{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T09:37:30Z","timestamp":1771061850558,"version":"3.50.1"},"publisher-location":"Cham","reference-count":122,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031757778","type":"print"},{"value":"9783031757785","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T00:00:00Z","timestamp":1731888000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T00:00:00Z","timestamp":1731888000000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-75778-5_7","type":"book-chapter","created":{"date-parts":[[2024,11,17]],"date-time":"2024-11-17T12:09:37Z","timestamp":1731845377000},"page":"126-154","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Robust Markov Decision Processes: A Place Where AI and\u00a0Formal Methods Meet"],"prefix":"10.1007","author":[{"given":"Marnix","family":"Suilen","sequence":"first","affiliation":[]},{"given":"Thom","family":"Badings","sequence":"additional","affiliation":[]},{"given":"Eline M.","family":"Bovy","sequence":"additional","affiliation":[]},{"given":"David","family":"Parker","sequence":"additional","affiliation":[]},{"given":"Nils","family":"Jansen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,18]]},"reference":[{"issue":"11","key":"7_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"},{"issue":"7","key":"7_CR2","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1109\/5.871304","volume":"88","author":"R Alur","year":"2000","unstructured":"Alur, R., Henzinger, T.A., Lafferriere, G., Pappas, G.J.: Discrete abstractions of hybrid systems. Proc. IEEE 88(7), 971\u2013984 (2000)","journal-title":"Proc. IEEE"},{"key":"7_CR3","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1007\/978-3-030-03928-8_23","volume-title":"Advances in Artificial Intelligence - IBERAMIA 2018","author":"I Andr\u00e9s","year":"2018","unstructured":"Andr\u00e9s, I., de Barros, L.N., Mau\u00e1, D.D., Sim\u00e3o, T.D.: When a robot reaches out for human help. In: Simari, G.R., Ferm\u00e9, E., Guti\u00e9rrez Segura, F., Rodr\u00edguez Melquiades, J.A. (eds.) IBERAMIA 2018. LNCS (LNAI), vol. 11238, pp. 277\u2013289. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-03928-8_23"},{"key":"7_CR4","unstructured":"Andriushchenko, R., et al.: Tools at the frontiers of quantitative verification. CoRR abs\/2405.13583 (2024)"},{"key":"7_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/978-3-319-99154-2_4","volume-title":"Quantitative Evaluation of Systems","author":"S Arming","year":"2018","unstructured":"Arming, S., Bartocci, E., Chatterjee, K., Katoen, J.-P., Sokolova, A.: Parameter-independent strategies for pMDPs via POMDPs. In: McIver, A., Horvath, A. (eds.) QEST 2018. LNCS, vol. 11024, pp. 53\u201370. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-99154-2_4"},{"key":"7_CR6","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"},{"issue":"5","key":"7_CR7","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1007\/s10009-022-00673-z","volume":"24","author":"TS Badings","year":"2022","unstructured":"Badings, T.S., Cubuktepe, M., Jansen, N., Junges, S., Katoen, J., Topcu, U.: Scenario-based verification of uncertain parametric MDPs. Int. J. Softw. Tools Technol. Transf. 24(5), 803\u2013819 (2022)","journal-title":"Int. J. Softw. Tools Technol. Transf."},{"key":"7_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1007\/978-3-031-13188-2_2","volume-title":"CAV 2022","author":"TS Badings","year":"2022","unstructured":"Badings, T.S., Jansen, N., Junges, S., Stoelinga, M., Volk, M.: Sampling-based verification of CTMCs with uncertain rates. In: Shoham, S., Vizel, Y. (eds.) CAV 2022. LNCS, vol. 13372, pp. 26\u201347. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-13188-2_2"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Badings, T.S., Romao, L., Abate, A., Jansen, N.: Probabilities are not enough: formal controller synthesis for stochastic dynamical models with epistemic uncertainty. In: AAAI, pp. 14701\u201314710. AAAI Press (2023)","DOI":"10.1609\/aaai.v37i12.26718"},{"key":"7_CR10","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1613\/jair.1.14253","volume":"76","author":"TS Badings","year":"2023","unstructured":"Badings, T.S., et al.: Robust control for dynamical systems with non-gaussian noise via formal abstractions. J. Artif. Intell. Res. 76, 341\u2013391 (2023)","journal-title":"J. Artif. Intell. Res."},{"issue":"3","key":"7_CR11","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1007\/s10009-023-00704-3","volume":"25","author":"TS Badings","year":"2023","unstructured":"Badings, T.S., Sim\u00e3o, T.D., Suilen, M., Jansen, N.: Decision-making under uncertainty: beyond probabilities. Int. J. Softw. Tools Technol. Transf. 25(3), 375\u2013391 (2023)","journal-title":"Int. J. Softw. Tools Technol. Transf."},{"key":"7_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1007\/978-3-540-78499-9_21","volume-title":"Foundations of Software Science and Computational Structures","author":"C Baier","year":"2008","unstructured":"Baier, C., Bertrand, N., Gr\u00f6\u00dfer, M.: On decision problems for probabilistic B\u00fcchi automata. In: Amadio, R. (ed.) FoSSaCS 2008. LNCS, vol. 4962, pp. 287\u2013301. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-78499-9_21"},{"key":"7_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1007\/978-3-319-91908-9_21","volume-title":"Computing and Software Science","author":"C Baier","year":"2019","unstructured":"Baier, C., Hermanns, H., Katoen, J.-P.: The 10,000 facets of MDP model checking. In: Steffen, B., Woeginger, G. (eds.) Computing and Software Science. LNCS, vol. 10000, pp. 420\u2013451. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-319-91908-9_21"},{"key":"7_CR14","volume-title":"Principles of Model Checking","author":"C Baier","year":"2008","unstructured":"Baier, C., Katoen, J.: Principles of Model Checking. MIT Press, Cambridge (2008)"},{"key":"7_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1007\/978-3-319-63387-9_8","volume-title":"Computer Aided Verification","author":"C Baier","year":"2017","unstructured":"Baier, C., Klein, J., Leuschner, L., Parker, D., Wunderlich, S.: Ensuring the reliability of your model checker: interval iteration for Markov decision processes. In: Majumdar, R., Kun\u010dak, V. (eds.) CAV 2017. LNCS, vol. 10426, pp. 160\u2013180. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-63387-9_8"},{"key":"7_CR16","unstructured":"Behzadian, B., Petrik, M., Ho, C.P.: Fast algorithms for $$l_{\\infty }$$-constrained S-rectangular robust MDPs. In: NeurIPS, pp. 25982\u201325992 (2021)"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Bovy, E.M., Suilen, M., Junges, S., Jansen, N.: Imprecise probabilities meet partial observability: game semantics for robust POMDPs. CoRR abs\/2405.04941 (2024)","DOI":"10.24963\/ijcai.2024\/740"},{"key":"7_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/978-3-319-11936-6_8","volume-title":"Automated Technology for Verification and Analysis","author":"T Br\u00e1zdil","year":"2014","unstructured":"Br\u00e1zdil, T., et al.: Verification of Markov decision processes using learning algorithms. In: Cassez, F., Raskin, J.-F. (eds.) ATVA 2014. LNCS, vol. 8837, pp. 98\u2013114. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-11936-6_8"},{"key":"7_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.arcontrol.2021.10.004","volume":"52","author":"MC Campi","year":"2021","unstructured":"Campi, M.C., Car\u00e8, A., Garatti, S.: The scenario approach: a tool at the service of data-driven decision making. Annu. Rev. Control. 52, 1\u201317 (2021)","journal-title":"Annu. Rev. Control."},{"issue":"3","key":"7_CR20","doi-asserted-by":"publisher","first-page":"1211","DOI":"10.1137\/07069821X","volume":"19","author":"MC Campi","year":"2008","unstructured":"Campi, M.C., Garatti, S.: The exact feasibility of randomized solutions of uncertain convex programs. SIAM J. Optim. 19(3), 1211\u20131230 (2008)","journal-title":"SIAM J. Optim."},{"key":"7_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1007\/978-3-030-17465-1_14","volume-title":"Tools and Algorithms for the Construction and Analysis of Systems","author":"N Cauchi","year":"2019","unstructured":"Cauchi, N., Abate, A.: $$\\sf StocHy$$: automated verification and synthesis of stochastic processes. In: Vojnar, T., Zhang, L. (eds.) TACAS 2019. LNCS, vol. 11428, pp. 247\u2013264. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-17465-1_14"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Chamie, M.E., Mostafa, H.: Robust action selection in partially observable Markov decision processes with model uncertainty. In: CDC, pp. 5586\u20135591. IEEE (2018)","DOI":"10.1109\/CDC.2018.8619468"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Chatterjee, K., Chmel\u00edk, M., Karkhanis, D., Novotn\u00fd, P., Royer, A.: Multiple-environment Markov decision processes: efficient analysis and applications. In: ICAPS, pp. 48\u201356. AAAI Press (2020)","DOI":"10.1609\/icaps.v30i1.6644"},{"key":"7_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1007\/978-3-642-15155-2_24","volume-title":"Mathematical Foundations of Computer Science 2010","author":"K Chatterjee","year":"2010","unstructured":"Chatterjee, K., Doyen, L., Henzinger, T.A.: Qualitative analysis of partially-observable Markov decision processes. In: Hlin\u011bn\u00fd, P., Ku\u010dera, A. (eds.) MFCS 2010. LNCS, vol. 6281, pp. 258\u2013269. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15155-2_24"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Chatterjee, K., Goharshady, E.K., Karrabi, M., Novotn\u00fd, P., Zikelic, D.: Solving long-run average reward robust MDPs via stochastic games. CoRR abs\/2312.13912 (2023)","DOI":"10.24963\/ijcai.2024\/741"},{"issue":"7","key":"7_CR26","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1016\/j.ipl.2013.01.004","volume":"113","author":"T Chen","year":"2013","unstructured":"Chen, T., Han, T., Kwiatkowska, M.Z.: On the complexity of model checking interval-valued discrete time Markov chains. Inf. Process. Lett. 113(7), 210\u2013216 (2013)","journal-title":"Inf. Process. Lett."},{"key":"7_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-642-35746-6_1","volume-title":"Tools for Practical Software Verification","author":"EM Clarke","year":"2012","unstructured":"Clarke, E.M., Klieber, W., Nov\u00e1\u010dek, M., Zuliani, P.: Model checking and the state explosion problem. In: Meyer, B., Nordio, M. (eds.) LASER 2011. LNCS, vol. 7682, pp. 1\u201330. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-35746-6_1"},{"key":"7_CR28","unstructured":"Coppola, R., Peruffo, A., Romao, L., Abate, A., Jr., M.M.: Data-driven interval MDP for robust control synthesis. CoRR abs\/2404.08344 (2024)"},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Costen, C., Rigter, M., Lacerda, B., Hawes, N.: Planning with hidden parameter polynomial MDPs. In: AAAI, pp. 11963\u201311971. AAAI Press (2023)","DOI":"10.1609\/aaai.v37i10.26411"},{"key":"7_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1007\/978-3-662-54580-5_8","volume-title":"Tools and Algorithms for the Construction and Analysis of Systems","author":"M Cubuktepe","year":"2017","unstructured":"Cubuktepe, M., et al.: Sequential convex programming for the efficient verification of parametric MDPs. In: Legay, A., Margaria, T. (eds.) TACAS 2017. LNCS, vol. 10206, pp. 133\u2013150. Springer, Heidelberg (2017). https:\/\/doi.org\/10.1007\/978-3-662-54580-5_8"},{"key":"7_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1007\/978-3-030-01090-4_10","volume-title":"Automated Technology for Verification and Analysis","author":"M Cubuktepe","year":"2018","unstructured":"Cubuktepe, M., Jansen, N., Junges, S., Katoen, J.-P., Topcu, U.: Synthesis in pMDPs: a tale of 1001 parameters. In: Lahiri, S.K., Wang, C. (eds.) ATVA 2018. LNCS, vol. 11138, pp. 160\u2013176. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01090-4_10"},{"key":"7_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1007\/978-3-030-45190-5_16","volume-title":"Tools and Algorithms for the Construction and Analysis of Systems","author":"M Cubuktepe","year":"2020","unstructured":"Cubuktepe, M., Jansen, N., Junges, S., Katoen, J.-P., Topcu, U.: Scenario-based verification of uncertain MDPs. In: Biere, A., Parker, D. (eds.) TACAS 2020. LNCS, vol. 12078, pp. 287\u2013305. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-45190-5_16"},{"issue":"12","key":"7_CR33","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., 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_CR34","doi-asserted-by":"crossref","unstructured":"Cubuktepe, M., Jansen, N., Junges, S., Marandi, A., Suilen, M., Topcu, U.: Robust finite-state controllers for uncertain POMDPs. In: AAAI, pp. 11792\u201311800. AAAI Press (2021)","DOI":"10.1609\/aaai.v35i13.17401"},{"key":"7_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1007\/978-3-662-49674-9_7","volume-title":"Tools and Algorithms for the Construction and Analysis of Systems","author":"P Daca","year":"2016","unstructured":"Daca, P., Henzinger, T.A., K\u0159et\u00ednsk\u00fd, J., Petrov, T.: Faster statistical model checking for unbounded temporal properties. In: Chechik, M., Raskin, J.-F. (eds.) TACAS 2016. LNCS, vol. 9636, pp. 112\u2013129. Springer, Heidelberg (2016). https:\/\/doi.org\/10.1007\/978-3-662-49674-9_7"},{"key":"7_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1007\/978-3-319-21690-4_13","volume-title":"Computer Aided Verification","author":"C Dehnert","year":"2015","unstructured":"Dehnert, C., et al.: PROPhESY: A PRObabilistic ParamEter SYnthesis tool. In: Kroening, D., P\u0103s\u0103reanu, C.S. (eds.) CAV 2015. LNCS, vol. 9206, pp. 214\u2013231. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-21690-4_13"},{"key":"7_CR37","unstructured":"Dehnert, C., et al.: Parameter synthesis for probabilistic systems. In: MBMV, pp. 72\u201374. Albert-Ludwigs-Universit\u00e4t Freiburg (2016)"},{"key":"7_CR38","doi-asserted-by":"publisher","first-page":"751","DOI":"10.1007\/s13235-023-00519-6","volume":"14","author":"A Delage","year":"2023","unstructured":"Delage, A., Buffet, O., Dibangoye, J.S., Saffidine, A.: HSVI can solve zero-sum partially observable stochastic games. Dyn. Games Appl. 14, 751\u2013805 (2023)","journal-title":"Dyn. Games Appl."},{"key":"7_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/11691617_5","volume-title":"Model Checking Software","author":"H Fecher","year":"2006","unstructured":"Fecher, H., Leucker, M., Wolf, V.: Don\u2019t Know in probabilistic systems. In: Valmari, A. (ed.) SPIN 2006. LNCS, vol. 3925, pp. 71\u201388. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11691617_5"},{"key":"7_CR40","unstructured":"Fijalkow, N., et al.: Games on graphs. CoRR abs\/2305.10546 (2023)"},{"key":"7_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/978-3-642-21455-4_3","volume-title":"Formal Methods for Eternal Networked Software Systems","author":"V Forejt","year":"2011","unstructured":"Forejt, V., Kwiatkowska, M., Norman, G., Parker, D.: Automated verification techniques for probabilistic systems. In: Bernardo, M., Issarny, V. (eds.) SFM 2011. LNCS, vol. 6659, pp. 53\u2013113. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-21455-4_3"},{"key":"7_CR42","doi-asserted-by":"crossref","unstructured":"Gadot, U., Derman, E., Kumar, N., Elfatihi, M.M., Levy, K., Mannor, S.: Solving non-rectangular reward-robust MDPs via frequency regularization. In: AAAI, pp. 21090\u201321098. AAAI Press (2024)","DOI":"10.1609\/aaai.v38i19.30101"},{"key":"7_CR43","unstructured":"Galesloot, M.F., et al.: Pessimistic iterative planning for robust POMDPs (2024)"},{"key":"7_CR44","unstructured":"Ghavamzadeh, M., Petrik, M., Chow, Y.: Safe policy improvement by minimizing robust baseline regret. In: NIPS, pp. 2298\u20132306 (2016)"},{"issue":"5","key":"7_CR45","doi-asserted-by":"publisher","first-page":"782","DOI":"10.1109\/TAC.2007.895849","volume":"52","author":"A Girard","year":"2007","unstructured":"Girard, A., Pappas, G.J.: Approximation metrics for discrete and continuous systems. IEEE Trans. Autom. Control 52(5), 782\u2013798 (2007)","journal-title":"IEEE Trans. Autom. Control"},{"issue":"1\u20132","key":"7_CR46","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/S0004-3702(00)00047-3","volume":"122","author":"R Givan","year":"2000","unstructured":"Givan, R., Leach, S.M., Dean, T.L.: Bounded-parameter Markov decision processes. Artif. Intell. 122(1\u20132), 71\u2013109 (2000)","journal-title":"Artif. Intell."},{"issue":"1","key":"7_CR47","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1287\/moor.2022.1259","volume":"48","author":"V Goyal","year":"2023","unstructured":"Goyal, V., Grand-Cl\u00e9ment, J.: Robust Markov decision processes: beyond rectangularity. Math. Oper. Res. 48(1), 203\u2013226 (2023)","journal-title":"Math. Oper. Res."},{"key":"7_CR48","unstructured":"Grand-Cl\u00e9ment, J., Petrik, M.: Reducing Blackwell and average optimality to discounted MDPs via the Blackwell discount factor. In: NeurIPS (2023)"},{"key":"7_CR49","doi-asserted-by":"crossref","unstructured":"Grand-Cl\u00e9ment, J., Petrik, M., Vieille, N.: Beyond discounted returns: robust Markov decision processes with average and Blackwell optimality. CoRR abs\/2312.03618 (2023)","DOI":"10.1287\/moor.2022.0284"},{"key":"7_CR50","unstructured":"Guez, A., Silver, D., Dayan, P.: Efficient Bayes-adaptive reinforcement learning using sample-based search. In: NIPS, pp. 1034\u20131042 (2012)"},{"key":"7_CR51","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1007\/978-3-319-11439-2_10","volume-title":"Reachability Problems","author":"S Haddad","year":"2014","unstructured":"Haddad, S., Monmege, B.: Reachability in MDPs: refining convergence of value iteration. In: Ouaknine, J., Potapov, I., Worrell, J. (eds.) RP 2014. LNCS, vol. 8762, pp. 125\u2013137. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-11439-2_10"},{"issue":"5","key":"7_CR52","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":"7_CR53","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1007\/978-3-031-30823-9_24","volume-title":"TACAS 2023","author":"A Hartmanns","year":"2023","unstructured":"Hartmanns, A., Junges, S., Quatmann, T., Weininger, M.: A practitioner\u2019s guide to MDP model checking algorithms. In: Sankaranarayanan, S., Sharygina, N. (eds.) TACAS 2023. LNCS, vol. 13993, pp. 469\u2013488. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-30823-9_24"},{"key":"7_CR54","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"488","DOI":"10.1007\/978-3-030-53291-8_26","volume-title":"Computer Aided Verification","author":"A Hartmanns","year":"2020","unstructured":"Hartmanns, A., Kaminski, B.L.: Optimistic value iteration. In: Lahiri, S.K., Wang, C. (eds.) CAV 2020. LNCS, vol. 12225, pp. 488\u2013511. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-53291-8_26"},{"key":"7_CR55","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1007\/978-3-030-17462-0_20","volume-title":"Tools and Algorithms for the Construction and Analysis of Systems","author":"A Hartmanns","year":"2019","unstructured":"Hartmanns, A., Klauck, M., Parker, D., Quatmann, T., Ruijters, E.: The quantitative verification benchmark set. In: Vojnar, T., Zhang, L. (eds.) TACAS 2019, Part I. LNCS, vol. 11427, pp. 344\u2013350. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-17462-0_20"},{"key":"7_CR56","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1007\/978-3-319-30000-9_9","volume-title":"Language and Automata Theory and Applications","author":"V Hashemi","year":"2016","unstructured":"Hashemi, V., Hermanns, H., Song, L., Subramani, K., Turrini, A., Wojciechowski, P.: Compositional bisimulation minimization for interval Markov decision processes. In: Dediu, A.-H., Janou\u0161ek, J., Mart\u00edn-Vide, C., Truthe, B. (eds.) LATA 2016. LNCS, vol. 9618, pp. 114\u2013126. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-30000-9_9"},{"issue":"4","key":"7_CR57","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1007\/s10009-021-00633-z","volume":"24","author":"C Hensel","year":"2022","unstructured":"Hensel, C., Junges, S., Katoen, J., Quatmann, T., Volk, M.: The probabilistic model checker storm. Int. J. Softw. Tools Technol. Transf. 24(4), 589\u2013610 (2022)","journal-title":"Int. J. Softw. Tools Technol. Transf."},{"key":"7_CR58","unstructured":"Ho, C.P., Petrik, M., Wiesemann, W.: Fast Bellman updates for robust MDPs. In: ICML. Proceedings of Machine Learning Research, vol.\u00a080, pp. 1984\u20131993. PMLR (2018)"},{"key":"7_CR59","unstructured":"Ho, C.P., Petrik, M., Wiesemann, W.: Partial policy iteration for l1-robust Markov decision processes. J. Mach. Learn. Res. 22, 275:1\u2013275:46 (2021)"},{"key":"7_CR60","unstructured":"Ho, C.P., Petrik, M., Wiesemann, W.: Robust $$\\phi $$-divergence MDPs. In: NeurIPS (2022)"},{"key":"7_CR61","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1080\/01621459.1963.10500830","volume":"58","author":"W Hoeffding","year":"1963","unstructured":"Hoeffding, W.: Probability inequalities for sums of bounded random variables. J. Am. Stat. Assoc. 58, 13\u201330 (1963)","journal-title":"J. Am. Stat. Assoc."},{"issue":"3","key":"7_CR62","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1007\/s10994-021-05946-3","volume":"110","author":"E H\u00fcllermeier","year":"2021","unstructured":"H\u00fcllermeier, E., Waegeman, W.: Aleatoric and epistemic uncertainty in machine learning: an introduction to concepts and methods. Mach. Learn. 110(3), 457\u2013506 (2021)","journal-title":"Mach. Learn."},{"issue":"8\u20139","key":"7_CR63","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1016\/j.artint.2007.03.004","volume":"171","author":"H Itoh","year":"2007","unstructured":"Itoh, H., Nakamura, K.: Partially observable Markov decision processes with imprecise parameters. Artif. Intell. 171(8\u20139), 453\u2013490 (2007)","journal-title":"Artif. Intell."},{"issue":"2","key":"7_CR64","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."},{"key":"7_CR65","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1007\/978-3-030-61362-4_15","volume-title":"Leveraging Applications of Formal Methods, Verification and Validation: Verification Principles","author":"M Jaeger","year":"2020","unstructured":"Jaeger, M., Bacci, G., Bacci, G., Larsen, K.G., Jensen, P.G.: Approximating Euclidean by imprecise Markov decision processes. In: Margaria, T., Steffen, B. (eds.) ISoLA 2020. LNCS, vol. 12476, pp. 275\u2013289. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-61362-4_15"},{"key":"7_CR66","first-page":"1563","volume":"11","author":"T Jaksch","year":"2010","unstructured":"Jaksch, T., Ortner, R., Auer, P.: Near-optimal regret bounds for reinforcement learning. J. Mach. Learn. Res. 11, 1563\u20131600 (2010)","journal-title":"J. Mach. Learn. Res."},{"key":"7_CR67","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1007\/978-3-031-22337-2_20","volume-title":"Principles of Systems Design","author":"N Jansen","year":"2022","unstructured":"Jansen, N., Junges, S., Katoen, J.: Parameter synthesis in Markov models: a gentle survey. In: Raskin, J.F., Chatterjee, K., Doyen, L., Majumdar, R. (eds.) Principles of Systems Design. LNCS, vol. 13660, pp. 407\u2013437. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-22337-2_20"},{"key":"7_CR68","doi-asserted-by":"publisher","unstructured":"Jonsson, B., Larsen, K.G.: Specification and refinement of probabilistic processes. In: Proceedings of the Sixth Annual Symposium on Logic in Computer Science (LICS 1991), Amsterdam, The Netherlands, 15\u201318 July 1991, pp. 266\u2013277. IEEE Computer Society (1991). https:\/\/doi.org\/10.1109\/LICS.1991.151651","DOI":"10.1109\/LICS.1991.151651"},{"issue":"1","key":"7_CR69","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1007\/s10703-023-00442-x","volume":"62","author":"S Junges","year":"2024","unstructured":"Junges, S., et al.: 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_CR70","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1016\/j.jcss.2021.02.006","volume":"119","author":"S Junges","year":"2021","unstructured":"Junges, S., Katoen, J., P\u00e9rez, G.A., Winkler, T.: The complexity of reachability in parametric Markov decision processes. J. Comput. Syst. Sci. 119, 183\u2013210 (2021)","journal-title":"J. Comput. Syst. Sci."},{"issue":"1\u20132","key":"7_CR71","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/S0004-3702(98)00023-X","volume":"101","author":"LP Kaelbling","year":"1998","unstructured":"Kaelbling, L.P., Littman, M.L., Cassandra, A.R.: Planning and acting in partially observable stochastic domains. Artif. Intell. 101(1\u20132), 99\u2013134 (1998)","journal-title":"Artif. Intell."},{"key":"7_CR72","doi-asserted-by":"crossref","unstructured":"Katoen, J.: The probabilistic model checking landscape. In: LICS, pp. 31\u201345. ACM (2016)","DOI":"10.1145\/2933575.2934574"},{"key":"7_CR73","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1007\/978-3-540-73368-3_37","volume-title":"Computer Aided Verification","author":"J-P Katoen","year":"2007","unstructured":"Katoen, J.-P., Klink, D., Leucker, M., Wolf, V.: Three-valued abstraction for continuous-time Markov chains. In: Damm, W., Hermanns, H. (eds.) CAV 2007. LNCS, vol. 4590, pp. 311\u2013324. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-73368-3_37"},{"issue":"4","key":"7_CR74","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1016\/j.jlap.2012.03.007","volume":"81","author":"J Katoen","year":"2012","unstructured":"Katoen, J., Klink, D., Leucker, M., Wolf, V.: Three-valued abstraction for probabilistic systems. J. Log. Algebraic Methods Program. 81(4), 356\u2013389 (2012)","journal-title":"J. Log. Algebraic Methods Program."},{"issue":"3","key":"7_CR75","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1007\/s10703-010-0097-6","volume":"36","author":"M Kattenbelt","year":"2010","unstructured":"Kattenbelt, M., Kwiatkowska, M.Z., Norman, G., Parker, D.: A game-based abstraction-refinement framework for Markov decision processes. Formal Methods Syst. Des. 36(3), 246\u2013280 (2010)","journal-title":"Formal Methods Syst. Des."},{"issue":"3","key":"7_CR76","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1287\/ijoc.1120.0509","volume":"25","author":"DL Kaufman","year":"2013","unstructured":"Kaufman, D.L., Schaefer, A.J.: Robust modified policy iteration. INFORMS J. Comput. 25(3), 396\u2013410 (2013)","journal-title":"INFORMS J. Comput."},{"key":"7_CR77","unstructured":"Kumar, N., Derman, E., Geist, M., Levy, K.Y., Mannor, S.: Policy gradient for rectangular robust Markov decision processes. In: NeurIPS (2023)"},{"key":"7_CR78","doi-asserted-by":"crossref","unstructured":"Kwiatkowska, M.Z., Norman, G., Parker, D.: Game-based abstraction for Markov decision processes. In: QEST, pp. 157\u2013166. IEEE Computer Society (2006)","DOI":"10.1109\/QEST.2006.19"},{"key":"7_CR79","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1007\/978-3-540-72522-0_6","volume-title":"Formal Methods for Performance Evaluation","author":"M Kwiatkowska","year":"2007","unstructured":"Kwiatkowska, M., Norman, G., Parker, D.: Stochastic model checking. In: Bernardo, M., Hillston, J. (eds.) SFM 2007. LNCS, vol. 4486, pp. 220\u2013270. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-72522-0_6"},{"key":"7_CR80","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":"8","key":"7_CR81","doi-asserted-by":"publisher","first-page":"2031","DOI":"10.1109\/TAC.2015.2398883","volume":"60","author":"M Lahijanian","year":"2015","unstructured":"Lahijanian, M., Andersson, S.B., Belta, C.: Formal verification and synthesis for discrete-time stochastic systems. IEEE Trans. Autom. Control 60(8), 2031\u20132045 (2015)","journal-title":"IEEE Trans. Autom. Control"},{"key":"7_CR82","unstructured":"Laroche, R., Trichelair, P., des Combes, R.T.: Safe policy improvement with baseline bootstrapping. In: ICML. Proceedings of Machine Learning Research, vol.\u00a097, pp. 3652\u20133661. PMLR (2019)"},{"issue":"1","key":"7_CR83","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0890-5401(91)90030-6","volume":"94","author":"KG Larsen","year":"1991","unstructured":"Larsen, K.G., Skou, A.: Bisimulation through probabilistic testing. Inf. Comput. 94(1), 1\u201328 (1991)","journal-title":"Inf. Comput."},{"key":"7_CR84","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110617","volume":"146","author":"A Lavaei","year":"2022","unstructured":"Lavaei, A., Soudjani, S., Abate, A., Zamani, M.: Automated verification and synthesis of stochastic hybrid systems: a survey. Autom. 146, 110617 (2022)","journal-title":"Autom."},{"key":"7_CR85","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1109\/LCSYS.2022.3188535","volume":"7","author":"A Lavaei","year":"2023","unstructured":"Lavaei, A., Soudjani, S., Frazzoli, E., Zamani, M.: Constructing MDP abstractions using data with formal guarantees. IEEE Control. Syst. Lett. 7, 460\u2013465 (2023)","journal-title":"IEEE Control. Syst. Lett."},{"key":"7_CR86","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1007\/978-3-642-16612-9_11","volume-title":"Runtime Verification","author":"A Legay","year":"2010","unstructured":"Legay, A., Delahaye, B., Bensalem, S.: Statistical model checking: an overview. In: Barringer, H. (ed.) RV 2010. LNCS, vol. 6418, pp. 122\u2013135. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-16612-9_11"},{"issue":"1\u20132","key":"7_CR87","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1016\/S0004-3702(02)00378-8","volume":"147","author":"O Madani","year":"2003","unstructured":"Madani, O., Hanks, S., Condon, A.: On the undecidability of probabilistic planning and related stochastic optimization problems. Artif. Intell. 147(1\u20132), 5\u201334 (2003)","journal-title":"Artif. Intell."},{"issue":"2","key":"7_CR88","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1287\/mnsc.1060.0614","volume":"53","author":"S Mannor","year":"2007","unstructured":"Mannor, S., Simester, D., Sun, P., Tsitsiklis, J.N.: Bias and variance approximation in value function estimates. Manag. Sci. 53(2), 308\u2013322 (2007)","journal-title":"Manag. Sci."},{"key":"7_CR89","doi-asserted-by":"crossref","unstructured":"Mathiesen, F.B., Lahijanian, M., Laurenti, L.: Intervalmdp.jl: accelerated value iteration for interval Markov decision processes. Technical report. arXiv:2401.04068, arXiv (2024)","DOI":"10.1016\/j.ifacol.2024.07.416"},{"key":"7_CR90","unstructured":"Meggendorfer, T., Weininger, M., Wienh\u00f6ft, P.: What are the Odds? Improving the foundations of statistical model checking. CoRR abs\/2404.05424 (2024)"},{"issue":"1","key":"7_CR91","doi-asserted-by":"publisher","first-page":"276","DOI":"10.3390\/make4010013","volume":"4","author":"J Moos","year":"2022","unstructured":"Moos, J., Hansel, K., Abdulsamad, H., Stark, S., Clever, D., Peters, J.: Robust reinforcement learning: a review of foundations and recent advances. Mach. Learn. Knowl. Extr. 4(1), 276\u2013315 (2022)","journal-title":"Mach. Learn. Knowl. Extr."},{"issue":"1","key":"7_CR92","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1137\/19M1268410","volume":"31","author":"H Nakao","year":"2021","unstructured":"Nakao, H., Jiang, R., Shen, S.: Distributionally robust partially observable Markov decision process with moment-based ambiguity. SIAM J. Optim. 31(1), 461\u2013488 (2021)","journal-title":"SIAM J. Optim."},{"issue":"5","key":"7_CR93","doi-asserted-by":"publisher","first-page":"780","DOI":"10.1287\/opre.1050.0216","volume":"53","author":"A Nilim","year":"2005","unstructured":"Nilim, A., Ghaoui, L.E.: Robust control of Markov decision processes with uncertain transition matrices. Oper. Res. 53(5), 780\u2013798 (2005)","journal-title":"Oper. Res."},{"key":"7_CR94","unstructured":"Osogami, T.: Robust partially observable Markov decision process. In: ICML. JMLR Workshop and Conference Proceedings, vol.\u00a037, pp. 106\u2013115. JMLR.org (2015)"},{"key":"7_CR95","unstructured":"Ou, W., Bi, S.: Sequential decision-making under uncertainty: a robust MDPs review. CoRR abs\/2305.10546 (2024)"},{"key":"7_CR96","doi-asserted-by":"crossref","unstructured":"Pnueli, A.: The temporal logic of programs. In: FOCS, pp. 46\u201357. IEEE Computer Society (1977)","DOI":"10.1109\/SFCS.1977.32"},{"key":"7_CR97","doi-asserted-by":"crossref","unstructured":"Ponnambalam, C.T., Oliehoek, F.A., Spaan, M.T.J.: Abstraction-guided policy recovery from expert demonstrations. In: ICAPS, pp. 560\u2013568. AAAI Press (2021)","DOI":"10.1609\/icaps.v31i1.16004"},{"key":"7_CR98","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1007\/978-3-642-39799-8_35","volume-title":"Computer Aided Verification","author":"A Puggelli","year":"2013","unstructured":"Puggelli, A., Li, W., Sangiovanni-Vincentelli, A.L., Seshia, S.A.: Polynomial-time verification of PCTL properties of MDPs with convex uncertainties. In: Sharygina, N., Veith, H. (eds.) CAV 2013. LNCS, vol. 8044, pp. 527\u2013542. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-39799-8_35"},{"key":"7_CR99","doi-asserted-by":"crossref","unstructured":"Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. Wiley Series in Probability and Statistics. Wiley, Hoboken (1994)","DOI":"10.1002\/9780470316887"},{"key":"7_CR100","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_CR101","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"643","DOI":"10.1007\/978-3-319-96145-3_37","volume-title":"Computer Aided Verification","author":"T Quatmann","year":"2018","unstructured":"Quatmann, T., Katoen, J.-P.: Sound value iteration. In: Chockler, H., Weissenbacher, G. (eds.) CAV 2018. LNCS, vol. 10981, pp. 643\u2013661. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-96145-3_37"},{"key":"7_CR102","unstructured":"Raskin, J., Sankur, O.: Multiple-environment Markov decision processes. In: FSTTCS. LIPIcs, vol.\u00a029, pp. 531\u2013543. Schloss Dagstuhl - Leibniz-Zentrum f\u00fcr Informatik (2014)"},{"key":"7_CR103","unstructured":"Rickard, L., Abate, A., Margellos, K.: Learning robust policies for uncertain parametric Markov decision processes. CoRR abs\/2312.06344 (2023)"},{"key":"7_CR104","doi-asserted-by":"crossref","unstructured":"Rigter, M., Lacerda, B., Hawes, N.: Minimax regret optimisation for robust planning in uncertain Markov decision processes. In: AAAI, pp. 11930\u201311938. AAAI Press (2021)","DOI":"10.1609\/aaai.v35i13.17417"},{"key":"7_CR105","unstructured":"Rigter, M., Lacerda, B., Hawes, N.: Risk-averse Bayes-adaptive reinforcement learning. In: NeurIPS, pp. 1142\u20131154 (2021)"},{"key":"7_CR106","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jet.2018.08.006","volume":"178","author":"S Saghafian","year":"2018","unstructured":"Saghafian, S.: Ambiguous partially observable Markov decision processes: structural results and applications. J. Econ. Theory 178, 1\u201335 (2018)","journal-title":"J. Econ. Theory"},{"key":"7_CR107","doi-asserted-by":"crossref","unstructured":"Sim\u00e3o, T.D., Suilen, M., Jansen, N.: Safe policy improvement for POMDPs via finite-state controllers. In: AAAI, pp. 15109\u201315117. AAAI Press (2023)","DOI":"10.1609\/aaai.v37i12.26763"},{"key":"7_CR108","first-page":"2413","volume":"10","author":"AL Strehl","year":"2009","unstructured":"Strehl, A.L., Li, L., Littman, M.L.: Reinforcement learning in finite MDPs: PAC analysis. J. Mach. Learn. Res. 10, 2413\u20132444 (2009)","journal-title":"J. Mach. Learn. Res."},{"issue":"8","key":"7_CR109","doi-asserted-by":"publisher","first-page":"1309","DOI":"10.1016\/j.jcss.2007.08.009","volume":"74","author":"AL Strehl","year":"2008","unstructured":"Strehl, A.L., Littman, M.L.: An analysis of model-based interval estimation for Markov decision processes. J. Comput. Syst. Sci. 74(8), 1309\u20131331 (2008)","journal-title":"J. Comput. Syst. Sci."},{"key":"7_CR110","doi-asserted-by":"crossref","unstructured":"Suilen, M., Jansen, N., Cubuktepe, M., Topcu, U.: Robust policy synthesis for uncertain pomdps via convex optimization. In: IJCAI, pp. 4113\u20134120. ijcai.org (2020)","DOI":"10.24963\/ijcai.2020\/569"},{"key":"7_CR111","unstructured":"Suilen, M., Sim\u00e3o, T.D., Parker, D., Jansen, N.: Robust anytime learning of Markov decision processes. In: NeurIPS (2022)"},{"key":"7_CR112","unstructured":"Suilen, M., van\u00a0der Vegt, M., Junges, S.: A PSPACE algorithm for almost-sure Rabin objectives in multi-environment MDPs. CoRR abs\/2407.07006 (2024)"},{"key":"7_CR113","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192","volume-title":"Reinforcement Learning - An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning - An Introduction. Adaptive Computation and Machine Learning. MIT Press, Cambridge (1998)"},{"key":"7_CR114","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"508","DOI":"10.1007\/978-3-031-30823-9_26","volume-title":"TACAS 2023","author":"M van der Vegt","year":"2023","unstructured":"van der Vegt, M., Jansen, N., Junges, S.: Robust almost-sure reachability in multi-environment MDPs. In: Sankaranarayanan, S., Sharygina, N. (eds.) TACAS 2023. LNCS, vol. 13993, pp. 508\u2013526. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-30823-9_26"},{"key":"7_CR115","unstructured":"Wang, Q., Ho, C.P., Petrik, M.: Policy gradient in robust MDPs with global convergence guarantee. In: ICML. Proceedings of Machine Learning Research, vol.\u00a0202, pp. 35763\u201335797. PMLR (2023)"},{"key":"7_CR116","unstructured":"Weissman, T., Ordentlich, E., Seroussi, G., Verdu, S., Weinberger, M.J.: Inequalities for the l1 deviation of the empirical distribution. Technical report, Hewlett-Packard Labs (2003)"},{"key":"7_CR117","doi-asserted-by":"crossref","unstructured":"Wienh\u00f6ft, P., Suilen, M., Sim\u00e3o, T.D., Dubslaff, C., Baier, C., Jansen, N.: More for less: safe policy improvement with stronger performance guarantees. In: IJCAI, pp. 4406\u20134415. ijcai.org (2023)","DOI":"10.24963\/ijcai.2023\/490"},{"issue":"1","key":"7_CR118","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_CR119","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, pp. 3372\u20133379. IEEE (2012)","DOI":"10.1109\/CDC.2012.6426174"},{"key":"7_CR120","doi-asserted-by":"crossref","unstructured":"Wooding, B., Lavaei, A.: Impact: interval MDP parallel construction for controller synthesis of large-scale stochastic systems. CoRR abs\/2401.03555 (2024)","DOI":"10.1007\/978-3-031-68416-6_15"},{"issue":"2","key":"7_CR121","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1287\/moor.1120.0540","volume":"37","author":"H Xu","year":"2012","unstructured":"Xu, H., Mannor, S.: Distributionally robust Markov decision processes. Math. Oper. Res. 37(2), 288\u2013300 (2012)","journal-title":"Math. Oper. Res."},{"key":"7_CR122","doi-asserted-by":"crossref","unstructured":"Yang, C., Littman, M.L., Carbin, M.: On the (in)tractability of reinforcement learning for LTL objectives. In: IJCAI, pp. 3650\u20133658. ijcai.org (2022)","DOI":"10.24963\/ijcai.2022\/507"}],"container-title":["Lecture Notes in Computer Science","Principles of Verification: Cycling the Probabilistic Landscape"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-75778-5_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,17]],"date-time":"2024-11-17T13:02:53Z","timestamp":1731848573000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-75778-5_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,18]]},"ISBN":["9783031757778","9783031757785"],"references-count":122,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-75778-5_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,18]]},"assertion":[{"value":"18 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}