{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T02:44:49Z","timestamp":1778121889994,"version":"3.51.4"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031460012","type":"print"},{"value":"9783031460029","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,12,14]],"date-time":"2023-12-14T00:00:00Z","timestamp":1702512000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,14]],"date-time":"2023-12-14T00:00:00Z","timestamp":1702512000000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-46002-9_3","type":"book-chapter","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T16:02:36Z","timestamp":1702483356000},"page":"33-54","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Shielded Reinforcement Learning for\u00a0Hybrid Systems"],"prefix":"10.1007","author":[{"given":"Asger Horn","family":"Brorholt","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter Gj\u00f8l","family":"Jensen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kim Guldstrand","family":"Larsen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florian","family":"Lorber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christian","family":"Schilling","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,12,14]]},"reference":[{"key":"3_CR1","unstructured":"Reproducibility package - shielded reinforcement learning for hybrid systems. https:\/\/github.com\/AsgerHB\/Shielded-Learning-for-Hybrid-Systems"},{"key":"3_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1007\/978-3-540-71493-4_4","volume-title":"Hybrid Systems: Computation and Control","author":"A Abate","year":"2007","unstructured":"Abate, A., Amin, S., Prandini, M., Lygeros, J., Sastry, S.: Computational approaches to reachability analysis of stochastic hybrid systems. In: Bemporad, A., Bicchi, A., Buttazzo, G. (eds.) HSCC 2007. LNCS, vol. 4416, pp. 4\u201317. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-71493-4_4"},{"key":"3_CR3","doi-asserted-by":"publisher","unstructured":"Alshiekh, M., Bloem, R., Ehlers, R., K\u00f6nighofer, B., Niekum, S., Topcu, U.: Safe reinforcement learning via shielding. In: AAAI, pp. 2669\u20132678. AAAI Press (2018). https:\/\/doi.org\/10.1609\/aaai.v32i1.11797","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"3_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1007\/978-3-030-30281-8_9","volume-title":"Quantitative Evaluation of Systems","author":"P Ashok","year":"2019","unstructured":"Ashok, P., K\u0159et\u00ednsk\u00fd, J., Larsen, K.G., Le Co\u00ebnt, A., Taankvist, J.H., Weininger, M.: SOS: safe, optimal and small strategies for hybrid markov decision processes. In: Parker, D., Wolf, V. (eds.) QEST 2019. LNCS, vol. 11785, pp. 147\u2013164. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-30281-8_9"},{"key":"3_CR5","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). https:\/\/doi.org\/10.1613\/jair.1.14253","journal-title":"J. Artif. Intell. Res."},{"key":"3_CR6","doi-asserted-by":"publisher","unstructured":"Bastani, O., Li, S.: Safe reinforcement learning via statistical model predictive shielding. In: Robotics (2021). https:\/\/doi.org\/10.15607\/RSS.2021.XVII.026","DOI":"10.15607\/RSS.2021.XVII.026"},{"key":"3_CR7","unstructured":"Berkenkamp, F., Turchetta, M., Schoellig, A.P., Krause, A.: Safe model-based reinforcement learning with stability guarantees. In: NeurIPS, pp. 908\u2013918 (2017). https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/766ebcd59621e305170616ba3d3dac32-Abstract.html"},{"issue":"3","key":"3_CR8","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1051\/ita:2002013","volume":"36","author":"J Bernet","year":"2002","unstructured":"Bernet, J., Janin, D., Walukiewicz, I.: Permissive strategies: from parity games to safety games. RAIRO Theor. Informatics Appl. 36(3), 261\u2013275 (2002). https:\/\/doi.org\/10.1051\/ita:2002013","journal-title":"RAIRO Theor. Informatics Appl."},{"key":"3_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1007\/978-3-662-46681-0_51","volume-title":"Tools and Algorithms for the Construction and Analysis of Systems","author":"R Bloem","year":"2015","unstructured":"Bloem, R., K\u00f6nighofer, B., K\u00f6nighofer, R., Wang, C.: Shield Synthesis: In: Baier, C., Tinelli, C. (eds.) TACAS 2015. LNCS, vol. 9035, pp. 533\u2013548. Springer, Heidelberg (2015). https:\/\/doi.org\/10.1007\/978-3-662-46681-0_51"},{"key":"3_CR10","doi-asserted-by":"publisher","unstructured":"Bogomolov, S., Forets, M., Frehse, G., Potomkin, K., Schilling, C.: JuliaReach: a toolbox for set-based reachability. In: HSCC, pp. 39\u201344. ACM (2019). https:\/\/doi.org\/10.1145\/3302504.3311804","DOI":"10.1145\/3302504.3311804"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Bujorianu, L.M.: Stochastic reachability analysis of hybrid systems. Springer Science & Business Media (2012)","DOI":"10.1007\/978-1-4471-2795-6"},{"key":"3_CR12","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1016\/j.arcontrol.2018.09.005","volume":"46","author":"L Busoniu","year":"2018","unstructured":"Busoniu, L., de Bruin, T., Tolic, D., Kober, J., Palunko, I.: Reinforcement learning for control: Performance, stability, and deep approximators. Annu. Rev. Control. 46, 8\u201328 (2018). https:\/\/doi.org\/10.1016\/j.arcontrol.2018.09.005","journal-title":"Annu. Rev. Control."},{"key":"3_CR13","doi-asserted-by":"publisher","unstructured":"Carr, S., Jansen, N., Junges, S., Topcu, U.: Safe reinforcement learning via shielding under partial observability. In: AAAI, pp. 14748\u201314756. AAAI Press (2023). https:\/\/doi.org\/10.1609\/aaai.v37i12.26723","DOI":"10.1609\/aaai.v37i12.26723"},{"key":"3_CR14","doi-asserted-by":"publisher","unstructured":"Cheng, R., Orosz, G., Murray, R.M., Burdick, J.W.: End-to-end safe reinforcement learning through barrier functions for safety-critical continuous control tasks. In: AAAI, pp. 3387\u20133395. AAAI Press (2019). https:\/\/doi.org\/10.1609\/aaai.v33i01.33013387","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"3_CR15","unstructured":"Chow, Y., Nachum, O., Du\u00e9\u00f1ez-Guzm\u00e1n, E.A., Ghavamzadeh, M.: A Lyapunov-based approach to safe reinforcement learning. In: NeurIPS, pp. 8103\u20138112 (2018), https:\/\/proceedings.neurips.cc\/paper\/2018\/hash\/4fe5149039b52765bde64beb9f674940-Abstract.html"},{"issue":"1","key":"3_CR16","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/S0747-7171(88)80004-X","volume":"5","author":"JH Davenport","year":"1988","unstructured":"Davenport, J.H., Heintz, J.: Real quantifier elimination is doubly exponential. J. Symb. Comput. 5(1), 29\u201335 (1988). https:\/\/doi.org\/10.1016\/S0747-7171(88)80004-X","journal-title":"J. Symb. Comput."},{"key":"3_CR17","doi-asserted-by":"publisher","unstructured":"David, A., et al.: Statistical model checking for stochastic hybrid systems. In: HSBm EPTCS, vol. 92, pp. 122\u2013136 (2012). https:\/\/doi.org\/10.4204\/EPTCS.92.9","DOI":"10.4204\/EPTCS.92.9"},{"key":"3_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1007\/978-3-662-46681-0_16","volume-title":"Tools and Algorithms for the Construction and Analysis of Systems","author":"A David","year":"2015","unstructured":"David, A., Jensen, P.G., Larsen, K.G., Miku\u010dionis, M., Taankvist, J.H.:  Uppaal Stratego. In: Baier, C., Tinelli, C. (eds.) TACAS 2015. LNCS, vol. 9035, pp. 206\u2013211. Springer, Heidelberg (2015). https:\/\/doi.org\/10.1007\/978-3-662-46681-0_16"},{"key":"3_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1007\/978-3-642-14295-6_17","volume-title":"Computer Aided Verification","author":"A Donz\u00e9","year":"2010","unstructured":"Donz\u00e9, A.: Breach, a toolbox for verification and parameter synthesis of hybrid systems. In: Touili, T., Cook, B., Jackson, P. (eds.) CAV 2010. LNCS, vol. 6174, pp. 167\u2013170. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-14295-6_17"},{"key":"3_CR20","doi-asserted-by":"publisher","first-page":"1047","DOI":"10.1007\/978-3-319-10575-8_30","volume-title":"Handbook of Model Checking","author":"L Doyen","year":"2018","unstructured":"Doyen, L., Frehse, G., Pappas, G.J., Platzer, A.: Verification of hybrid systems. In: Handbook of Model Checking, pp. 1047\u20131110. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-10575-8_30"},{"key":"3_CR21","unstructured":"Doyle, J.C., Francis, B.A., Tannenbaum, A.R.: Feedback control theory. Courier Corporation (2013)"},{"key":"3_CR22","doi-asserted-by":"publisher","unstructured":"Forets, M., Freire, D., Schilling, C.: Efficient reachability analysis of parametric linear hybrid systems with time-triggered transitions. In: MEMOCODE, pp. 1\u20136. IEEE (2020). https:\/\/doi.org\/10.1109\/MEMOCODE51338.2020.9314994","DOI":"10.1109\/MEMOCODE51338.2020.9314994"},{"key":"3_CR23","doi-asserted-by":"publisher","first-page":"1437","DOI":"10.5555\/2789272.2886795","volume":"16","author":"J Garc\u00eda","year":"2015","unstructured":"Garc\u00eda, J., Fern\u00e1ndez, F.: A comprehensive survey on safe reinforcement learning. J. Mach. Learn. Res. 16, 1437\u20131480 (2015). https:\/\/doi.org\/10.5555\/2789272.2886795","journal-title":"J. Mach. Learn. Res."},{"key":"3_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1007\/978-3-642-02658-4_40","volume-title":"Computer Aided Verification","author":"C Le Guernic","year":"2009","unstructured":"Le Guernic, C., Girard, A.: Reachability analysis of hybrid systems using support functions. In: Bouajjani, A., Maler, O. (eds.) CAV 2009. LNCS, vol. 5643, pp. 540\u2013554. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-02658-4_40"},{"key":"3_CR25","doi-asserted-by":"publisher","unstructured":"Hasanbeig, M., Abate, A., Kroening, D.: Cautious reinforcement learning with logical constraints. In: AAMAS, pp. 483\u2013491 (2020). https:\/\/doi.org\/10.5555\/3398761.3398821","DOI":"10.5555\/3398761.3398821"},{"issue":"1","key":"3_CR26","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1006\/jcss.1998.1581","volume":"57","author":"TA Henzinger","year":"1998","unstructured":"Henzinger, T.A., Kopke, P.W., Puri, A., Varaiya, P.: What\u2019s decidable about hybrid automata? J. Comput. Syst. Sci. 57(1), 94\u2013124 (1998). https:\/\/doi.org\/10.1006\/jcss.1998.1581","journal-title":"J. Comput. Syst. Sci."},{"key":"3_CR27","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":"3_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1007\/978-3-030-31784-3_5","volume-title":"Automated Technology for Verification and Analysis","author":"M Jaeger","year":"2019","unstructured":"Jaeger, M., Jensen, P.G., Guldstrand Larsen, K., Legay, A., Sedwards, S., Taankvist, J.H.: Teaching stratego to play ball: optimal synthesis for continuous space MDPs. In: Chen, Y.-F., Cheng, C.-H., Esparza, J. (eds.) ATVA 2019. LNCS, vol. 11781, pp. 81\u201397. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-31784-3_5"},{"key":"3_CR29","doi-asserted-by":"publisher","unstructured":"Jansen, N., K\u00f6nighofer, B., Junges, S., Serban, A., Bloem, R.: Safe reinforcement learning using probabilistic shields. In: CONCUR, LIPIcs, vol. 171, pp. 3:1\u20133:16. Schloss Dagstuhl - Leibniz-Zentrum f\u00fcr Informatik (2020). https:\/\/doi.org\/10.4230\/LIPIcs.CONCUR.2020.3","DOI":"10.4230\/LIPIcs.CONCUR.2020.3"},{"key":"3_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1007\/3-540-36580-X_22","volume-title":"Hybrid Systems: Computation and Control","author":"J Kapinski","year":"2003","unstructured":"Kapinski, J., Krogh, B.H., Maler, O., Stursberg, O.: On systematic simulation of open continuous systems. In: Maler, O., Pnueli, A. (eds.) HSCC 2003. LNCS, vol. 2623, pp. 283\u2013297. Springer, Heidelberg (2003). https:\/\/doi.org\/10.1007\/3-540-36580-X_22"},{"issue":"2","key":"3_CR31","doi-asserted-by":"publisher","first-page":"968","DOI":"10.1109\/TPEL.2013.2256370","volume":"29","author":"P Karamanakos","year":"2013","unstructured":"Karamanakos, P., Geyer, T., Manias, S.: Direct voltage control of DC-DC boost converters using enumeration-based model predictive control. IEEE Trans. Power Electron. 29(2), 968\u2013978 (2013)","journal-title":"IEEE Trans. Power Electron."},{"key":"3_CR32","doi-asserted-by":"publisher","unstructured":"Klischat, M., Althoff, M.: A multi-step approach to accelerate the computation of reachable sets for road vehicles. In: ITSC, pp. 1\u20137. IEEE (2020). https:\/\/doi.org\/10.1109\/ITSC45102.2020.9294328","DOI":"10.1109\/ITSC45102.2020.9294328"},{"issue":"7","key":"3_CR33","doi-asserted-by":"publisher","first-page":"2235","DOI":"10.1090\/S0002-9939-02-06753-9","volume":"131","author":"M Laczkovich","year":"2003","unstructured":"Laczkovich, M.: The removal of $$\\pi $$ from some undecidable problems involving elementary functions. Proc. Am. Math. Soc. 131(7), 2235\u20132240 (2003). https:\/\/doi.org\/10.1090\/S0002-9939-02-06753-9","journal-title":"Proc. Am. Math. Soc."},{"key":"3_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1007\/978-3-642-33365-1_2","volume-title":"Formal Modeling and Analysis of Timed Systems","author":"KG Larsen","year":"2012","unstructured":"Larsen, K.G.: Statistical model checking, refinement checking, optimization, for stochastic hybrid systems. In: Jurdzi\u0144ski, M., Ni\u010dkovi\u0107, D. (eds.) FORMATS 2012. LNCS, vol. 7595, pp. 7\u201310. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33365-1_2"},{"key":"3_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/978-3-030-23703-5_6","volume-title":"Cyber Physical Systems. Model-Based Design","author":"KG Larsen","year":"2019","unstructured":"Larsen, K.G., Le Co\u00ebnt, A., Miku\u010dionis, M., Taankvist, J.H.: Guaranteed control synthesis for continuous systems in Uppaal Tiga. In: Chamberlain, R., Taha, W., T\u00f6rngren, M. (eds.) CyPhy\/WESE -2018. LNCS, vol. 11615, pp. 113\u2013133. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-23703-5_6"},{"key":"3_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1007\/978-3-319-23506-6_17","volume-title":"Correct System Design","author":"KG Larsen","year":"2015","unstructured":"Larsen, K.G., Miku\u010dionis, M., Taankvist, J.H.: Safe and optimal adaptive cruise control. In: Meyer, R., Platzer, A., Wehrheim, H. (eds.) Correct System Design. LNCS, vol. 9360, pp. 260\u2013277. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-23506-6_17"},{"key":"3_CR37","doi-asserted-by":"crossref","unstructured":"Lewis, F.L., Vrabie, D., Syrmos, V.L.: Optimal control. John Wiley & Sons (2012)","DOI":"10.1002\/9781118122631"},{"key":"3_CR38","unstructured":"Luo, Y., Ma, T.: Learning barrier certificates: towards safe reinforcement learning with zero training-time violations. In: NeurIPS, pp. 25621\u201325632 (2021). https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/d71fa38b648d86602d14ac610f2e6194-Abstract.html"},{"key":"3_CR39","doi-asserted-by":"publisher","unstructured":"Maderbacher, B., Schupp, S., Bartocci, E., Bloem, R., Nickovic, D., K\u00f6nighofer, B.: Provable correct and adaptive simplex architecture for bounded-liveness properties. In: SPIN. LNCS, vol. 13872, pp. 141\u2013160. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-32157-3_8","DOI":"10.1007\/978-3-031-32157-3_8"},{"key":"3_CR40","doi-asserted-by":"publisher","unstructured":"Majumdar, R., Ozay, N., Schmuck, A.: On abstraction-based controller design with output feedback. In: HSCC, pp. 15:1\u201315:11. ACM (2020). https:\/\/doi.org\/10.1145\/3365365.3382219","DOI":"10.1145\/3365365.3382219"},{"key":"3_CR41","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.116830","volume":"199","author":"M Noaee","year":"2022","unstructured":"Noaee, M., et al.: Reinforcement learning in urban network traffic signal control: a systematic literature review. Expert Syst. Appl. 199, 116830 (2022). https:\/\/doi.org\/10.1016\/j.eswa.2022.116830","journal-title":"Expert Syst. Appl."},{"key":"3_CR42","doi-asserted-by":"publisher","unstructured":"Shmarov, F., Zuliani, P.: Probreach: a tool for guaranteed reachability analysis of stochastic hybrid systems. In: SNR. EPiC Series in Computing, vol. 37, pp. 40\u201348. EasyChair (2015). https:\/\/doi.org\/10.29007\/mh2c","DOI":"10.29007\/mh2c"},{"key":"3_CR43","unstructured":"Tarski, A.: A decision method for elementary algebra and geometry. The RAND Corporation (1948). https:\/\/www.rand.org\/pubs\/reports\/R109.html"},{"key":"3_CR44","doi-asserted-by":"crossref","unstructured":"Tarski, A.: A lattice-theoretical fixpoint theorem and its applications. Pacific J. Math. 5(2), 285\u2013309 (1955). https:\/\/www.projecteuclid.org\/journalArticle\/Download?urlId=pjm%2F1103044538","DOI":"10.2140\/pjm.1955.5.285"},{"issue":"3","key":"3_CR45","doi-asserted-by":"publisher","first-page":"1317","DOI":"10.1109\/TPWRS.2004.831259","volume":"19","author":"JG Vlachogiannis","year":"2004","unstructured":"Vlachogiannis, J.G., Hatziargyriou, N.D.: Reinforcement learning for reactive power control. IEEE Trans. Power Syst. 19(3), 1317\u20131325 (2004). https:\/\/doi.org\/10.1109\/TPWRS.2004.831259","journal-title":"IEEE Trans. Power Syst."},{"key":"3_CR46","doi-asserted-by":"publisher","unstructured":"\u017dikeli\u0107, D., Lechner, M., Henzinger, T.A., Chatterjee, K.: Learning control policies for stochastic systems with reach-avoid guarantees. In: AAAI, pp. 11926\u201311935. AAAI Press (2023). https:\/\/doi.org\/10.1609\/aaai.v37i10.26407","DOI":"10.1609\/aaai.v37i10.26407"},{"key":"3_CR47","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2021.109597","volume":"129","author":"KP Wabersich","year":"2021","unstructured":"Wabersich, K.P., Zeilinger, M.N.: A predictive safety filter for learning-based control of constrained nonlinear dynamical systems. Autom. 129, 109597 (2021). https:\/\/doi.org\/10.1016\/j.automatica.2021.109597","journal-title":"Autom."},{"key":"3_CR48","unstructured":"Watkins, C.J.C.H.: Learning from Delayed Rewards. Ph.D. thesis, University of Cambridge (1989)"},{"key":"3_CR49","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1007\/978-3-642-32759-9_38","volume-title":"FM 2012: Formal Methods","author":"H Zhao","year":"2012","unstructured":"Zhao, H., Zhan, N., Kapur, D., Larsen, K.G.: A \u201cHybrid\u2019\u2019 approach for synthesizing optimal controllers of hybrid systems: a case study of the oil pump industrial example. In: Giannakopoulou, D., M\u00e9ry, D. (eds.) FM 2012. LNCS, vol. 7436, pp. 471\u2013485. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-32759-9_38"}],"container-title":["Lecture Notes in Computer Science","Bridging the Gap Between AI and Reality"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-46002-9_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T16:03:22Z","timestamp":1702483402000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-46002-9_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,14]]},"ISBN":["9783031460012","9783031460029"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-46002-9_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,14]]},"assertion":[{"value":"14 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AISoLA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Bridging the Gap between AI and Reality","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Crete","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aisola2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2023-aisola.isola-conference.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}