{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T12:02:36Z","timestamp":1742990556559,"version":"3.40.3"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031150074"},{"type":"electronic","value":"9783031150081"}],"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\/978-3-031-15008-1_1","type":"book-chapter","created":{"date-parts":[[2022,9,4]],"date-time":"2022-09-04T23:02:47Z","timestamp":1662332567000},"page":"3-7","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Reinforcement Learning with\u00a0Guarantees that\u00a0Hold for\u00a0Ever"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9348-7684","authenticated-orcid":false,"given":"Ernst Moritz","family":"Hahn","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4220-3212","authenticated-orcid":false,"given":"Mateo","family":"Perez","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9093-9518","authenticated-orcid":false,"given":"Sven","family":"Schewe","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2085-2003","authenticated-orcid":false,"given":"Fabio","family":"Somenzi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9346-0126","authenticated-orcid":false,"given":"Ashutosh","family":"Trivedi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5560-0546","authenticated-orcid":false,"given":"Dominik","family":"Wojtczak","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,9,5]]},"reference":[{"key":"1_CR1","doi-asserted-by":"publisher","unstructured":"Bozkurt, A.K., Wang, Y., Zavlanos, M.M., Pajic, M.: Control synthesis from linear temporal logic specifications using model-free reinforcement learning. In: 2020 IEEE International Conference on Robotics and Automation, ICRA 2020, Paris, France, May 31\u2013August 31, 2020, pp. 10349\u201310355. IEEE (2020). https:\/\/doi.org\/10.1109\/ICRA40945.2020.9196796","DOI":"10.1109\/ICRA40945.2020.9196796"},{"key":"1_CR2","unstructured":"B\u00fcchi, J.R.: On a decision method in restricted second order arithmetic. In: Proceedings of the International Congress on Logic, Methodology, and Philosophy of Science, 1960, Berkeley, California, USA, pp. 1\u201311. Stanford University Press (1962)"},{"issue":"4","key":"1_CR3","doi-asserted-by":"publisher","first-page":"857","DOI":"10.1145\/210332.210339","volume":"42","author":"C Courcoubetis","year":"1995","unstructured":"Courcoubetis, C., Yannakakis, M.: The complexity of probabilistic verification. J. ACM 42(4), 857\u2013907 (1995)","journal-title":"J. ACM"},{"key":"1_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1007\/978-3-030-17462-0_27","volume-title":"Tools and Algorithms for the Construction and Analysis of Systems","author":"EM Hahn","year":"2019","unstructured":"Hahn, E.M., Perez, M., Schewe, S., Somenzi, F., Trivedi, A., Wojtczak, D.: Omega-regular objectives in model-free reinforcement learning. In: Vojnar, T., Zhang, L. (eds.) TACAS 2019. LNCS, vol. 11427, pp. 395\u2013412. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-17462-0_27"},{"key":"1_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1007\/978-3-030-59152-6_6","volume-title":"Automated Technology for Verification and Analysis","author":"EM Hahn","year":"2020","unstructured":"Hahn, E.M., Perez, M., Schewe, S., Somenzi, F., Trivedi, A., Wojtczak, D.: Faithful and Effective Reward Schemes for Model-Free Reinforcement Learning of Omega-Regular Objectives. In: Hung, D.V., Sokolsky, O. (eds.) ATVA 2020. LNCS, vol. 12302, pp. 108\u2013124. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59152-6_6"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Hahn, E.M., Perez, M., Schewe, S., Somenzi, F., Trivedi, A., Wojtczak, D.: Good-for-MDPS automata for probabilistic analysis and reinforcement learning. In: Tools and Algorithms for the Construction and Analysis of Systems, pp. 306\u2013323 (2020)","DOI":"10.1007\/978-3-030-45190-5_17"},{"key":"1_CR7","unstructured":"Hahn, E.M., Li, G., Schewe, S., Turrini, A., Zhang, L.: Lazy probabilistic model checking without determinisation. In: Proceedings of the 26th Conference on Concurrency Theory (CONCUR 2015), September 1\u20134, Madrid. LIPIcs, vol. 42, pp. 354\u2013367. Schloss Dagstuhl - Leibniz-Zentrum f\u00fcr Informatik, Germany (2015)"},{"key":"1_CR8","unstructured":"Trivedi, A., Wojtczak, D.: Model-free reinforcement learning for stochastic parity games. In: Konnov, I., Kov\u00e1cs, L. (eds.) 31st International Conference on Concurrency Theory, CONCUR 2020, 1\u20134 September 2020, Vienna, Austria (Virtual Conference). LIPIcs, vol. 171, pp. 21:1\u201321:16. Schloss Dagstuhl - Leibniz-Zentrum f\u00fcr Informatik (2020)"},{"key":"1_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1007\/978-3-030-81688-9_30","volume-title":"Computer Aided Verification","author":"EM Hahn","year":"2021","unstructured":"Hahn, E.M., Perez, M., Schewe, S., Somenzi, F., Trivedi, A., Wojtczak, D.: Model-free reinforcement learning for branching Markov decision processes. In: Silva, A., Leino, K.R.M. (eds.) CAV 2021. LNCS, vol. 12760, pp. 651\u2013673. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-81688-9_30"},{"key":"1_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1007\/11874683_26","volume-title":"Computer Science Logic","author":"TA Henzinger","year":"2006","unstructured":"Henzinger, T.A., Piterman, N.: Solving games without determinization. In: \u00c9sik, Z. (ed.) CSL 2006. LNCS, vol. 4207, pp. 395\u2013410. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11874683_26"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Hiromoto, M., Ushio, T.: Learning an optimal control policy for a Markov decision process under linear temporal logic specifications. In: Symposium Series on Computational Intelligence, pp. 548\u2013555, December 2015","DOI":"10.1109\/SSCI.2015.87"},{"key":"1_CR12","doi-asserted-by":"publisher","unstructured":"Manna, Z., Pnueli, A.: The Temporal Logic of Reactive and Concurrent Systems *Specification*. Springer, New York (1991). https:\/\/doi.org\/10.1007\/978-1-4612-0931-7","DOI":"10.1007\/978-1-4612-0931-7"},{"key":"1_CR13","unstructured":"Perrin, D., Pin, J.\u00c9.: Infinite Words: Automata, Semigroups. Logic and Games. Elsevier, Amsterdam (2004)"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Sadigh, D., Kim, E., Coogan, S., Sastry, S.S., Seshia, S.A.: A learning based approach to control synthesis of Markov decision processes for linear temporal logic specifications. In: IEEE Conference on Decision and Control (CDC), pp. 1091\u20131096, December 2014","DOI":"10.21236\/ADA623517"},{"key":"1_CR15","unstructured":"Schewe, S., Tang, Q., Zhanabekova, T.: Deciding what is good-for-MDPS. CoRR abs\/2202.07629 (2022), https:\/\/arxiv.org\/abs\/2202.07629"},{"key":"1_CR16","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, 2nd edn. MIT Press, London (2018)"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Thomas, W.: Handbook of Theoretical Computer Science, Chap. Automata on Infinite Objects, pp. 133\u2013191. The MIT Press\/Elsevier, London (1990)","DOI":"10.1016\/B978-0-444-88074-1.50009-3"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Vardi, M.Y.: Automatic verification of probabilistic concurrent finite-state programs. In: 26th Annual Symposium on Foundations of Computer Science, Portland, Oregon, USA, 21\u201323 October 1985. pp. 327\u2013338. IEEE Computer Society (1985)","DOI":"10.1109\/SFCS.1985.12"},{"key":"1_CR19","doi-asserted-by":"publisher","unstructured":"Wiering, M., van Otterlo, M. (eds.): Reinforcement Learning: State of the Art. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-27645-3","DOI":"10.1007\/978-3-642-27645-3"}],"container-title":["Lecture Notes in Computer Science","Formal Methods for Industrial Critical Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-15008-1_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,4]],"date-time":"2022-09-04T23:08:52Z","timestamp":1662332932000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-15008-1_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031150074","9783031150081"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-15008-1_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"5 September 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"FMICS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Formal Methods for Industrial Critical Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Warsaw","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Poland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"fmics2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/fmics2022.fsa.win.tue.nl\/","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":"22","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":"13","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":"59% - 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":"2.5","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)"}}]}}