{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T00:43:14Z","timestamp":1759365794117,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":69,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032057914","type":"print"},{"value":"9783032057921","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T00:00:00Z","timestamp":1759363200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T00:00:00Z","timestamp":1759363200000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-05792-1_8","type":"book-chapter","created":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T10:31:44Z","timestamp":1759314704000},"page":"134-156","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PyDSMC: Statistical Model Checking for\u00a0Neural Agents Using the\u00a0Gymnasium Interface"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1100-1952","authenticated-orcid":false,"given":"Timo P.","family":"Gros","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3268-8674","authenticated-orcid":false,"given":"Arnd","family":"Hartmanns","sequence":"additional","affiliation":[]},{"given":"Ivo","family":"Hoese","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8703-1136","authenticated-orcid":false,"given":"Joshua","family":"Meyer","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5932-3395","authenticated-orcid":false,"given":"Nicola J.","family":"M\u00fcller","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8460-6007","authenticated-orcid":false,"given":"Verena","family":"Wolf","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,2]]},"reference":[{"key":"8_CR1","doi-asserted-by":"publisher","unstructured":"Achiam, J., et\u00a0al.: GPT-4 Technical Report. arXiv preprint arXiv:2303.08774 (2024). https:\/\/doi.org\/10.48550\/arXiv.2303.08774","DOI":"10.48550\/arXiv.2303.08774"},{"key":"8_CR2","unstructured":"Agarwal, R., Schuurmans, D., Norouzi, M.: An optimistic perspective on offline reinforcement learning. In: Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13\u201318 July 2020, Virtual Event. Proceedings of Machine Learning Research, vol.\u00a0119, pp. 104\u2013114. PMLR (2020). http:\/\/proceedings.mlr.press\/v119\/agarwal20c.html"},{"key":"8_CR3","doi-asserted-by":"publisher","unstructured":"Agha, G., Palmskog, K.: A survey of statistical model checking. ACM Trans. Model. Comput. Simul. 28(1), 6:1\u20136:39 (2018). https:\/\/doi.org\/10.1145\/3158668","DOI":"10.1145\/3158668"},{"issue":"1\u20132","key":"8_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2500000051","volume":"7","author":"A Albarghouthi","year":"2021","unstructured":"Albarghouthi, A.: Introduction to neural network verification. Found. Trends Program. Lang. 7(1\u20132), 1\u2013157 (2021). https:\/\/doi.org\/10.1561\/2500000051","journal-title":"Found. Trends Program. Lang."},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Alshiekh, M., Bloem, R., Ehlers, R., K\u00f6nighofer, B., Niekum, S., Topcu, U.: Safe reinforcement learning via shielding. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"8_CR6","doi-asserted-by":"publisher","unstructured":"Baier, C.: Probabilistic model checking. In: Esparza, J., Grumberg, O., Sickert, S. (eds.) Dependable Software Systems Engineering, NATO Science for Peace and Security Series \u2013 D: Information and Communication Security, vol.\u00a045, pp. 1\u201323. IOS Press (2016). https:\/\/doi.org\/10.3233\/978-1-61499-627-9-1","DOI":"10.3233\/978-1-61499-627-9-1"},{"key":"8_CR7","doi-asserted-by":"publisher","first-page":"963","DOI":"10.1007\/978-3-319-10575-8_28","volume-title":"Handbook of Model Checking","author":"C Baier","year":"2018","unstructured":"Baier, C., de Alfaro, L., Forejt, V., Kwiatkowska, M.: Model checking probabilistic systems. In: Handbook of Model Checking, pp. 963\u2013999. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-10575-8_28"},{"key":"8_CR8","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1007\/978-3-030-73959-1_8","volume-title":"Trustworthy AI - Integrating Learning, Optimization and Reasoning","author":"C Baier","year":"2021","unstructured":"Baier, C., et al.: Lab conditions for research on\u00a0explainable automated decisions. In: Heintz, F., Milano, M., O\u2019Sullivan, B. (eds.) TAILOR 2020. LNCS (LNAI), vol. 12641, pp. 83\u201390. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-73959-1_8"},{"key":"8_CR9","doi-asserted-by":"publisher","unstructured":"Banerjee, D., Xu, C., Singh, G.: Input-relational verification of deep neural networks. Proc. ACM Program. Lang. 8(PLDI), 1\u201327 (2024). https:\/\/doi.org\/10.1145\/3656377","DOI":"10.1145\/3656377"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents. J. Artif. Intell. Res. 47, 253\u2013279 (2013)","DOI":"10.1613\/jair.3912"},{"key":"8_CR11","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. J. Artif. Intell. Res. 47, 253\u2013279 (2013). https:\/\/doi.org\/10.1613\/jair.3912","journal-title":"J. Artif. Intell. Res."},{"key":"8_CR12","doi-asserted-by":"publisher","unstructured":"Berner, C., et\u00a0al.: Dota 2 with large scale deep reinforcement learning. arXiv preprint arXiv:1912.06680 (2019). https:\/\/doi.org\/10.48550\/arXiv.1912.06680","DOI":"10.48550\/arXiv.1912.06680"},{"key":"8_CR13","unstructured":"Bernstein, S.: On a modification of Chebyshev\u2019s inequality and of the error formula of Laplace. Ann. Sci. Inst. Sav. Ukraine, Sect. Math 1(4), 38\u201349 (1924)"},{"key":"8_CR14","unstructured":"Bernstein, S.: Theory of Probability, 2 edn. (1934)"},{"key":"8_CR15","unstructured":"Brockman, G., et al.: Openai gym (2016)"},{"key":"8_CR16","doi-asserted-by":"publisher","unstructured":"Brockman, G., et al.: OpenAI Gym. arXiv preprint arXiv:1606.01540 (2016). https:\/\/doi.org\/10.48550\/arXiv.1606.01540","DOI":"10.48550\/arXiv.1606.01540"},{"key":"8_CR17","unstructured":"Brown, T., et\u00a0al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems, vol.\u00a033, pp. 1877\u20131901. Curran Associates, Inc. (2020). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html"},{"key":"8_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TSE.2024.3392720","volume":"01","author":"H Bu","year":"2024","unstructured":"Bu, H., Sun, M.: Clopper-pearson algorithms for efficient statistical model checking estimation. IEEE Trans. Softw. Eng. 01, 1\u201320 (2024). https:\/\/doi.org\/10.1109\/TSE.2024.3392720","journal-title":"IEEE Trans. Softw. Eng."},{"issue":"6","key":"8_CR19","doi-asserted-by":"publisher","first-page":"759","DOI":"10.1007\/S10009-020-00563-2","volume":"22","author":"CE Budde","year":"2020","unstructured":"Budde, C.E., D\u2019Argenio, P.R., Hartmanns, A., Sedwards, S.: An efficient statistical model checker for nondeterminism and rare events. Int. J. Softw. Tools Technol. Transf. 22(6), 759\u2013780 (2020). https:\/\/doi.org\/10.1007\/S10009-020-00563-2","journal-title":"Int. J. Softw. Tools Technol. Transf."},{"key":"8_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/978-3-662-54580-5_9","volume-title":"Tools and Algorithms for the Construction and Analysis of Systems","author":"CE Budde","year":"2017","unstructured":"Budde, C.E., Dehnert, C., Hahn, E.M., Hartmanns, A., Junges, S., Turrini, A.: JANI: quantitative model and tool interaction. In: Legay, A., Margaria, T. (eds.) TACAS 2017. LNCS, vol. 10206, pp. 151\u2013168. Springer, Heidelberg (2017). https:\/\/doi.org\/10.1007\/978-3-662-54580-5_9"},{"key":"8_CR21","doi-asserted-by":"publisher","unstructured":"Budde, C.E., Hartmanns, A., Meggendorfer, T., Weininger, M., Wienh\u00f6ft, P.: Sound statistical model checking for probabilities and expected rewards. In: 31st International Conference on Tools and Algorithms for Construction and Analysis of Systems (TACAS). Lecture Notes in Computer Science. Springer, Heidelberg (2025). https:\/\/doi.org\/10.1007\/978-3-031-90643-5_9","DOI":"10.1007\/978-3-031-90643-5_9"},{"key":"8_CR22","unstructured":"Burda, Y., Edwards, H., Storkey, A., Klimov, O.: Exploration by random network distillation. arXiv preprint arXiv:1810.12894 (2018)"},{"key":"8_CR23","doi-asserted-by":"publisher","unstructured":"Castro, P.S., Moitra, S., Gelada, C., Kumar, S., Bellemare, M.G.: Dopamine: a research framework for deep reinforcement Learning. arXiv preprint arXiv:1812.06110 (2018). https:\/\/doi.org\/10.48550\/arXiv.1812.06110","DOI":"10.48550\/arXiv.1812.06110"},{"key":"8_CR24","unstructured":"Chevalier-Boisvert, M., et al.: Minigrid & miniworld: modular & customizable reinforcement learning environments for goal-oriented tasks. CoRR arxiv:2306.13831 (2023)"},{"issue":"2","key":"8_CR25","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1214\/aoms\/1177700156","volume":"36","author":"YS Chow","year":"1965","unstructured":"Chow, Y.S., Robbins, H.: On the asymptotic theory of fixed-width sequential confidence intervals for the mean. Ann. Math. Stat. 36(2), 457\u2013462 (1965). https:\/\/doi.org\/10.1214\/aoms\/1177700156","journal-title":"Ann. Math. Stat."},{"key":"8_CR26","unstructured":"Cobbe, K., Hesse, C., Hilton, J., Schulman, J.: Leveraging procedural generation to benchmark reinforcement learning. In: International Conference on Machine Learning, pp. 2048\u20132056. PMLR (2020)"},{"key":"8_CR27","unstructured":"Corsi, D., Marchesini, E., Farinelli, A.: Formal verification of neural networks for safety-critical tasks in deep reinforcement learning. In: de\u00a0Campos, C.P., Maathuis, M.H., Quaeghebeur, E. (eds.) 37th Conference on Uncertainty in Artificial Intelligence (UAI). Proceedings of Machine Learning Research, vol.\u00a0161, pp. 333\u2013343. AUAI Press (2021). https:\/\/proceedings.mlr.press\/v161\/corsi21a.html"},{"key":"8_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"592","DOI":"10.1007\/978-3-319-63390-9_31","volume-title":"Computer Aided Verification","author":"C Dehnert","year":"2017","unstructured":"Dehnert, C., Junges, S., Katoen, J.-P., Volk, M.: A storm is coming: a modern probabilistic model checker. In: Majumdar, R., Kun\u010dak, V. (eds.) CAV 2017. LNCS, vol. 10427, pp. 592\u2013600. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-63390-9_31"},{"key":"8_CR29","doi-asserted-by":"publisher","unstructured":"Duan, J., Guan, Y., Li, S.E., Ren, Y., Sun, Q., Cheng, B.: Distributional soft actor-critic: off-policy reinforcement learning for addressing value estimation errors. IEEE Trans. Neural Networks Learn. Syst. 33(11), 6584\u20136598 (2022). https:\/\/doi.org\/10.1109\/TNNLS.2021.3082568","DOI":"10.1109\/TNNLS.2021.3082568"},{"issue":"3","key":"8_CR30","doi-asserted-by":"publisher","first-page":"642","DOI":"10.1214\/aoms\/1177728174","volume":"27","author":"A Dvoretzky","year":"1956","unstructured":"Dvoretzky, A., Kiefer, J., Wolfowitz, J.: Asymptotic minimax character of the sample distribution function and of the classical multinomial estimator. Ann. Math. Stat. 27(3), 642\u2013669 (1956). https:\/\/doi.org\/10.1214\/aoms\/1177728174","journal-title":"Ann. Math. Stat."},{"key":"8_CR31","unstructured":"Gros, T.P.: Tracking the race: analyzing racetrack agents trained with imitation learning and deep reinforcement learning. Master\u2019s thesis 5 (2021)"},{"issue":"4","key":"8_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3607198","volume":"33","author":"TP Gros","year":"2023","unstructured":"Gros, T.P., et al.: Dsmc evaluation stages: fostering robust and safe behavior in deep reinforcement learning-extended version. ACM Trans. Model. Comput. Simul. 33(4), 1\u201328 (2023)","journal-title":"ACM Trans. Model. Comput. Simul."},{"key":"8_CR33","unstructured":"Gros, T.P., Gro\u00df, D., Kamp, J., Gumhold, S., Hoffman, J.: Visual analysis of action policy behavior: a case study in grid-world driving. In: World Conference on Explainable Artificial Intelligence. Springer, Heidelberg (2025)"},{"key":"8_CR34","doi-asserted-by":"publisher","unstructured":"Gros, T.P., Hermanns, H., Hoffmann, J., Klauck, M., K\u00f6hl, M.A., Wolf, V.: Mogym: using formal models for training and verifying decision-making agents. In: International Conference on Computer Aided Verification, pp. 430\u2013443. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-13188-2_21","DOI":"10.1007\/978-3-031-13188-2_21"},{"key":"8_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1007\/978-3-030-50086-3_6","volume-title":"Formal Techniques for Distributed Objects, Components, and Systems","author":"TP Gros","year":"2020","unstructured":"Gros, T.P., Hermanns, H., Hoffmann, J., Klauck, M., Steinmetz, M.: Deep statistical model checking. In: Gotsman, A., Sokolova, A. (eds.) FORTE 2020. LNCS, vol. 12136, pp. 96\u2013114. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-50086-3_6"},{"issue":"3","key":"8_CR36","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1007\/s10009-022-00685-9","volume":"25","author":"TP Gros","year":"2023","unstructured":"Gros, T.P., Hermanns, H., Hoffmann, J., Klauck, M., Steinmetz, M.: Analyzing neural network behavior through deep statistical model checking. Int. J. Softw. Tools Technol. Transfer 25(3), 407\u2013426 (2023)","journal-title":"Int. J. Softw. Tools Technol. Transfer"},{"key":"8_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1007\/978-3-030-85172-9_11","volume-title":"Quantitative Evaluation of Systems","author":"TP Gros","year":"2021","unstructured":"Gros, T.P., H\u00f6ller, D., Hoffmann, J., Klauck, M., Meerkamp, H., Wolf, V.: Dsmc evaluation stages: fostering robust and safe behavior in deep reinforcement learning. In: Abate, A., Marin, A. (eds.) QEST 2021. LNCS, vol. 12846, pp. 197\u2013216. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-85172-9_11"},{"key":"8_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1007\/978-3-030-59854-9_2","volume-title":"Quantitative Evaluation of Systems","author":"TP Gros","year":"2020","unstructured":"Gros, T.P., H\u00f6ller, D., Hoffmann, J., Wolf, V.: Tracking the race between deep reinforcement learning and imitation learning. In: Gribaudo, M., Jansen, D.N., Remke, A. (eds.) QEST 2020. LNCS, vol. 12289, pp. 11\u201317. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59854-9_2"},{"key":"8_CR39","doi-asserted-by":"crossref","unstructured":"Gros, T.P., M\u00fcller, N., H\u00f6ller, D., Hoffmann, J., Wolf, V.: Safe reinforcement learning through regret and state restorations in evaluation stages. Currently in publication (2024)","DOI":"10.1007\/978-3-031-75778-5_2"},{"key":"8_CR40","doi-asserted-by":"publisher","unstructured":"Gross, D., Jansen, N., Junges, S., P\u00e9rez, G.A.: Cool-mc: a comprehensive tool for reinforcement learning and model checking. In: International Symposium on Dependable Software Engineering: Theories, Tools, and Applications, pp. 41\u201349. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-21213-0_3","DOI":"10.1007\/978-3-031-21213-0_3"},{"key":"8_CR41","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861\u20131870. PMLR (2018)"},{"key":"8_CR42","unstructured":"Hafner, D., Lillicrap, T., Norouzi, M., Ba, J.: Mastering atari with discrete world models. arXiv preprint arXiv:2010.02193 (2020)"},{"key":"8_CR43","doi-asserted-by":"publisher","unstructured":"Hartmanns, A., Hermanns, H.: The Modest Toolset: an integrated environment for quantitative modelling and verification. In: \u00c1brah\u00e1m, E., Havelund, K. (eds.) TACAS 2014. LNCS, vol. 8413, pp. 593\u2013598. Springer, Heidelberg (2014). https:\/\/doi.org\/10.1007\/978-3-642-54862-8_51","DOI":"10.1007\/978-3-642-54862-8_51"},{"key":"8_CR44","doi-asserted-by":"crossref","unstructured":"Hessel, M., et al.: Rainbow: combining improvements in deep reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.11796"},{"issue":"301","key":"8_CR45","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(301), 13\u201330 (1963). https:\/\/doi.org\/10.1080\/01621459.1963.10500830","journal-title":"J. Am. Stat. Assoc."},{"key":"8_CR46","unstructured":"Huang, S., et al.: CleanRL: high-quality single-file implementations of deep reinforcement learning algorithms. J. Mach. Learn. Res. 23(274), 1\u201318 (2022). http:\/\/jmlr.org\/papers\/v23\/21-1342.html"},{"key":"8_CR47","unstructured":"Jansen, N., K\u00f6nighofer, B., Junges, S., Serban, A., Bloem, R.: Safe reinforcement learning using probabilistic shields. In: 31st International Conference on Concurrency Theory (CONCUR 2020). Schloss-Dagstuhl-Leibniz Zentrum f\u00fcr Informatik (2020)"},{"key":"8_CR48","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"},{"key":"8_CR49","doi-asserted-by":"publisher","unstructured":"Legay, A., Lukina, A., Traonouez, L.M., Yang, J., Smolka, S.A., Grosu, R.: Statistical model checking. In: Steffen, B., Woeginger, G.J. (eds.) Computing and Software Science \u2013 State of the Art and Perspectives, Lecture Notes in Computer Science, vol. 10000, pp. 478\u2013504. Springer, Heidelberg (2019). https:\/\/doi.org\/10.1007\/978-3-319-91908-9_23","DOI":"10.1007\/978-3-319-91908-9_23"},{"issue":"3","key":"8_CR50","doi-asserted-by":"publisher","first-page":"1269","DOI":"10.1214\/aop\/1176990746","volume":"18","author":"P Massart","year":"1990","unstructured":"Massart, P.: The tight constant in the dvoretzky-kiefer-wolfowitz inequality. Ann. Probab. 18(3), 1269\u20131283 (1990). https:\/\/doi.org\/10.1214\/aop\/1176990746","journal-title":"Ann. Probab."},{"key":"8_CR51","doi-asserted-by":"publisher","unstructured":"Meggendorfer, T., Weininger, M., Wienh\u00f6ft, P.: What are the odds? Improving the foundations of statistical model checking. CoRR arxiv:2404.05424 (2024). https:\/\/doi.org\/10.48550\/ARXIV.2404.05424","DOI":"10.48550\/ARXIV.2404.05424"},{"key":"8_CR52","doi-asserted-by":"crossref","unstructured":"Mnih, V., et\u00a0al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","DOI":"10.1038\/nature14236"},{"key":"8_CR53","doi-asserted-by":"publisher","unstructured":"Mnih, V., Szepesv\u00e1ri, C., Audibert, J.Y.: Empirical Bernstein stopping. In: Cohen, W.W., McCallum, A., Roweis, S.T. (eds.) 25th International Conference on Machine Learning (ICML). ACM International Conference Proceeding Series, vol.\u00a0307, pp. 672\u2013679. ACM (2008). https:\/\/doi.org\/10.1145\/1390156.1390241","DOI":"10.1145\/1390156.1390241"},{"key":"8_CR54","doi-asserted-by":"publisher","unstructured":"Narodytska, N.: Formal verification of deep neural networks. In: Bj\u00f8rner, N.S., Gurfinkel, A. (eds.) 18th Conference on Formal Methods in Computer Aided Design (FMCAD). IEEE (2018). https:\/\/doi.org\/10.23919\/FMCAD.2018.8603017","DOI":"10.23919\/FMCAD.2018.8603017"},{"key":"8_CR55","doi-asserted-by":"publisher","unstructured":"Parmentier, M., Legay, A.: Adaptive stopping algorithms based on concentration inequalities. In: Steffen, B. (ed.) 2nd International Conference on Bridging the Gap Between AI and Reality (AISoLA). Lecture Notes in Computer Science, vol. 15217, pp. 336\u2013353. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-75434-0_23","DOI":"10.1007\/978-3-031-75434-0_23"},{"key":"8_CR56","unstructured":"Phan, M., Thomas, P.S., Learned-Miller, E.G.: Towards practical mean bounds for small samples. In: Meila, M., Zhang, T. (eds.) 38th International Conference on Machine Learning (ICML). Proceedings of Machine Learning Research, vol.\u00a0139, pp. 8567\u20138576. PMLR (2021). http:\/\/proceedings.mlr.press\/v139\/phan21a.html"},{"key":"8_CR57","unstructured":"Pranger, S.: Minigridsafe: an extension of the minigrid library for safe reinforcement learning (2025). https:\/\/github.com\/PrangerStefan\/MinigridSafex"},{"key":"8_CR58","unstructured":"Raffin, A., Hill, A., Gleave, A., Kanervisto, A., Ernestus, M., Dormann, N.: Stable-Baselines3: reliable reinforcement learning implementations. J. Mach. Learn. Res. 22(268), 1\u20138 (2021). http:\/\/jmlr.org\/papers\/v22\/20-1364.html"},{"key":"8_CR59","doi-asserted-by":"publisher","unstructured":"Schl\u00fcter, M., Steffen, B.: Affinitree: a compositional framework for formal analysis and explanation of deep neural networks. In: Huisman, M., Howar, F. (eds.) 18th International Conference on Tests and Proofs (TAP). Lecture Notes in Computer Science, vol. 15153, pp. 148\u2013167. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-72044-4_8","DOI":"10.1007\/978-3-031-72044-4_8"},{"key":"8_CR60","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"issue":"7792","key":"8_CR61","doi-asserted-by":"publisher","first-page":"706","DOI":"10.1038\/s41586-019-1923-7","volume":"577","author":"AW Senior","year":"2020","unstructured":"Senior, A.W., et al.: Improved protein structure prediction using potentials from deep learning. Nature 577(7792), 706\u2013710 (2020)","journal-title":"Nature"},{"key":"8_CR62","first-page":"15032","volume":"34","author":"J Terry","year":"2021","unstructured":"Terry, J., et al.: Pettingzoo: gym for multi-agent reinforcement learning. Adv. Neural. Inf. Process. Syst. 34, 15032\u201315043 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR63","doi-asserted-by":"publisher","unstructured":"Todorov, E., Erez, T., Tassa, Y.: MuJoCo: a physics engine for model-based control. In: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 5026\u20135033 (2012). https:\/\/doi.org\/10.1109\/IROS.2012.6386109","DOI":"10.1109\/IROS.2012.6386109"},{"key":"8_CR64","doi-asserted-by":"publisher","unstructured":"Towers, M., et al.: Gymnasium: a standard interface for reinforcement learning environments. arXiv preprint arXiv:2407.17032 (2024). https:\/\/doi.org\/10.48550\/arXiv.2407.17032","DOI":"10.48550\/arXiv.2407.17032"},{"key":"8_CR65","unstructured":"Towers, M., et\u00a0al.: Gymnasium: a standard interface for reinforcement learning environments. arXiv preprint arXiv:2407.17032 (2024)"},{"key":"8_CR66","doi-asserted-by":"publisher","unstructured":"Vandin, A.: Statistical model checking of python agent-based models: an integration of multivesta and mesa. In: Steffen, B. (ed.) 2nd International Conference on Bridging the Gap Between AI and Reality (AISoLA). Lecture Notes in Computer Science, vol. 15217, pp. 398\u2013419. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-75434-0_26","DOI":"10.1007\/978-3-031-75434-0_26"},{"key":"8_CR67","doi-asserted-by":"publisher","unstructured":"Vandin, A., Giachini, D., Lamperti, F., Chiaromonte, F.: Multivesta: statistical analysis of economic agent-based models by statistical model checking. In: Bowles, J., Broccia, G., Pellungrini, R. (eds.) 10th International DataMod Symposium \u2013 From Data to Models and Back. Lecture Notes in Computer Science, vol. 13268, pp.\u00a03\u20136. Springer, Heidelberg (2021). https:\/\/doi.org\/10.1007\/978-3-031-16011-0_1","DOI":"10.1007\/978-3-031-16011-0_1"},{"key":"8_CR68","doi-asserted-by":"crossref","unstructured":"Vinyals, O., et\u00a0al.: Grandmaster level in starcraft ii using multi-agent reinforcement learning. Nature 575(7782), 350\u2013354 (2019)","DOI":"10.1038\/s41586-019-1724-z"},{"key":"8_CR69","doi-asserted-by":"publisher","unstructured":"Younes, H.L.S., Simmons, R.G.: Probabilistic verification of discrete event systems using acceptance sampling. In: Brinksma, E., Larsen, K.G. (eds.) 14th International Conference on Computer Aided Verification (CAV). Lecture Notes in Computer Science, vol.\u00a02404, pp. 223\u2013235. Springer, Heidelberg (2002). https:\/\/doi.org\/10.1007\/3-540-45657-0_17","DOI":"10.1007\/3-540-45657-0_17"}],"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\/978-3-032-05792-1_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T10:31:51Z","timestamp":1759314711000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05792-1_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,2]]},"ISBN":["9783032057914","9783032057921"],"references-count":69,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05792-1_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,2]]},"assertion":[{"value":"2 October 2025","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":"Aarhus","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Denmark","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"qest2025","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"}}]}}