{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T14:16:08Z","timestamp":1788012968592,"version":"build-2784847793"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032352972","type":"print"},{"value":"9783032352989","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,30]],"date-time":"2026-08-30T00:00:00Z","timestamp":1788048000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,30]],"date-time":"2026-08-30T00:00:00Z","timestamp":1788048000000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-35298-9_7","type":"book-chapter","created":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T13:24:23Z","timestamp":1788009863000},"page":"114-133","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Robust Parameter Learning for\u00a0Uncertain MDPs"],"prefix":"10.1007","author":[{"given":"Yannik","family":"Schnitzer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessandro","family":"Abate","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Parker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,30]]},"reference":[{"key":"7_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1007\/978-3-030-25540-4_29","volume-title":"Computer Aided Verification","author":"P Ashok","year":"2019","unstructured":"Ashok, P., K\u0159et\u00ednsk\u00fd, J., Weininger, M.: PAC Statistical Model Checking for Markov Decision Processes and Stochastic Games. In: Dillig, I., Tasiran, S. (eds.) CAV 2019. LNCS, vol. 11561, pp. 497\u2013519. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-25540-4_29"},{"key":"7_CR2","unstructured":"Auer, P., Jaksch, T., Ortner, R.: Near-optimal regret bounds for reinforcement learning. In: NIPS, pp. 89\u201396. Curran Associates, Inc. (2008)"},{"key":"7_CR3","unstructured":"Ayoub, A., Jia, Z., Szepesvari, C., Wang, M., Yang, L.: Model-based reinforcement learning with value-targeted regression. In: Proceedings of the 37th International Conference on Machine Learning, vol. 119, pp. 463\u2013474. PMLR (2020)"},{"key":"7_CR4","doi-asserted-by":"publisher","unstructured":"Badings, T., Junges, S., Marandi, A., Topcu, U., Jansen, N.: Efficient sensitivity analysis for parametric robust Markov chains. In: Enea, C., Lal, A. (eds.) CAV (3), Lecture Notes in Computer Science, pp. 62\u201385. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-37709-9_4","DOI":"10.1007\/978-3-031-37709-9_4"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Badings, T.S., Abate, A., Jansen, N., Parker, D., Poonawala, H.A. , Stoelinga, M.: Sampling-based robust control of autonomous systems with non-Gaussian noise. In: AAAI, pp. 9669\u20139678. AAAI Press (2022)","DOI":"10.1609\/aaai.v36i9.21201"},{"key":"7_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"326","DOI":"10.1007\/978-3-642-19835-9_30","volume-title":"Tools and Algorithms for the Construction and Analysis of Systems","author":"E Bartocci","year":"2011","unstructured":"Bartocci, E., Grosu, R., Katsaros, P., Ramakrishnan, C.R., Smolka, S.A.: Model Repair for Probabilistic Systems. In: Abdulla, P.A., Leino, K.R.M. (eds.) TACAS 2011. LNCS, vol. 6605, pp. 326\u2013340. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-19835-9_30"},{"key":"7_CR7","unstructured":"Bertsimas, D., Tsitsiklis, J.N.: Introduction to linear optimization, volume\u00a06 of Athena scientific optimization and computation series. Athena Scientific (1997)"},{"key":"7_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1007\/3-540-60692-0_70","volume-title":"Foundations of Software Technology and Theoretical Computer Science","author":"A Bianco","year":"1995","unstructured":"Bianco, A., de Alfaro, L.: Model checking of probabilistic and nondeterministic systems. In: Thiagarajan, P.S. (ed.) FSTTCS 1995. LNCS, vol. 1026, pp. 499\u2013513. Springer, Heidelberg (1995). https:\/\/doi.org\/10.1007\/3-540-60692-0_70"},{"issue":"1","key":"7_CR9","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1109\/TR.2015.2452931","volume":"65","author":"R Calinescu","year":"2016","unstructured":"Calinescu, R., Ghezzi, C., Johnson, K., Pezz\u00e8, M., Rafiq, Y., Tamburrelli, G.: Formal verification with confidence intervals to establish quality of service properties of software systems. IEEE Trans. Reliab. 65(1), 107\u2013125 (2016)","journal-title":"IEEE Trans. Reliab."},{"issue":"6","key":"7_CR10","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1007\/s00236-016-0265-2","volume":"54","author":"M Ceska","year":"2017","unstructured":"Ceska, M., Dannenberg, F., Paoletti, N., Kwiatkowska, M., Brim, L.: Precise parameter synthesis for stochastic biochemical systems. Acta Informatica 54(6), 589\u2013623 (2017)","journal-title":"Acta Informatica"},{"issue":"4","key":"7_CR11","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1093\/biomet\/26.4.404","volume":"26","author":"CJ Clopper","year":"1934","unstructured":"Clopper, C.J., Pearson, E.S.: The use of confidence or fiducial limits illustrated in the case of the binomial. Biometrika 26(4), 404\u2013413 (1934)","journal-title":"Biometrika"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Cubuktepe, M., et al.: Sequential convex programming for the efficient verification of parametric mdps. In: TACAS (2), Lecture Notes in Computer Science, pp. 133\u2013150 (2017)","DOI":"10.1007\/978-3-662-54580-5_8"},{"issue":"12","key":"7_CR13","doi-asserted-by":"publisher","first-page":"6333","DOI":"10.1109\/TAC.2021.3133265","volume":"67","author":"M Cubuktepe","year":"2022","unstructured":"Cubuktepe, M., Jansen, N., Junges, S., Katoen, J.-P., Topcu, U.: Convex optimization for parameter synthesis in MDPs. IEEE Trans. Autom. Control 67(12), 6333\u20136348 (2022)","journal-title":"IEEE Trans. Autom. Control"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Engelen, K., P\u00e9rez, G.A., Suilen, M.: Data-efficient safe policy improvement using parametric structure. CoRR, abs\/2507.15532 (2025)","DOI":"10.3233\/FAIA251392"},{"key":"7_CR15","unstructured":"Fruit, R., Pirotta, M., Lazaric, A., Brunskill, E.: Regret minimization in MDPs with options without prior knowledge. In: NIPS, pp. 3166\u20133176 (2017)"},{"issue":"4","key":"7_CR16","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1007\/s10898-016-0450-4","volume":"67","author":"AM Gleixner","year":"2017","unstructured":"Gleixner, A.M., Berthold, T., M\u00fcller, B., Weltge, S.: Three enhancements for optimization-based bound tightening. J. Glob. Optim. 67(4), 731\u2013757 (2017)","journal-title":"J. Glob. Optim."},{"key":"7_CR17","doi-asserted-by":"publisher","unstructured":"Hahn, E.M., Han, T., Zhang, L.: Synthesis for PCTL in parametric Markov decision processes. In: Bobaru, M., Havelund, K., Holzmann, G.J., Joshi, R. (eds.) NASA Formal Methods, Lecture Notes in Computer Science, pp. 146\u2013161. Springer, Cham (2011). https:\/\/doi.org\/10.1007\/978-3-642-20398-5_12","DOI":"10.1007\/978-3-642-20398-5_12"},{"key":"7_CR18","doi-asserted-by":"publisher","unstructured":"Heck, L., Quatmann, T., Spel, J., Katoen, JP., Junges, S.: Generalized parameter lifting: Finer abstractions for parametric markov chains. In: D\u00b4Souza, M., Komondoor, R., Srivathsan, B. (eds) ATVA, Lecture Notes in Computer Science, pp. 207\u2013230. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-032-08707-2_10","DOI":"10.1007\/978-3-032-08707-2_10"},{"issue":"2","key":"7_CR19","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1287\/moor.1040.0129","volume":"30","author":"GN Iyengar","year":"2005","unstructured":"Iyengar, G.N.: Robust dynamic programming. Math. Oper. Res. 30(2), 257\u2013280 (2005)","journal-title":"Math. Oper. Res."},{"issue":"1","key":"7_CR20","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1007\/s10703-023-00442-x","volume":"62","author":"S Junges","year":"2024","unstructured":"Junges, S., \u00c1brah\u00e1m, E., Hensel, C., Jansen, N., Katoen, J.-P., Quatmann, T., Volk, M.: Parameter synthesis for Markov models: covering the parameter space. Formal Methods Syst. Des. 62(1), 181\u2013259 (2024)","journal-title":"Formal Methods Syst. Des."},{"key":"7_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1007\/978-3-662-49674-9_8","volume-title":"Tools and Algorithms for the Construction and Analysis of Systems","author":"S Junges","year":"2016","unstructured":"Junges, S., Jansen, N., Dehnert, C., Topcu, U., Katoen, J.-P.: Safety-Constrained Reinforcement Learning for MDPs. In: Chechik, M., Raskin, J.-F. (eds.) TACAS 2016. LNCS, vol. 9636, pp. 130\u2013146. Springer, Heidelberg (2016). https:\/\/doi.org\/10.1007\/978-3-662-49674-9_8"},{"key":"7_CR22","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: Verification of Probabilistic Real-Time Systems. 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":"1","key":"7_CR23","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1007\/s00165-006-0015-2","volume":"19","author":"R Lanotte","year":"2007","unstructured":"Lanotte, R., Maggiolo-Schettini, A., Troina, A.: Parametric probabilistic transition systems for system design and analysis. Formal Aspects Comput. 19(1), 93\u2013109 (2007)","journal-title":"Formal Aspects Comput."},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Lobo, M.S., Vandenberghe, L., Boyd, S., Lebret, H.: Applications of second-order cone programming. Linear Algebra Appl. 284(1\u20133), 193\u2013228 (1998)","DOI":"10.1016\/S0024-3795(98)10032-0"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Long, F., Rinard, M.C.: Automatic patch generation by learning correct code. In: POPL, pp. 298\u2013312. ACM (2016)","DOI":"10.1145\/2837614.2837617"},{"issue":"1","key":"7_CR26","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1007\/BF01580665","volume":"10","author":"GP McCormick","year":"1976","unstructured":"McCormick, G.P.: Computability of global solutions to factorable nonconvex programs: Part I - convex underestimating problems. Math. Program. 10(1), 147\u2013175 (1976)","journal-title":"Math. Program."},{"key":"7_CR27","doi-asserted-by":"publisher","unstructured":"Meggendorfer, T., Weininger, M., Wienh\u00f6ft, P.: What are the odds? improving statistical model checking of Markov decision processes. In: Prabhakar, P., Vandin, A. (eds.) Proceedings 2nd International Joint Conference on Quantitative Evaluation of Systems and Formal Modeling and Analysis of Timed Systems (QEST+FORMATS\u201925), LNCS, pp. 195\u2013218. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-032-05792-1_11","DOI":"10.1007\/978-3-032-05792-1_11"},{"issue":"5","key":"7_CR28","doi-asserted-by":"publisher","first-page":"780","DOI":"10.1287\/opre.1050.0216","volume":"53","author":"A Nilim","year":"2005","unstructured":"Nilim, A., El Ghaoui, L.: Robust control of Markov decision processes with uncertain transition matrices. Oper. Res. 53(5), 780\u2013798 (2005)","journal-title":"Oper. Res."},{"key":"7_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/978-3-319-43425-4_3","volume-title":"Quantitative Evaluation of Systems","author":"E Polgreen","year":"2016","unstructured":"Polgreen, E., Wijesuriya, V.B., Haesaert, S., Abate, A.: Data-Efficient Bayesian Verification of Parametric Markov Chains. In: Agha, G., Van Houdt, B. (eds.) QEST 2016. LNCS, vol. 9826, pp. 35\u201351. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-43425-4_3"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. Wiley Series in Probability and Statistics. Wiley (1994)","DOI":"10.1002\/9780470316887"},{"key":"7_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1007\/978-3-319-46520-3_4","volume-title":"Automated Technology for Verification and Analysis","author":"T Quatmann","year":"2016","unstructured":"Quatmann, T., Dehnert, C., Jansen, N., Junges, S., Katoen, J.-P.: Parameter Synthesis for Markov Models: Faster Than Ever. In: Artho, C., Legay, A., Peled, D. (eds.) ATVA 2016. LNCS, vol. 9938, pp. 50\u201367. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46520-3_4"},{"key":"7_CR32","doi-asserted-by":"publisher","unstructured":"Schnitzer, Y., Abate, A., Parker, D.: Certifiably robust policies for uncertain parametric environments. In: Gurfinkel, A., Heule, M. (eds.) TACAS (3), vol. 15698 of Lecture Notes in Computer Science, pp. 63\u201383. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-90660-2_4","DOI":"10.1007\/978-3-031-90660-2_4"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Schnitzer, Y., Abate, A., Parker, D.: Efficient solution and learning of robust factored mdps. AAAI (2026)","DOI":"10.1609\/aaai.v40i43.40957"},{"key":"7_CR34","unstructured":"Schnitzer, Y., Abate, A., Parker, D.: Robust parameter learning for uncertain MDPs. CoRR, abs\/2605.01339 (2026)"},{"issue":"4","key":"7_CR35","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1007\/s10898-011-9664-7","volume":"51","author":"JK Scott","year":"2011","unstructured":"Scott, J.K., Stuber, M.D., Barton, P.I.: Generalized mccormick relaxations. J. Glob. Optim. 51(4), 569\u2013606 (2011)","journal-title":"J. Glob. Optim."},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Strehl, A.L., Littman, M.L.; A theoretical analysis of model-based interval estimation. In ICML, vol. 119 of ACM International Conference Proceeding Series, pp. 856\u2013863. ACM (2005)","DOI":"10.1145\/1102351.1102459"},{"issue":"4","key":"7_CR37","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1002\/rob.21592","volume":"33","author":"J St\u00fcckler","year":"2016","unstructured":"St\u00fcckler, J., Schwarz, M., Schadler, M., Topalidou-Kyniazopoulou, A., Behnke, S.: Nimbro explorer: Semiautonomous exploration and mobile manipulation in rough terrain. J. Field Robot. 33(4), 411\u2013430 (2016)","journal-title":"J. Field Robot."},{"key":"7_CR38","doi-asserted-by":"publisher","unstructured":"Suilen, M., Badings, T.S., Bovy, E.M., Parker, D., Jansen, N.: Robust markov decision processes: A place where AI and formal methods meet. In: Principles of Verification (3), vol. 15262 of Lecture Notes in Computer Science, pp. 126\u2013154. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-75778-5_7","DOI":"10.1007\/978-3-031-75778-5_7"},{"key":"7_CR39","doi-asserted-by":"crossref","unstructured":"Suilen, M., Sim\u00e3o, T.D., Parker, D., Jansen, N.: Robust anytime learning of Markov decision processes. In: NeurIPS (2022)","DOI":"10.52202\/068431-2087"},{"key":"7_CR40","doi-asserted-by":"crossref","unstructured":"Valiant, L.G.: A theory of the learnable. In: STOC, pp. 436\u2013445. ACM (1984)","DOI":"10.1145\/800057.808710"},{"key":"7_CR41","unstructured":"Vanderbei, R.J.: Linear programming - foundations and extensions, volume 4 of Kluwer international series in operations research and management service, Kluwer (1998)"},{"key":"7_CR42","unstructured":"Weissman, T., Ordentlich, E., Seroussi, G., Verd\u00fa, S., Weinberger, M.J.: Inequalities for the $$l_1$$ deviation of the empirical distribution. Technical Report HPL-2003-97(R.1), Hewlett-Packard Laboratories (2003)"},{"issue":"1","key":"7_CR43","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1287\/moor.1120.0566","volume":"38","author":"W Wiesemann","year":"2013","unstructured":"Wiesemann, W., Kuhn, D., Rustem, B.: Robust Markov decision processes. Math. Oper. Res. 38(1), 153\u2013183 (2013)","journal-title":"Math. Oper. Res."},{"key":"7_CR44","doi-asserted-by":"crossref","unstructured":"Wolff, E.M., Topcu, U., Murray, R.M.: Robust control of uncertain markov decision processes with temporal logic specifications. In: CDC, IEEE (2012)","DOI":"10.1109\/CDC.2012.6426174"},{"key":"7_CR45","unstructured":"Zhou, D., Gu, Q., Szepesv\u00e1ri, C.: Nearly minimax optimal reinforcement learning for linear mixture markov decision processes. In: Proceedings of the 34th Annual Conference on Learning Theory, vol. 134, pp. 4532\u20134576. PMLR (2021)"}],"container-title":["Lecture Notes in Computer Science","Quantitative Evaluation of Systems and Formal Modeling and Analysis of Timed Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-35298-9_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T13:24:24Z","timestamp":1788009864000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-35298-9_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,30]]},"ISBN":["9783032352972","9783032352989"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-35298-9_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,30]]},"assertion":[{"value":"30 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"QEST+FORMATS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Quantitative Evaluation of Systems and Formal Modeling and Analysis of Timed Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Liverpool","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"qest2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.qest-formats.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}