{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T02:50:11Z","timestamp":1784775011368,"version":"3.55.0"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031438349","type":"print"},{"value":"9783031438356","type":"electronic"}],"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\/978-3-031-43835-6_22","type":"book-chapter","created":{"date-parts":[[2023,9,14]],"date-time":"2023-09-14T14:32:18Z","timestamp":1694701938000},"page":"311-328","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Probabilistic Counterexample Guidance for\u00a0Safer Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Xiaotong","family":"Ji","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antonio","family":"Filieri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,9,15]]},"reference":[{"key":"22_CR1","unstructured":"Achiam, J., Held, D., Tamar, A., Abbeel, P.: Constrained policy optimization. In: International Conference on Machine Learning, pp. 22\u201331. PMLR (2017)"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Alshiekh, M., Bloem, R., Ehlers, R., K\u00f6nighofer, B., Niekum, S., Topcu, U.: Safe reinforcement learning via shielding. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"22_CR3","volume-title":"Principles of Model Checking","author":"C Baier","year":"2008","unstructured":"Baier, C., Katoen, J.P.: Principles of Model Checking. MIT press, Cambridge (2008)"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Bellman, R.: A Markovian decision process. J. Math. Mech., 679\u2013684 (1957)","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"22_CR5","unstructured":"Bharadhwaj, H., Kumar, A., Rhinehart, N., Levine, S., Shkurti, F., Garg, A.: Conservative safety critics for exploration. arXiv preprint arXiv:2010.14497 (2020)"},{"key":"22_CR6","unstructured":"Brockman, G., et al.: Openai gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"22_CR7","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1146\/annurev-control-042920-020211","volume":"5","author":"L Brunke","year":"2022","unstructured":"Brunke, L., Greeff, M., Hall, A.W., Yuan, Z., Zhou, S., Panerati, J., Schoellig, A.P.: Safe learning in robotics: from learning-based control to safe reinforcement learning. Ann. Rev. Control Rob. Auton. Syst. 5, 411\u2013444 (2022)","journal-title":"Ann. Rev. Control Rob. Auton. Syst."},{"issue":"5","key":"22_CR8","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1145\/290179.290184","volume":"45","author":"NH Bshouty","year":"1998","unstructured":"Bshouty, N.H., Goldman, S.A., Mathias, H.D., Suri, S., Tamaki, H.: Noise-tolerant distribution-free learning of general geometric concepts. J. ACM (JACM) 45(5), 863\u2013890 (1998)","journal-title":"J. ACM (JACM)"},{"key":"22_CR9","unstructured":"Buckman, J., Gelada, C., Bellemare, M.G.: The importance of pessimism in fixed-dataset policy optimization. arXiv preprint arXiv:2009.06799 (2020)"},{"key":"22_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1007\/978-3-030-30942-8_8","volume-title":"Formal Methods \u2013 The Next 30 Years","author":"M \u010ce\u0161ka","year":"2019","unstructured":"\u010ce\u0161ka, M., Hensel, C., Junges, S., Katoen, J.-P.: Counterexample-driven synthesis for probabilistic program sketches. In: ter Beek, M.H., McIver, A., Oliveira, J.N. (eds.) FM 2019. LNCS, vol. 11800, pp. 101\u2013120. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-30942-8_8"},{"key":"22_CR11","unstructured":"Dalal, G., Dvijotham, K., Vecerik, M., Hester, T., Paduraru, C., Tassa, Y.: Safe exploration in continuous action spaces. arXiv preprint arXiv:1801.08757 (2018)"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Desharnais, J., Laviolette, F., Tracol, M.: Approximate analysis of probabilistic processes: logic, simulation and games. In: 2008 Fifth International Conference on Quantitative Evaluation of Systems, pp. 264\u2013273. IEEE (2008)","DOI":"10.1109\/QEST.2008.42"},{"key":"22_CR13","volume-title":"Think Bayes","author":"A Downey","year":"2021","unstructured":"Downey, A.: Think Bayes. O\u2019Reilly Media, Sebastopol (2021)"},{"key":"22_CR14","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, vol. 32, no. 1 (2018)","DOI":"10.1609\/aaai.v32i1.12107"},{"key":"22_CR15","doi-asserted-by":"publisher","first-page":"515","DOI":"10.1613\/jair.3761","volume":"45","author":"J Garcia","year":"2012","unstructured":"Garcia, J., Fern\u00e1ndez, F.: Safe exploration of state and action spaces in reinforcement learning. J. Artif. Intell. Res. 45, 515\u2013564 (2012)","journal-title":"J. Artif. Intell. Res."},{"issue":"1","key":"22_CR16","first-page":"1437","volume":"16","author":"J Garc\u0131a","year":"2015","unstructured":"Garc\u0131a, J., Fern\u00e1ndez, F.: A comprehensive survey on safe reinforcement learning. J. Mach. Learn. Res. 16(1), 1437\u20131480 (2015)","journal-title":"J. Mach. Learn. Res."},{"key":"22_CR17","unstructured":"Gurobi Optimization, LLC: Gurobi Optimizer Reference Manual (2022). https:\/\/www.gurobi.com"},{"issue":"2","key":"22_CR18","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1109\/TSE.2009.5","volume":"35","author":"T Han","year":"2009","unstructured":"Han, T., Katoen, J.P., Berteun, D.: Counterexample generation in probabilistic model checking. IEEE Trans. Softw. Eng. 35(2), 241\u2013257 (2009)","journal-title":"IEEE Trans. Softw. Eng."},{"issue":"5","key":"22_CR19","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1007\/BF01211866","volume":"6","author":"H Hansson","year":"1994","unstructured":"Hansson, H., Jonsson, B.: A logic for reasoning about time and reliability. Formal Aspects Comput. 6(5), 512\u2013535 (1994)","journal-title":"Formal Aspects Comput."},{"key":"22_CR20","unstructured":"Hasanbeig, M., Abate, A., Kroening, D.: Logically-constrained reinforcement learning. arXiv preprint arXiv:1801.08099 (2018)"},{"key":"22_CR21","unstructured":"Hasanbeig, M., Kroening, D., Abate, A.: LCRL: Certified policy synthesis via logically-constrained reinforcement learning - implementation. https:\/\/github.com\/grockious\/lcrl"},{"key":"22_CR22","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":"22_CR23","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1007\/978-3-031-16336-4_11","volume-title":"Quantitative Evaluation of Systems, QEST","author":"M Hasanbeig","year":"2022","unstructured":"Hasanbeig, M., Kroening, D., Abate, A.: LCRL: certified policy synthesis via logically-constrained reinforcement learning. In: Abraham, E., Paolieri, M. (eds.) Quantitative Evaluation of Systems, QEST. LNCS, vol. 13479, pp. 217\u2013231. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-16336-4_11"},{"key":"22_CR24","unstructured":"Huang, J., Wu, F., Precup, D., Cai, Y.: Learning safe policies with expert guidance. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, NIPS\u201918, Curran Associates Inc., pp. 9123\u20139132 (2018)"},{"key":"22_CR25","unstructured":"Jansen, N., K\u00f6nighofer, B., Junges, S., Bloem, R.: Shielded decision-making in mdps. arXiv preprint arXiv:1807.06096 (2018)"},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Ji, X., Filieri, A.: Probabilistic counterexample guidance for safer reinforcement learning (extended version). arXiv preprint arXiv:2307.04927 (2023)","DOI":"10.1007\/978-3-031-43835-6_22"},{"key":"22_CR27","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/978-3-030-73959-1_12","volume-title":"Trustworthy AI - Integrating Learning, Optimization and Reasoning","author":"Y Kim","year":"2021","unstructured":"Kim, Y., Allmendinger, R., L\u00f3pez-Ib\u00e1\u00f1ez, M.: Safe learning and optimization techniques: towards a survey of the state of the art. In: Heintz, F., Milano, M., O\u2019Sullivan, B. (eds.) TAILOR 2020. LNCS (LNAI), vol. 12641, pp. 123\u2013139. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-73959-1_12"},{"key":"22_CR28","unstructured":"Kumar, A., Fu, J., Tucker, G., Levine, S.: Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction. Curran Associates Inc. (2019)"},{"key":"22_CR29","first-page":"1179","volume":"33","author":"A Kumar","year":"2020","unstructured":"Kumar, A., Zhou, A., Tucker, G., Levine, S.: Conservative q-learning for offline reinforcement learning. Adv. Neural. Inf. Process. Syst. 33, 1179\u20131191 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"4","key":"22_CR30","doi-asserted-by":"publisher","first-page":"699","DOI":"10.1287\/opre.14.4.699","volume":"14","author":"EL Lawler","year":"1966","unstructured":"Lawler, E.L., Wood, D.E.: Branch-and-bound methods: a survey. Oper. Res. 14(4), 699\u2013719 (1966)","journal-title":"Oper. Res."},{"key":"22_CR31","unstructured":"Levine, S., Kumar, A., Tucker, G., Fu, J.: Offline reinforcement learning: Tutorial, review, and perspectives on open problems. arXiv preprint arXiv:2005.01643 (2020)"},{"key":"22_CR32","unstructured":"Liu, A., Shi, G., Chung, S.J., Anandkumar, A., Yue, Y.: Robust regression for safe exploration in control. In: Learning for Dynamics and Control, pp. 608\u2013619. PMLR (2020)"},{"key":"22_CR33","doi-asserted-by":"crossref","unstructured":"Mason, G.R., Calinescu, R.C., Kudenko, D., Banks, A.: Assured reinforcement learning with formally verified abstract policies. In: 9th International Conference on Agents and Artificial Intelligence (ICAART), York (2017)","DOI":"10.5220\/0006156001050117"},{"issue":"1","key":"22_CR34","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1038\/ngeo2014","volume":"7","author":"AS McEwen","year":"2014","unstructured":"McEwen, A.S., et al.: Recurring slope lineae in equatorial regions of Mars. Nature Geosci. 7(1), 53\u201358 (2014)","journal-title":"Nature Geosci."},{"key":"22_CR35","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"key":"22_CR36","unstructured":"Moldovan, T.M., Abbeel, P.: Safe exploration in Markov decision processes. arXiv preprint arXiv:1205.4810 (2012)"},{"key":"22_CR37","unstructured":"OpenAI: Stable baselines version 3 - dqn. https:\/\/stable-baselines3.readthedocs.io\/en\/master\/modules\/dqn.html"},{"key":"22_CR38","doi-asserted-by":"crossref","unstructured":"Pham, T.H., De Magistris, G., Tachibana, R.: Optlayer-practical constrained optimization for deep reinforcement learning in the real world. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 6236\u20136243. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8460547"},{"key":"22_CR39","unstructured":"Prakash, B., Khatwani, M., Waytowich, N., Mohsenin, T.: Improving safety in reinforcement learning using model-based architectures and human intervention. arXiv preprint arXiv:1903.09328 (2019)"},{"key":"22_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1007\/978-3-642-38856-9_21","volume-title":"Static Analysis","author":"R Sharma","year":"2013","unstructured":"Sharma, R., Gupta, S., Hariharan, B., Aiken, A., Nori, A.V.: Verification as learning geometric concepts. In: Logozzo, F., F\u00e4hndrich, M. (eds.) SAS 2013. LNCS, vol. 7935, pp. 388\u2013411. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-38856-9_21"},{"key":"22_CR41","unstructured":"Siegel, N.Y., et al.: Keep doing what worked: Behavioral modelling priors for offline reinforcement learning. arXiv preprint arXiv:2002.08396 (2020)"},{"key":"22_CR42","doi-asserted-by":"crossref","unstructured":"Singh, G., P\u00fcschel, M., Vechev, M.: A practical construction for decomposing numerical abstract domains. Proc. ACM Program. Lang. 2(POPL) (2017)","DOI":"10.1145\/3158143"},{"key":"22_CR43","unstructured":"Stooke, A., Achiam, J., Abbeel, P.: Responsive safety in reinforcement learning by pid Lagrangian methods. In: International Conference on Machine Learning, pp. 9133\u20139143. PMLR (2020)"},{"key":"22_CR44","unstructured":"Sui, Y., Gotovos, A., Burdick, J., Krause, A.: Safe exploration for optimization with gaussian processes. In: International Conference on Machine Learning, pp. 997\u20131005. PMLR (2015)"},{"key":"22_CR45","unstructured":"Tessler, C., Mankowitz, D.J., Mannor, DS.: Reward constrained policy optimization. arXiv preprint arXiv:1805.11074 (2018)"},{"key":"22_CR46","unstructured":"Urp\u00ed, N.A., Curi, S., Krause, A.: Risk-averse offline reinforcement learning. arXiv preprint arXiv:2102.05371 (2021)"},{"key":"22_CR47","doi-asserted-by":"crossref","unstructured":"Wachi, A., Sui, Y., Yue, Y., Ono, M.: Safe exploration and optimization of constrained mdps using Gaussian processes. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.12103"},{"issue":"3","key":"22_CR48","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF00992698","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8(3), 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"key":"22_CR49","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1007\/978-3-642-40196-1_4","volume-title":"Quantitative Evaluation of Systems","author":"R Wimmer","year":"2013","unstructured":"Wimmer, R., Jansen, N., Vorpahl, A., \u00c1brah\u00e1m, E., Katoen, J.-P., Becker, B.: High-level counterexamples for probabilistic automata. In: Joshi, K., Siegle, M., Stoelinga, M., D\u2019Argenio, P.R. (eds.) QEST 2013. LNCS, vol. 8054, pp. 39\u201354. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-40196-1_4"},{"key":"22_CR50","unstructured":"Wu, Y., Tucker, G., Nachum, O.: Behavior regularized offline reinforcement learning. arXiv preprint arXiv:1911.11361 (2019)"},{"key":"22_CR51","doi-asserted-by":"crossref","unstructured":"Xu, H., Zhan, X., Zhu, X.: Constraints penalized q-learning for safe offline reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 8753\u20138760 (2022)","DOI":"10.1609\/aaai.v36i8.20855"},{"key":"22_CR52","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"662","DOI":"10.1007\/978-3-319-96145-3_38","volume-title":"Computer Aided Verification","author":"W Zhou","year":"2018","unstructured":"Zhou, W., Li, W.: Safety-aware apprenticeship learning. In: Chockler, H., Weissenbacher, G. (eds.) CAV 2018. LNCS, vol. 10981, pp. 662\u2013680. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-96145-3_38"}],"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\/978-3-031-43835-6_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,21]],"date-time":"2023-12-21T19:44:11Z","timestamp":1703187851000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43835-6_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031438349","9783031438356"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43835-6_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"15 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"A prototype Python implementation of our method is available at Github:\u00a0.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Data availability"}},{"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":"Antwerp","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Belgium","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":"20 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"qest2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.qest.org\/qest2023\/","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":"23","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":"52% - 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":"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)"}}]}}