{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T16:59:16Z","timestamp":1762102756996,"version":"3.40.3"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031163357"},{"type":"electronic","value":"9783031163364"}],"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\/978-3-031-16336-4_11","type":"book-chapter","created":{"date-parts":[[2022,9,10]],"date-time":"2022-09-10T18:02:40Z","timestamp":1662832960000},"page":"217-231","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["LCRL: Certified Policy Synthesis via\u00a0Logically-Constrained Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Mohammadhosein","family":"Hasanbeig","sequence":"first","affiliation":[]},{"given":"Daniel","family":"Kroening","sequence":"additional","affiliation":[]},{"given":"Alessandro","family":"Abate","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,9,11]]},"reference":[{"issue":"11","key":"11_CR1","doi-asserted-by":"publisher","first-page":"2724","DOI":"10.1016\/j.automatica.2008.03.027","volume":"44","author":"A Abate","year":"2008","unstructured":"Abate, A., Prandini, M., Lygeros, J., Sastry, S.: Probabilistic reachability and safety for controlled discrete time stochastic hybrid systems. Automatica 44(11), 2724\u20132734 (2008)","journal-title":"Automatica"},{"key":"11_CR2","unstructured":"Andreas, J., Klein, D., Levine, S.: Modular multitask reinforcement learning with policy sketches. In: ICML, vol. 70, pp. 166\u2013175 (2017)"},{"key":"11_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. JAIR 47, 253\u2013279 (2013)","journal-title":"JAIR"},{"key":"11_CR4","unstructured":"Bertsekas, D.P., Shreve, S.: Stochastic Optimal Control: The Discrete-Time Case. Athena Scientific (2004)"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Bertsekas, D.P., Tsitsiklis, J.N.: Neuro-dynamic Programming, vol. 1. Athena Scientific (1996)","DOI":"10.1109\/CDC.1995.478953"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Bozkurt, A.K., Wang, Y., Zavlanos, M.M., Pajic, M.: Control synthesis from linear temporal logic specifications using model-free reinforcement learning. arXiv preprint:1909.07299 (2019)","DOI":"10.1109\/ICRA40945.2020.9196796"},{"key":"11_CR7","unstructured":"Brockman, G., et al.: OpenAI gym. arXiv preprint:1606.01540 (2016)"},{"issue":"4","key":"11_CR8","doi-asserted-by":"publisher","first-page":"7973","DOI":"10.1109\/LRA.2021.3101544","volume":"6","author":"M Cai","year":"2021","unstructured":"Cai, M., Hasanbeig, M., Xiao, S., Abate, A., Kan, Z.: Modular deep reinforcement learning for continuous motion planning with temporal logic. IEEE Robot. Aut. Lett. 6(4), 7973\u20137980 (2021). https:\/\/doi.org\/10.1109\/LRA.2021.3101544","journal-title":"IEEE Robot. Aut. Lett."},{"key":"11_CR9","unstructured":"Clarke Jr, E.M., Grumberg, O., Kroening, D., Peled, D., Veith, H.: Model Checking. MIT Press, London (2018)"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"De Giacomo, G., Iocchi, L., Favorito, M., Patrizi, F.: Foundations for restraining bolts: Reinforcement learning with LTLf\/LDLf restraining specifications. In: ICAPS, vol. 29, pp. 128\u2013136 (2019)","DOI":"10.1609\/icaps.v29i1.3549"},{"key":"11_CR11","unstructured":"Favorito, M.: Reinforcement learning framework for temporal goals. https:\/\/github.com\/whitemech\/temprl (2020)"},{"key":"11_CR12","unstructured":"Fulton, N.: Verifiably safe autonomy for cyber-physical systems. Ph.D. thesis, Carnegie Mellon University Pittsburgh (2018)"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Fulton, N., Platzer, A.: Safe reinforcement learning via formal methods: Toward safe control through proof and learning. In: Proceedings of the AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12107"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Fulton, N., Platzer, A.: Verifiably safe off-model reinforcement learning. In: TACAS, pp. 413\u2013430 (2019)","DOI":"10.1007\/978-3-030-17462-0_28"},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Gordon, G.J.: Stable function approximation in dynamic programming. In: Proceedings of the Twelfth International Conference on Machine Learning, pp. 261\u2013268. Elsevier (1995)","DOI":"10.1016\/B978-1-55860-377-6.50040-2"},{"key":"11_CR16","unstructured":"Gunter, E.: From natural language to linear temporal logic: Aspects of specifying embedded systems in LTL. In: Workshop on Software Engineering for Embedded Systems: From Requirements to Implementation (2003)"},{"key":"11_CR17","unstructured":"Hahn, E.M., Perez, M., Schewe, S., Somenzi, F., Trivedi, A., Wojtczak, D.: Mungojerrie: reinforcement learning of linear-time objectives. arXiv preprint arXiv:2106.09161 (2021)"},{"key":"11_CR18","unstructured":"Hasanbeig, M.: Safe and certified reinforcement learning with logical constraints. Ph.D. thesis, University of Oxford (2020)"},{"key":"11_CR19","unstructured":"Hasanbeig, M., Abate, A., Kroening, D.: Logically-constrained reinforcement learning. arXiv preprint:1801.08099 (2018)"},{"key":"11_CR20","unstructured":"Hasanbeig, M., Abate, A., Kroening, D.: Certified reinforcement learning with logic guidance. arXiv preprint:1902.00778 (2019)"},{"key":"11_CR21","unstructured":"Hasanbeig, M., Abate, A., Kroening, D.: Logically-constrained neural fitted Q-iteration. In: AAMAS. pp. 2012\u20132014. International Foundation for Autonomous Agents and Multiagent Systems (2019)"},{"key":"11_CR22","unstructured":"Hasanbeig, M., Abate, A., Kroening, D.: Cautious reinforcement learning with logical constraints. In: AAMAS. International Foundation for Autonomous Agents and Multiagent Systems (2020)"},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Hasanbeig, M., Kantaros, Y., Abate, A., Kroening, D., Pappas, G.J., Lee, I.: Reinforcement learning for temporal logic control synthesis with probabilistic satisfaction guarantees. In: Proceedings of the 58th Conference on Decision and Control, pp. 5338\u20135343. IEEE (2019)","DOI":"10.1109\/CDC40024.2019.9028919"},{"key":"11_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-030-57628-8_1","volume-title":"Formal Modeling and Analysis of Timed Systems","author":"M Hasanbeig","year":"2020","unstructured":"Hasanbeig, M., Kroening, D., Abate, A.: Deep reinforcement learning with temporal logics. In: Bertrand, N., Jansen, N. (eds.) FORMATS 2020. LNCS, vol. 12288, pp. 1\u201322. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-57628-8_1"},{"key":"11_CR25","unstructured":"Hasanbeig, M., Kroening, D., Abate, A.: Towards verifiable and safe model-free reinforcement learning. In: Proceedings of Workshop on Artificial Intelligence and Formal Verification, Logics, Automata and Synthesis (OVERLAY), pp. 1\u201310. Italian Association for Artificial Intelligence (2020)"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Hasanbeig, M., Yogananda Jeppu, N., Abate, A., Melham, T., Kroening, D.: DeepSynth: Program synthesis for automatic task segmentation in deep reinforcement learning. In: AAAI Conference on Artificial Intelligence. Association for the Advancement of Artificial Intelligence (2021)","DOI":"10.1609\/aaai.v35i9.16935"},{"key":"11_CR27","doi-asserted-by":"publisher","unstructured":"Hensel, C., Junges, S., Katoen, J.-P., Quatmann, T., Volk, M.: The probabilistic model checker Storm. Int. J. Softw. Tools Technol. Transfer 22, 1\u201322 (2021). https:\/\/doi.org\/10.1007\/s10009-021-00633-z","DOI":"10.1007\/s10009-021-00633-z"},{"key":"11_CR28","doi-asserted-by":"crossref","unstructured":"Hunt, N., Fulton, N., Magliacane, S., Hoang, N., Das, S., Solar-Lezama, A.: Verifiably safe exploration for end-to-end reinforcement learning. arXiv preprint arXiv:2007.01223 (2020)","DOI":"10.1145\/3447928.3456653"},{"key":"11_CR29","unstructured":"Icarte, R.T., Klassen, T., Valenzano, R., McIlraith, S.: Using reward machines for high-level task specification and decomposition in reinforcement learning. In: ICML, pp. 2107\u20132116 (2018)"},{"key":"11_CR30","unstructured":"Jothimurugan, K., Alur, R., Bastani, O.: A composable specification language for reinforcement learning tasks. In: NeurIPS, pp. 13041\u201313051 (2019)"},{"key":"11_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/978-3-662-54580-5_7","volume-title":"Tools and Algorithms for the Construction and Analysis of Systems","author":"D Kini","year":"2017","unstructured":"Kini, D., Viswanathan, M.: Optimal translation of LTL to limit deterministic automata. In: Legay, A., Margaria, T. (eds.) TACAS 2017. LNCS, vol. 10206, pp. 113\u2013129. Springer, Heidelberg (2017). https:\/\/doi.org\/10.1007\/978-3-662-54580-5_7"},{"key":"11_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1007\/978-3-030-01090-4_34","volume-title":"Automated Technology for Verification and Analysis","author":"J K\u0159et\u00ednsk\u00fd","year":"2018","unstructured":"K\u0159et\u00ednsk\u00fd, J., Meggendorfer, T., Sickert, S.: Owl: a library for $$\\omega $$-words, automata, and LTL. In: Lahiri, S.K., Wang, C. (eds.) ATVA 2018. LNCS, vol. 11138, pp. 543\u2013550. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01090-4_34"},{"key":"11_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1007\/978-3-642-22110-1_47","volume-title":"Computer Aided Verification","author":"M Kwiatkowska","year":"2011","unstructured":"Kwiatkowska, M., Norman, G., Parker, D.: PRISM 4.0: a. In: Gopalakrishnan, G., Qadeer, S. (eds.) CAV 2011. LNCS, vol. 6806, pp. 585\u2013591. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-22110-1_47"},{"issue":"6","key":"11_CR34","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1016\/j.engappai.2004.08.005","volume":"17","author":"IS Lee","year":"2004","unstructured":"Lee, I.S., Lau, H.Y.: Adaptive state space partitioning for reinforcement learning. Eng. Appl. Artif. Intell. 17(6), 577\u2013588 (2004)","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"1","key":"11_CR35","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1016\/S0095-0696(02)00031-1","volume":"46","author":"RG Newell","year":"2003","unstructured":"Newell, R.G., Pizer, W.A.: Discounting the distant future: how much do uncertain rates increase valuations? J. Environ. Econ. Manag 46(1), 52\u201371 (2003)","journal-title":"J. Environ. Econ. Manag"},{"key":"11_CR36","doi-asserted-by":"crossref","unstructured":"Nikora, A.P., Balcom, G.: Automated identification of LTL patterns in natural language requirements. In: ISSRE, pp. 185\u2013194. IEEE (2009)","DOI":"10.1109\/ISSRE.2009.15"},{"key":"11_CR37","doi-asserted-by":"crossref","unstructured":"Pitis, S.: Rethinking the discount factor in reinforcement learning: a decision theoretic approach. arXiv preprint:1902.02893 (2019)","DOI":"10.1609\/aaai.v33i01.33017949"},{"key":"11_CR38","doi-asserted-by":"crossref","unstructured":"Sadigh, D., Kim, E.S., 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: CDC, pp. 1091\u20131096. IEEE (2014)","DOI":"10.21236\/ADA623517"},{"key":"11_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1007\/978-3-319-41540-6_17","volume-title":"Computer Aided Verification","author":"S Sickert","year":"2016","unstructured":"Sickert, S., Esparza, J., Jaax, S., K\u0159et\u00ednsk\u00fd, J.: Limit-deterministic B\u00fcchi automata for linear temporal logic. In: Chaudhuri, S., Farzan, A. (eds.) CAV 2016. LNCS, vol. 9780, pp. 312\u2013332. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-41540-6_17"},{"key":"11_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1007\/978-3-319-46520-3_9","volume-title":"Automated Technology for Verification and Analysis","author":"S Sickert","year":"2016","unstructured":"Sickert, S., K\u0159et\u00ednsk\u00fd, J.: MoChiBA: probabilistic LTL model checking using limit-deterministic B\u00fcchi automata. In: Artho, C., Legay, A., Peled, D. (eds.) ATVA 2016. LNCS, vol. 9938, pp. 130\u2013137. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46520-3_9"},{"key":"11_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1007\/978-3-662-46681-0_23","volume-title":"Tools and Algorithms for the Construction and Analysis of Systems","author":"SEZ Soudjani","year":"2015","unstructured":"Soudjani, S.E.Z., Gevaerts, C., Abate, A.: FAUST$$^{\\sf 2}$$: $$\\underline{\\text{ F }}$$ormal $$\\underline{\\text{ A }}$$bstractions of $$\\underline{\\text{ U }}$$ncountable-$$\\underline{\\text{ ST }}$$ate $$\\underline{\\text{ ST }}$$ochastic processes. In: Baier, C., Tinelli, C. (eds.) TACAS 2015. LNCS, vol. 9035, pp. 272\u2013286. Springer, Heidelberg (2015). https:\/\/doi.org\/10.1007\/978-3-662-46681-0_23"},{"key":"11_CR42","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, vol. 1. MIT Press, Cambridge (1998)"},{"key":"11_CR43","unstructured":"Tassa, Y., et al.: Deepmind control suite. arXiv preprint:1801.00690 (2018)"},{"key":"11_CR44","doi-asserted-by":"crossref","unstructured":"Voronoi, G.: Nouvelles applications des param\u00e8tres continus \u00e0 la th\u00e9orie des formes quadratiques. Deuxi\u00e8me m\u00e9moire. Recherches sur les parall\u00e9llo\u00e8dres primitifs. Journal f\u00fcr die reine und angewandte Mathematik 134, 198\u2013287 (1908)","DOI":"10.1515\/crll.1908.134.198"},{"issue":"5","key":"11_CR45","first-page":"369","volume":"39","author":"Q Wei","year":"2011","unstructured":"Wei, Q., Guo, X.: Markov decision processes with state-dependent discount factors and unbounded rewards\/costs. Oper. Res. Lett. 39(5), 369\u2013374 (2011)","journal-title":"Oper. Res. Lett."},{"key":"11_CR46","doi-asserted-by":"crossref","unstructured":"Yan, R., Cheng, C.H., Chai, Y.: Formal consistency checking over specifications in natural languages. In: Proceedings of the 2015 Design, Automation & Test in Europe Conference & Exhibition, pp. 1677\u20131682. EDA Consortium (2015)","DOI":"10.7873\/DATE.2015.0452"},{"key":"11_CR47","doi-asserted-by":"crossref","unstructured":"Yoshida, N., Uchibe, E., Doya, K.: Reinforcement learning with state-dependent discount factor. In: ICDL, pp. 1\u20136. IEEE (2013)","DOI":"10.1109\/DevLrn.2013.6652533"}],"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\/978-3-031-16336-4_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T16:49:08Z","timestamp":1727974148000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-16336-4_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031163357","9783031163364"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-16336-4_11","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":"11 September 2022","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":"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":"12 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"qest2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.qest.org\/qest2022\/","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":"44","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":"19","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":"43% - 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":"3-4","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)"}}]}}