{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T14:48:44Z","timestamp":1766414924374,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,5,19]],"date-time":"2021-05-19T00:00:00Z","timestamp":1621382400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["IIS-1723995, IIS-2024606, DGE-1840990"],"award-info":[{"award-number":["IIS-1723995, IIS-2024606, DGE-1840990"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,5,19]]},"DOI":"10.1145\/3447928.3456639","type":"proceedings-article","created":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T03:54:48Z","timestamp":1620100488000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Model-based reinforcement learning for approximate optimal control with temporal logic specifications"],"prefix":"10.1145","author":[{"given":"Max H.","family":"Cohen","sequence":"first","affiliation":[{"name":"Boston University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Calin","family":"Belta","sequence":"additional","affiliation":[{"name":"Boston University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,5,19]]},"reference":[{"volume-title":"Proc. Conf. Decis. Control. 6565 -- 6570","author":"Aksaray D.","key":"e_1_3_2_1_1_1","unstructured":"D. Aksaray , A. Jones , Z. Kong , M. Schwager , and C. Belta . 2016. Q-learning for robust satisfaction of signal temporal logic specifications . In Proc. Conf. Decis. Control. 6565 -- 6570 . D. Aksaray, A. Jones, Z. Kong, M. Schwager, and C. Belta. 2016. Q-learning for robust satisfaction of signal temporal logic specifications. In Proc. Conf. Decis. Control. 6565 -- 6570."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2638961"},{"key":"e_1_3_2_1_3_1","unstructured":"C. Baier and J. P. Katoen. 2008. Principles of model checking. MIT Press.  C. Baier and J. P. Katoen. 2008. Principles of model checking. MIT Press."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-053018-023717"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"C. Belta B. Yordanov and E. A. Gol. 2017. Formal methods for discrete-time dynamical systems. Springer.  C. Belta B. Yordanov and E. A. Gol. 2017. Formal methods for discrete-time dynamical systems. Springer.","DOI":"10.1007\/978-3-319-50763-7"},{"volume-title":"Proc. Amer. Control Conf. 634--639","author":"Bisoffi A.","key":"e_1_3_2_1_6_1","unstructured":"A. Bisoffi and D. V. Dimarogonas . 2018. A hybrid barrier certificate approach to satisfy linear temporal logic specifications . In Proc. Amer. Control Conf. 634--639 . A. Bisoffi and D. V. Dimarogonas. 2018. A hybrid barrier certificate approach to satisfy linear temporal logic specifications. In Proc. Amer. Control Conf. 634--639."},{"key":"e_1_3_2_1_7_1","unstructured":"A. Bisoffi and D. V. Dimarogonas. 2020. Satisfaction of linear temporal logic specifications through recurrence tools for hybrid systems. IEEE Trans. Autom. Control (2020).  A. Bisoffi and D. V. Dimarogonas. 2020. Satisfaction of linear temporal logic specifications through recurrence tools for hybrid systems. IEEE Trans. Autom. Control (2020)."},{"volume-title":"Proc. Amer. Control Conf. 3547--3552","author":"Chowdhary G.","key":"e_1_3_2_1_9_1","unstructured":"G. Chowdhary and E. Johnson . 2011. A singular value maximizing data recording algorithm for concurrent learning . In Proc. Amer. Control Conf. 3547--3552 . G. Chowdhary and E. Johnson. 2011. A singular value maximizing data recording algorithm for concurrent learning. In Proc. Amer. Control Conf. 3547--3552."},{"volume-title":"Proc. Conf. Decis. Control. 2062--2067","author":"Cohen M. H.","key":"e_1_3_2_1_10_1","unstructured":"M. H. Cohen and C. Belta . 2020. Approximate Optimal Control for Safety-Critical Systems with Control Barrier Functions . In Proc. Conf. Decis. Control. 2062--2067 . M. H. Cohen and C. Belta. 2020. Approximate Optimal Control for Safety-Critical Systems with Control Barrier Functions. In Proc. Conf. Decis. Control. 2062--2067."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"P. Deptula Z. I. Bell E. A. Doucette J. W. Curtis and W. E. Dixon. 2020. Data-based reinforcement learning approximate optimal control for an uncertain nonlinear system with control effectiveness faults. Automatica 116 (2020).  P. Deptula Z. I. Bell E. A. Doucette J. W. Curtis and W. E. Dixon. 2020. Data-based reinforcement learning approximate optimal control for an uncertain nonlinear system with control effectiveness faults. Automatica 116 (2020).","DOI":"10.1016\/j.automatica.2020.108922"},{"volume-title":"Proc. Conf. Decis. Control. 7136--7141","author":"Deptula P.","key":"e_1_3_2_1_12_1","unstructured":"P. Deptula , Z. I. Bell , F. M. Zegers , R. A. Licitra , and W. E. Dixon . 2018. Single agent indirect herding via approximate dynamic programming . In Proc. Conf. Decis. Control. 7136--7141 . P. Deptula, Z. I. Bell, F. M. Zegers, R. A. Licitra, and W. E. Dixon. 2018. Single agent indirect herding via approximate dynamic programming. In Proc. Conf. Decis. Control. 7136--7141."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2955321"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2808102"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2013.11.030"},{"key":"e_1_3_2_1_16_1","volume-title":"Birkhauser: Boston.","author":"Dixon W. E.","year":"2003","unstructured":"W. E. Dixon , A. Behal , D. M. Dawson , and S. Nagarkatti . 2003 . Nonlinear Control of Engineering Systems: A Lyapunov-Based Approach . Birkhauser: Boston. W. E. Dixon, A. Behal, D. M. Dawson, and S. Nagarkatti. 2003. Nonlinear Control of Engineering Systems: A Lyapunov-Based Approach. Birkhauser: Boston."},{"volume-title":"Proceedings of the 20th International Conference on Hybrid Systems: Computation and Control. 227--235","author":"Fu J.","key":"e_1_3_2_1_17_1","unstructured":"J. Fu , I. Papusha , and U. Topcu . 2017. Sampling-based Approximate Optimal Control Under Temporal Logic Constraints . In Proceedings of the 20th International Conference on Hybrid Systems: Computation and Control. 227--235 . J. Fu, I. Papusha, and U. Topcu. 2017. Sampling-based Approximate Optimal Control Under Temporal Logic Constraints. In Proceedings of the 20th International Conference on Hybrid Systems: Computation and Control. 227--235."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"R. Goebel R. G. Sanfelice and A. R. Teel. 2012. Hybrid dynamical systems: modeling stability robustness. Princeton University Press.  R. Goebel R. G. Sanfelice and A. R. Teel. 2012. Hybrid dynamical systems: modeling stability robustness. Princeton University Press.","DOI":"10.23943\/princeton\/9780691153896.001.0001"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2511658"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.08.004"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2015.10.039"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"R. Kamalapurkar P. Walters J. A. Rosenfeld and W. E. Dixon. 2018. Reinforcement Learning for Optimal Feedback Control: A Lyapunov-Based Approach. Springer.  R. Kamalapurkar P. Walters J. A. Rosenfeld and W. E. Dixon. 2018. Reinforcement Learning for Optimal Feedback Control: A Lyapunov-Based Approach. Springer.","DOI":"10.1007\/978-3-319-78384-0"},{"key":"e_1_3_2_1_23_1","volume-title":"Nonlinear Systems","author":"Khalil H. K.","unstructured":"H. K. Khalil . 2002. Nonlinear Systems , 3 rd edition. Prentice Hall . H. K. Khalil. 2002. Nonlinear Systems, 3rd edition. Prentice Hall.","edition":"3"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2773458"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2007.914952"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011254632723"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"T. Latvala. 2003. Efficient model checking of safety properties. In Model Checking Software. 74--88.  T. Latvala. 2003. Efficient model checking of safety properties. In Model Checking Software. 74--88.","DOI":"10.1007\/3-540-44829-2_5"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1934-6093.1999.tb00021.x"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2012.2214134"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2018.2853182"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(98)00193-9"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"O. Maler and D. Nickovic. 2004. Monitoring temporal properties of continuous signals. Formal Techniques Modelling and Analysis of Timed and Fault-Tolerant Systems (2004) 152--166.  O. Maler and D. Nickovic. 2004. Monitoring temporal properties of continuous signals. Formal Techniques Modelling and Analysis of Timed and Fault-Tolerant Systems (2004) 152--166.","DOI":"10.1007\/978-3-540-30206-3_12"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2005.851439"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2015.2444131"},{"volume-title":"Proc. Conf. Decis. Control. 434--440","author":"Papusha I.","key":"e_1_3_2_1_35_1","unstructured":"I. Papusha , J. Fu , U. Topcu , and R. M. Murray . 2016. Automata Theory Meets Approximate Dynamic Programming: Optimal Control with Temporal Logic Constraints . In Proc. Conf. Decis. Control. 434--440 . I. Papusha, J. Fu, U. Topcu, and R. M. Murray. 2016. Automata Theory Meets Approximate Dynamic Programming: Optimal Control with Temporal Logic Constraints. In Proc. Conf. Decis. Control. 434--440."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1002\/acs.2945"},{"volume-title":"Proceedings of the 18th International Conference on Hybrid Systems: Computation and Control. 239--248","author":"Raman V.","key":"e_1_3_2_1_37_1","unstructured":"V. Raman , A. Donze , D. Sadigh , R. M. Murray , and S. A. Seshia . 2015. Reactive synthesis from signal temporal logic specifications . In Proceedings of the 18th International Conference on Hybrid Systems: Computation and Control. 239--248 . V. Raman, A. Donze, D. Sadigh, R. M. Murray, and S. A. Seshia. 2015. Reactive synthesis from signal temporal logic specifications. In Proceedings of the 18th International Conference on Hybrid Systems: Computation and Control. 239--248."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2870040"},{"volume-title":"Proc. Conf. Decis. Control. 1091--1096","author":"Sadigh D.","key":"e_1_3_2_1_39_1","unstructured":"D. Sadigh , E. S. Kim , S. Coogan , S. S. Sastry , and S. A. Seshia . 2014. A learning based approach to control synthesis of markov decision processes for linear temporal logic specifications . In Proc. Conf. Decis. Control. 1091--1096 . D. Sadigh, E. S. Kim, S. Coogan, S. S. Sastry, and S. A. Seshia. 2014. A learning based approach to control synthesis of markov decision processes for linear temporal logic specifications. In Proc. Conf. Decis. Control. 1091--1096."},{"volume-title":"Proceedings of the 53rd Annual Allerton Conference on Communication, Control, and Computing. 772--779","author":"Sadraddini S.","key":"e_1_3_2_1_40_1","unstructured":"S. Sadraddini and C. Belta . 2015. Robust temporal logic model predictive control . In Proceedings of the 53rd Annual Allerton Conference on Communication, Control, and Computing. 772--779 . S. Sadraddini and C. Belta. 2015. Robust temporal logic model predictive control. In Proceedings of the 53rd Annual Allerton Conference on Communication, Control, and Computing. 772--779."},{"volume-title":"Proc. Conf. Decis. Control. 1782--1787","author":"Sadraddini S.","key":"e_1_3_2_1_41_1","unstructured":"S. Sadraddini and C. Belta . 2017. Formal methods for adaptive control of dynamical systems . In Proc. Conf. Decis. Control. 1782--1787 . S. Sadraddini and C. Belta. 2017. Formal methods for adaptive control of dynamical systems. In Proc. Conf. Decis. Control. 1782--1787."},{"volume-title":"Proceedings of the 21st International Conference on Hybrid Systems: Computation and Control. 147--156","author":"Sadraddini S.","key":"e_1_3_2_1_42_1","unstructured":"S. Sadraddini and C. Belta . 2018. Formal Guarantees in Data-Driven Model Identification and Control Synthesis . In Proceedings of the 21st International Conference on Hybrid Systems: Computation and Control. 147--156 . S. Sadraddini and C. Belta. 2018. Formal Guarantees in Data-Driven Model Identification and Control Synthesis. In Proceedings of the 21st International Conference on Hybrid Systems: Computation and Control. 147--156."},{"volume-title":"Proc. IEEE\/RSJ Int. Conf. Intel. Robot. Syst. 4862--4868","author":"Serlin Z.","key":"e_1_3_2_1_43_1","unstructured":"Z. Serlin , K. Leahy , R. Tron , and C. Belta . 2018. Distributed sensing subject to temporal logic constraints . In Proc. IEEE\/RSJ Int. Conf. Intel. Robot. Syst. 4862--4868 . Z. Serlin, K. Leahy, R. Tron, and C. Belta. 2018. Distributed sensing subject to temporal logic constraints. In Proc. IEEE\/RSJ Int. Conf. Intel. Robot. Syst. 4862--4868."},{"volume-title":"Proc. Conf. Decis. Control. 1991--1996","author":"Srinivasan M.","key":"e_1_3_2_1_44_1","unstructured":"M. Srinivasan , S. Coogan , and M. Egerstedt . 2018. Control of multi-agent systems with finite time control barrier certificates and temporal logic . In Proc. Conf. Decis. Control. 1991--1996 . M. Srinivasan, S. Coogan, and M. Egerstedt. 2018. Control of multi-agent systems with finite time control barrier certificates and temporal logic. In Proc. Conf. Decis. Control. 1991--1996."},{"volume-title":"Proc. Amer. Control Conf. 4786--4791","author":"Sun C.","key":"e_1_3_2_1_45_1","unstructured":"C. Sun and K. G. Vamvoudakis . 2020. Continuous-time safe learning with temporal logic constraints in adversarial environments . In Proc. Amer. Control Conf. 4786--4791 . C. Sun and K. G. Vamvoudakis. 2020. Continuous-time safe learning with temporal logic constraints in adversarial environments. In Proc. Amer. Control Conf. 4786--4791."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"P. Tabuada. 2009. Verification and control of hybrid systems: a symbolic approach. Spring Science & Business Media.  P. Tabuada. 2009. Verification and control of hybrid systems: a symbolic approach. Spring Science & Business Media.","DOI":"10.1007\/978-1-4419-0224-5"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2006.886494"},{"key":"e_1_3_2_1_48_1","volume-title":"Learning for Safety-Critical Control with Control Barrier Functions. In Proc. Conf. Learn. Dyn. Contr. (PLMR","volume":"717","author":"Taylor A.","unstructured":"A. Taylor , A. Singletary , Y. Yue , and A. Ames . 2020 . Learning for Safety-Critical Control with Control Barrier Functions. In Proc. Conf. Learn. Dyn. Contr. (PLMR , Vol. 120). 708-- 717 . A. Taylor, A. Singletary, Y. Yue, and A. Ames. 2020. Learning for Safety-Critical Control with Control Barrier Functions. In Proc. Conf. Learn. Dyn. Contr. (PLMR, Vol. 120). 708--717."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2487972"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2004.03.002"}],"event":{"name":"HSCC '21: 24th ACM International Conference on Hybrid Systems: Computation and Control","sponsor":["SIGBED ACM Special Interest Group on Embedded Systems"],"location":"Nashville Tennessee","acronym":"HSCC '21"},"container-title":["Proceedings of the 24th International Conference on Hybrid Systems: Computation and Control"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3447928.3456639","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3447928.3456639","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3447928.3456639","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3447928.3456639","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:28:23Z","timestamp":1750195703000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3447928.3456639"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,19]]},"references-count":49,"alternative-id":["10.1145\/3447928.3456639","10.1145\/3447928"],"URL":"https:\/\/doi.org\/10.1145\/3447928.3456639","relation":{},"subject":[],"published":{"date-parts":[[2021,5,19]]},"assertion":[{"value":"2021-05-19","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}