{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T09:26:13Z","timestamp":1750843573929,"version":"3.40.3"},"publisher-location":"Cham","reference-count":65,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030945824"},{"type":"electronic","value":"9783030945831"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-030-94583-1_7","type":"book-chapter","created":{"date-parts":[[2022,1,13]],"date-time":"2022-01-13T22:02:34Z","timestamp":1642111354000},"page":"127-150","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Gradient-Descent for Randomized Controllers Under Partial Observability"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4774-7609","authenticated-orcid":false,"given":"Linus","family":"Heck","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9113-2791","authenticated-orcid":false,"given":"Jip","family":"Spel","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0978-8466","authenticated-orcid":false,"given":"Sebastian","family":"Junges","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9819-8374","authenticated-orcid":false,"given":"Joshua","family":"Moerman","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6143-1926","authenticated-orcid":false,"given":"Joost-Pieter","family":"Katoen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,1,14]]},"reference":[{"key":"7_CR1","unstructured":"Aberdeen, D.A.: Policy-gradient algorithms for partially observable Markov decision processes. Ph.D. thesis, The Australian National University (2003)"},{"key":"7_CR2","unstructured":"Alur, R., et al.: Syntax-guided synthesis. In: Dependable Software Systems Engineering, NATO Science for Peace and Security Series D: Information and Communication Security, vol. 40, pp. 1\u201325. IOS Press (2015)"},{"key":"7_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1007\/978-3-030-72016-2_11","volume-title":"Tools and Algorithms for the Construction and Analysis of Systems","author":"R Andriushchenko","year":"2021","unstructured":"Andriushchenko, R., \u010ce\u0161ka, M., Junges, S., Katoen, J.-P.: Inductive synthesis for probabilistic programs reaches new horizons. In: Groote, J.F., Larsen, K.G. (eds.) TACAS 2021. LNCS, vol. 12651, pp. 191\u2013209. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-72016-2_11"},{"issue":"1","key":"7_CR4","doi-asserted-by":"publisher","first-page":"1:1","DOI":"10.1145\/2108242.2108243","volume":"59","author":"C Baier","year":"2012","unstructured":"Baier, C., Gr\u00f6\u00dfer, M., Bertrand, N.: Probabilistic $$\\omega $$-automata. J. ACM 59(1), 1:1-1:52 (2012)","journal-title":"J. ACM"},{"key":"7_CR5","doi-asserted-by":"publisher","first-page":"104504","DOI":"10.1016\/j.ic.2019.104504","volume":"272","author":"C Baier","year":"2020","unstructured":"Baier, C., Hensel, C., Hutschenreiter, L., Junges, S., Katoen, J.P., Klein, J.: Parametric Markov chains: PCTL complexity and fraction-free Gaussian elimination. Inf. Comput. 272, 104504 (2020)","journal-title":"Inf. Comput."},{"key":"7_CR6","volume-title":"Principles of Model Checking","author":"C Baier","year":"2008","unstructured":"Baier, C., Katoen, J.P.: Principles of Model Checking. MIT Press, Cambridge (2008)"},{"key":"7_CR7","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_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1007\/978-3-030-59152-6_16","volume-title":"Automated Technology for Verification and Analysis","author":"A Bork","year":"2020","unstructured":"Bork, A., Junges, S., Katoen, J.-P., Quatmann, T.: Verification of indefinite-horizon POMDPs. In: Hung, D.V., Sokolsky, O. (eds.) ATVA 2020. LNCS, vol. 12302, pp. 288\u2013304. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59152-6_16"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Carr, S., Jansen, N., Topcu, U.: Verifiable RNN-based policies for POMDPs under temporal logic constraints. In: IJCAI, pp. 4121\u20134127. ijcai.org (2020)","DOI":"10.24963\/ijcai.2020\/570"},{"key":"7_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1007\/978-3-662-44584-6_16","volume-title":"CONCUR 2014 \u2013 Concurrency Theory","author":"T Chen","year":"2014","unstructured":"Chen, T., Feng, Y., Rosenblum, D.S., Su, G.: Perturbation analysis in verification of discrete-time Markov chains. In: Baldan, P., Gorla, D. (eds.) CONCUR 2014. LNCS, vol. 8704, pp. 218\u2013233. Springer, Heidelberg (2014). https:\/\/doi.org\/10.1007\/978-3-662-44584-6_16"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Chen, T., Hahn, E.M., Han, T., Kwiatkowska, M.Z., Qu, H., Zhang, L.: Model repair for Markov decision processes. In: TASE. IEEE (2013)","DOI":"10.1109\/TASE.2013.20"},{"key":"7_CR12","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_CR13","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_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1007\/978-3-540-31862-0_21","volume-title":"Theoretical Aspects of Computing - ICTAC 2004","author":"C Daws","year":"2005","unstructured":"Daws, C.: Symbolic and parametric model checking of discrete-time Markov chains. In: Liu, Z., Araki, K. (eds.) ICTAC 2004. LNCS, vol. 3407, pp. 280\u2013294. Springer, Heidelberg (2005). https:\/\/doi.org\/10.1007\/978-3-540-31862-0_21"},{"key":"7_CR15","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_CR16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-01492-5","volume-title":"Handbook of Weighted Automata","author":"M Droste","year":"2009","unstructured":"Droste, M., Kuich, W., Vogler, H.: Handbook of Weighted Automata. Springer, Heidelberg (2009)"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Fang, X., Calinescu, R., Gerasimou, S., Alhwikem, F.: Fast parametric model checking through model fragmentation. In: ICSE, pp. 835\u2013846. IEEE (2021)","DOI":"10.1109\/ICSE43902.2021.00081"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Filieri, A., Ghezzi, C., Tamburrelli, G.: Run-time efficient probabilistic model checking. In: ICSE. ACM (2011)","DOI":"10.1145\/1985793.1985840"},{"key":"7_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1007\/978-3-319-96145-3_17","volume-title":"Computer Aided Verification","author":"DJ Fremont","year":"2018","unstructured":"Fremont, D.J., Seshia, S.A.: Reactive control improvisation. In: Chockler, H., Weissenbacher, G. (eds.) CAV 2018. LNCS, vol. 10981, pp. 307\u2013326. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-96145-3_17"},{"key":"7_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1007\/978-3-030-01090-4_18","volume-title":"Automated Technology for Verification and Analysis","author":"P Gainer","year":"2018","unstructured":"Gainer, P., Hahn, E.M., Schewe, S.: Accelerated model checking of parametric Markov chains. In: Lahiri, S.K., Wang, C. (eds.) ATVA 2018. LNCS, vol. 11138, pp. 300\u2013316. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01090-4_18"},{"key":"7_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1007\/978-3-540-75454-1_14","volume-title":"Formal Modeling and Analysis of Timed Systems","author":"S Giro","year":"2007","unstructured":"Giro, S., D\u2019Argenio, P.R.: Quantitative model checking revisited: neither decidable nor approximable. In: Raskin, J.-F., Thiagarajan, P.S. (eds.) FORMATS 2007. LNCS, vol. 4763, pp. 179\u2013194. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-75454-1_14"},{"key":"7_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1007\/978-3-642-20398-5_12","volume-title":"NASA Formal Methods","author":"EM Hahn","year":"2011","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.) NFM 2011. LNCS, vol. 6617, pp. 146\u2013161. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-20398-5_12"},{"key":"7_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1007\/978-3-642-02652-2_10","volume-title":"Model Checking Software","author":"EM Hahn","year":"2009","unstructured":"Hahn, E.M., Hermanns, H., Zhang, L.: Probabilistic reachability for parametric Markov models. In: P\u0103s\u0103reanu, C.S. (ed.) SPIN 2009. LNCS, vol. 5578, pp. 88\u2013106. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-02652-2_10"},{"key":"7_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1007\/3-540-59497-3_175","volume-title":"From Natural to Artificial Neural Computation","author":"J Han","year":"1995","unstructured":"Han, J., Moraga, C.: The influence of the sigmoid function parameters on the speed of backpropagation learning. In: Mira, J., Sandoval, F. (eds.) IWANN 1995. LNCS, vol. 930, pp. 195\u2013201. Springer, Heidelberg (1995). https:\/\/doi.org\/10.1007\/3-540-59497-3_175"},{"key":"7_CR25","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. LNCS, vol. 11427, pp. 344\u2013350. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-17462-0_20"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Heck, L., Spel, J., Junges, S., Moerman, J., Katoen, J.P.: Gradient-descent for randomized controllers under partial observability. CoRR abs\/2111.04407 (2021, extended version)","DOI":"10.1007\/978-3-030-94583-1_7"},{"key":"7_CR27","doi-asserted-by":"publisher","unstructured":"Heck, L., Spel, J., Junges, S., Moerman, J., Katoen, J.P.: Gradient-descent for randomized controllers under partial observability (artifact). Zenodo (2021). https:\/\/doi.org\/10.4121\/14910426","DOI":"10.4121\/14910426"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Hensel, C., Junges, S., Katoen, J.P., Quatmann, T., Volk, M.: The probabilistic model checker storm. CoRR abs\/2002.07080 (2020)","DOI":"10.1007\/s10009-021-00633-z"},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Hor\u00e1k, K., Bosansk\u00fd, B., Chatterjee, K.: Goal-HSVI: heuristic search value iteration for goal POMDPs. In: IJCAI, pp. 4764\u20134770. ijcai.org (2018)","DOI":"10.24963\/ijcai.2018\/662"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Israeli, A., Jalfon, M.: Token management schemes and random walks yield self-stabilizing mutual exclusion. In: PODC, pp. 119\u2013131. ACM (1990)","DOI":"10.1145\/93385.93409"},{"key":"7_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1007\/978-3-319-10696-0_31","volume-title":"Quantitative Evaluation of Systems","author":"N Jansen","year":"2014","unstructured":"Jansen, N., et al.: Accelerating parametric probabilistic verification. In: Norman, G., Sanders, W. (eds.) QEST 2014. LNCS, vol. 8657, pp. 404\u2013420. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10696-0_31"},{"key":"7_CR32","unstructured":"Junges, S.: Parameter synthesis in Markov models. Ph.D. thesis, RWTH Aachen University, Germany (2020)"},{"key":"7_CR33","unstructured":"Junges, S., \u00c1brah\u00e1m, E., Hensel, C., Jansen, N., Katoen, J.P., Quatmann, T., Volk, M.: Parameter synthesis for Markov models. CoRR abs\/1903.07993 (2019)"},{"key":"7_CR34","unstructured":"Junges, S., et al.: Finite-state controllers of POMDPs using parameter synthesis. In: UAI. AUAI Press (2018)"},{"key":"7_CR35","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., 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_CR36","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_CR37","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (Poster) (2015)"},{"key":"7_CR38","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_CR39","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_CR40","unstructured":"Liu, L., et al.: On the variance of the adaptive learning rate and beyond. In: ICLR. OpenReview.net (2020)"},{"issue":"1","key":"7_CR41","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1287\/opre.39.1.162","volume":"39","author":"WS Lovejoy","year":"1991","unstructured":"Lovejoy, W.S.: Computationally feasible bounds for partially observed Markov decision processes. Oper. Res. 39(1), 162\u2013175 (1991)","journal-title":"Oper. Res."},{"issue":"1\u20132","key":"7_CR42","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."},{"key":"7_CR43","unstructured":"Meuleau, N., Kim, K., Kaelbling, L.P., Cassandra, A.R.: Solving POMDPs by searching the space of finite policies. In: UAI, pp. 417\u2013426. Morgan Kaufmann (1999)"},{"key":"7_CR44","unstructured":"Meuleau, N., Peshkin, L., Kim, K., Kaelbling, L.P.: Learning finite-state controllers for partially observable environments. In: UAI, pp. 427\u2013436. Morgan Kaufmann (1999)"},{"key":"7_CR45","unstructured":"Mnih, V., et al.: Playing Atari with deep reinforcement learning. CoRR abs\/1312.5602 (2013)"},{"key":"7_CR46","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.ins.2019.04.012","volume":"492","author":"E Moulay","year":"2019","unstructured":"Moulay, E., L\u00e9chapp\u00e9, V., Plestan, F.: Properties of the sign gradient descent algorithms. Inf. Sci. 492, 29\u201339 (2019)","journal-title":"Inf. Sci."},{"key":"7_CR47","unstructured":"Nesterov, Y.E.: A method for solving the convex programming problem with convergence rate $$O(1\/k^{2})$$. In: Dokl. akad. nauk Sssr, vol. 269, pp. 543\u2013547 (1983)"},{"issue":"3","key":"7_CR48","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1007\/s11241-017-9269-4","volume":"53","author":"G Norman","year":"2017","unstructured":"Norman, G., Parker, D., Zou, X.: Verification and control of partially observable probabilistic systems. Real-Time Syst. 53(3), 354\u2013402 (2017). https:\/\/doi.org\/10.1007\/s11241-017-9269-4","journal-title":"Real-Time Syst."},{"key":"7_CR49","unstructured":"Pineau, J., Gordon, G.J., Thrun, S.: Point-based value iteration: an anytime algorithm for POMDPs. In: IJCAI, pp. 1025\u20131032. Morgan Kaufmann (2003)"},{"key":"7_CR50","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_CR51","unstructured":"Ruder, S.: An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747 (2016)"},{"key":"7_CR52","volume-title":"Parallel Distributed Processing","author":"DE Rumelhart","year":"1989","unstructured":"Rumelhart, D.E.: Parallel Distributed Processing. MIT Press, Cambridge (1989)"},{"key":"7_CR53","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/978-3-030-59854-9_9","volume-title":"Quantitative Evaluation of Systems","author":"B Salmani","year":"2020","unstructured":"Salmani, B., Katoen, J.-P.: Bayesian inference by symbolic model checking. In: Gribaudo, M., Jansen, D.N., Remke, A. (eds.) QEST 2020. LNCS, vol. 12289, pp. 115\u2013133. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59854-9_9"},{"key":"7_CR54","unstructured":"Scutari, M.: Bayesian network repository (2021). https:\/\/www.bnlearn.com\/bnrepository\/"},{"key":"7_CR55","unstructured":"Silver, D., Veness, J.: Monte-Carlo planning in large POMDPs. In: NIPS, pp. 2164\u20132172. Curran Associates, Inc. (2010)"},{"issue":"1","key":"7_CR56","first-page":"C5","volume":"97","author":"AE Smith","year":"1997","unstructured":"Smith, A.E., Coit, D.W., Baeck, T., Fogel, D., Michalewicz, Z.: Penalty functions. Handb. Evol. Comput. 97(1), C5 (1997)","journal-title":"Handb. Evol. Comput."},{"key":"7_CR57","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1613\/jair.1659","volume":"24","author":"MTJ Spaan","year":"2005","unstructured":"Spaan, M.T.J., Vlassis, N.A.: Perseus: randomized point-based value iteration for POMDPs. J. Artif. Intell. Res. 24, 195\u2013220 (2005)","journal-title":"J. Artif. Intell. Res."},{"key":"7_CR58","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"479","DOI":"10.1007\/978-3-030-31784-3_28","volume-title":"Automated Technology for Verification and Analysis","author":"J Spel","year":"2019","unstructured":"Spel, J., Junges, S., Katoen, J.-P.: Are parametric Markov chains monotonic? In: Chen, Y.-F., Cheng, C.-H., Esparza, J. (eds.) ATVA 2019. LNCS, vol. 11781, pp. 479\u2013496. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-31784-3_28"},{"key":"7_CR59","unstructured":"Sutskever, I., Martens, J., Dahl, G.E., Hinton, G.E.: On the importance of initialization and momentum in deep learning. In: ICML (3). JMLR Workshop and Conference Proceedings, vol. 28, pp. 1139\u20131147. JMLR.org (2013)"},{"key":"7_CR60","volume-title":"Probabilistic Robotics","author":"S Thrun","year":"2005","unstructured":"Thrun, S., Burgard, W., Fox, D.: Probabilistic Robotics. MIT Press, Cambridge (2005)"},{"key":"7_CR61","unstructured":"Tieleman, T., Hinton, G.: Lecture 6.5\u2013RMSProp: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural Networks for Machine Learning (2012)"},{"key":"7_CR62","unstructured":"Vanderbei, R.J.: Linear programming - foundations and extensions, Kluwer International Series in Operations Research and Management Service, vol. 4. Kluwer (1998)"},{"key":"7_CR63","doi-asserted-by":"crossref","unstructured":"Walraven, E., Spaan, M.T.J.: Accelerated vector pruning for optimal POMDP solvers. In: AAAI, pp. 3672\u20133678. AAAI Press (2017)","DOI":"10.1609\/aaai.v31i1.11032"},{"issue":"3","key":"7_CR64","doi-asserted-by":"publisher","first-page":"1040","DOI":"10.1109\/TAC.2020.2990140","volume":"66","author":"L Winterer","year":"2021","unstructured":"Winterer, L., et al.: Strategy synthesis for POMDPs in robot planning via game-based abstractions. IEEE Trans. Autom. Control 66(3), 1040\u20131054 (2021)","journal-title":"IEEE Trans. Autom. Control"},{"key":"7_CR65","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/978-3-030-55754-6_7","volume-title":"NASA Formal Methods","author":"L Winterer","year":"2020","unstructured":"Winterer, L., Wimmer, R., Jansen, N., Becker, B.: Strengthening deterministic policies for POMDPs. In: Lee, R., Jha, S., Mavridou, A., Giannakopoulou, D. (eds.) NFM 2020. LNCS, vol. 12229, pp. 115\u2013132. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-55754-6_7"}],"container-title":["Lecture Notes in Computer Science","Verification, Model Checking, and Abstract Interpretation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-94583-1_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,22]],"date-time":"2023-01-22T22:17:19Z","timestamp":1674425839000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-94583-1_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030945824","9783030945831"],"references-count":65,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-94583-1_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"14 January 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"VMCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Verification, Model Checking, and Abstract Interpretation","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Philadelphia, PA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 January 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 January 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"vmcai2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/popl22.sigplan.org\/home\/VMCAI-2022","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"63","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"23","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"37% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"6","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}