted-by":"publisher","first-page":"1134","DOI":"10.1145\/1968.1972","volume":"27","author":"LG Valiant","year":"1984","unstructured":"Valiant, L.G.: A theory of the learnable. Commun. ACM 27(11), 1134\u20131142 (1984)","journal-title":"Commun. ACM"},{"key":"13_CR24","first-page":"279","volume":"8","author":"CJCH Watkins","year":"1992","unstructured":"Watkins, C.J.C.H., Dayan, P.: Technical note Q-learning. Mach. Learn. 8, 279\u2013292 (1992)","journal-title":"Mach. Learn."}],"container-title":["Lecture Notes in Computer Science","Quantitative Evaluation of Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-85172-9_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,7]],"date-time":"2023-01-07T15:59:15Z","timestamp":1673107155000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-85172-9_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030851712","9783030851729"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-85172-9_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"19 August 2021","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":"Paris","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 August 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"qest2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.qest.org\/","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":"47","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":"21","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":"2","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":"45% - 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":"3.5","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":"5-6","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)"}},{"value":"1 keynote paper is also included.","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)"}}]}}