{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T04:21:22Z","timestamp":1775881282901,"version":"3.50.1"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030557539","type":"print"},{"value":"9783030557546","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-55754-6_6","type":"book-chapter","created":{"date-parts":[[2020,8,9]],"date-time":"2020-08-09T23:02:37Z","timestamp":1597014157000},"page":"97-114","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":56,"title":["Neural Simplex Architecture"],"prefix":"10.1007","author":[{"given":"Dung T.","family":"Phan","sequence":"first","affiliation":[]},{"given":"Radu","family":"Grosu","sequence":"additional","affiliation":[]},{"given":"Nils","family":"Jansen","sequence":"additional","affiliation":[]},{"given":"Nicola","family":"Paoletti","sequence":"additional","affiliation":[]},{"given":"Scott A.","family":"Smolka","sequence":"additional","affiliation":[]},{"given":"Scott D.","family":"Stoller","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,8,10]]},"reference":[{"key":"6_CR1","unstructured":"Achiam, J., Held, D., Tamar, A., Abbeel, P.: Constrained policy optimization. In: International Conference on Machine Learning, pp. 22\u201331 (2017)"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Alshiekh, M., Bloem, R., Ehlers, R., K\u00f6nighofer, B., Niekum, S., Topcu, U.: Safe reinforcement learning via shielding. arXiv preprint arXiv:1708.08611 (2017)","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"6_CR3","unstructured":"Alshiekh, M., Bloem, R., Ehlers, R., K\u00f6nighofer, B., Niekum, S., Topcu, U.: Safe reinforcement learning via shielding. In: AAAI (2018). https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI18\/paper\/view\/17211"},{"key":"6_CR4","unstructured":"Berkenkamp, F., Turchetta, M., Schoellig, A., Krause, A.: Safe model-based reinforcement learning with stability guarantees. In: Advances in Neural Information Processing Systems, pp. 908\u2013918 (2017)"},{"key":"6_CR5","unstructured":"Bouton, M., Karlsson, J., Nakhaei, A., Fujimura, K., Kochenderfer, M.J., Tumova, J.: Reinforcement learning with probabilistic guarantees for autonomous driving. CoRR abs\/1904.07189 (2019)"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Chen, H., Paoletti, N., Smolka, S.A., Lin, S.: Committed moving horizon estimation for meal detection and estimation in type 1 diabetes. In: American Control Conference (ACC 2019), pp. 4765\u20134772 (2019)","DOI":"10.23919\/ACC.2019.8814868"},{"key":"6_CR7","doi-asserted-by":"crossref","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. AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"6_CR8","unstructured":"Chow, Y., Nachum, O., Duenez-Guzman, E., Ghavamzadeh, M.: A Lyapunov-based approach to safe reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 8103\u20138112 (2018)"},{"key":"6_CR9","unstructured":"Dalal, G., Dvijotham, K., Vecerik, M., Hester, T., Paduraru, C., Tassa, Y.: Safe exploration in continuous action spaces. arXiv e-prints (2018)"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Desai, A., Ghosh, S., Seshia, S.A., Shankar, N., Tiwari, A.: A runtime assurance framework for programming safe robotics systems. In: IEEE\/IFIP International Conference on Dependable Systems and Networks (DSN) (2019)","DOI":"10.1109\/DSN.2019.00027"},{"key":"6_CR11","unstructured":"Duan, Y., Chen, X., Houthooft, R., Schulman, J., Abbeel, P.: Benchmarking deep reinforcement learning for continuous control. In: Proceedings of the 33rd International Conference on Machine Learning ICML 2016, vol. 48, pp. 1329\u20131338 (2016). http:\/\/dl.acm.org\/citation.cfm?id=3045390.3045531"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Fu, J., Topcu, U.: Probably approximately correct MDP learning and control with temporal logic constraints. In: 2014 Robotics: Science and Systems Conference (2014)","DOI":"10.15607\/RSS.2014.X.039"},{"key":"6_CR13","unstructured":"Fulton, N., Platzer, A.: Safe reinforcement learning via formal methods. In: AAAI 2018 (2018)"},{"key":"6_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1007\/978-3-030-17462-0_28","volume-title":"Tools and Algorithms for the Construction and Analysis of Systems","author":"N Fulton","year":"2019","unstructured":"Fulton, N., Platzer, A.: Verifiably safe off-model reinforcement learning. In: Vojnar, T., Zhang, L. (eds.) TACAS 2019. LNCS, vol. 11427, pp. 413\u2013430. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-17462-0_28"},{"key":"6_CR15","unstructured":"Garc\u00eda, J., Fern\u00e1ndez, F.: A comprehensive survey on safe reinforcement learning. J. Mach. Learn. Res. 16(1), 1437\u20131480 (2015). http:\/\/dl.acm.org\/citation.cfm?id=2789272.2886795"},{"issue":"3","key":"6_CR16","first-page":"14","volume":"13","author":"J Garc\u00eda","year":"2019","unstructured":"Garc\u00eda, J., Fern\u00e1ndez, F.: Probabilistic policy reuse for safe reinforcement learning. ACM Trans. Auton. Adapt. Syst. (TAAS) 13(3), 14 (2019)","journal-title":"ACM Trans. Auton. Adapt. Syst. (TAAS)"},{"key":"6_CR17","unstructured":"Hasanbeig, M., Abate, A., Kroening, D.: Logically-correct reinforcement learning. CoRR abs\/1801.08099 (2018)"},{"key":"6_CR18","doi-asserted-by":"publisher","unstructured":"Johnson, T., Bak, S., Caccamo, M., Sha, L.: Real-time reachability for verified Simplex design. ACM Trans. Embed. Comput. Syst. 15(2), 26:1\u201326:27 (2016). https:\/\/doi.org\/10.1145\/2723871, http:\/\/doi.acm.org\/10.1145\/2723871","DOI":"10.1145\/2723871"},{"key":"6_CR19","unstructured":"Lillicrap, T., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Mason, G., Calinescu, R., Kudenko, D., Banks, A.: Assured reinforcement learning with formally verified abstract policies. In: ICAART, no. 2, pp. 105\u2013117. SciTePress (2017)","DOI":"10.5220\/0006156001050117"},{"key":"6_CR21","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: ICML, pp. 1928\u20131937 (2016)"},{"key":"6_CR22","unstructured":"Moldovan, T.M., Abbeel, P.: Safe exploration in Markov decision processes. In: ICML. icml.cc\/Omnipress (2012)"},{"key":"6_CR23","doi-asserted-by":"publisher","unstructured":"Ohnishi, M., Wang, L., Notomista, G., Egerstedt, M.: Barrier-certified adaptive reinforcement learning with applications to Brushbot navigation. IEEE Trans. Robot. 1\u201320 (2019). https:\/\/doi.org\/10.1109\/TRO.2019.2920206","DOI":"10.1109\/TRO.2019.2920206"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Phan, D., Paoletti, N., Grosu, R., Jansen, N., Smolka, S.A., Stoller, S.D.: Neural simplex architecture. arXiv preprint arXiv:1908.00528 (2019)","DOI":"10.1007\/978-3-030-55754-6_6"},{"key":"6_CR25","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: ICML, pp. 1889\u20131897 (2015)"},{"key":"6_CR26","doi-asserted-by":"publisher","unstructured":"Seto, D., Krogh, B., Sha, L., Chutinan, A.: The Simplex architecture for safe online control system upgrades. In: Proceedings of 1998 American Control Conference, vol. 6, pp. 3504\u20133508 (1998). https:\/\/doi.org\/10.1109\/ACC.1998.703255","DOI":"10.1109\/ACC.1998.703255"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Seto, D., Sha, L., Compton, N.: A case study on analytical analysis of the inverted pendulum real-time control system (1999)","DOI":"10.21236\/ADA373286"},{"issue":"4","key":"6_CR28","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1109\/MS.2001.936213","volume":"18","author":"L Sha","year":"2001","unstructured":"Sha, L.: Using simplicity to control complexity. IEEE Softw. 18(4), 20\u201328 (2001). https:\/\/doi.org\/10.1109\/MS.2001.936213","journal-title":"IEEE Softw."},{"key":"6_CR29","unstructured":"Silver, D., Hubert, T., Schrittwieser, J., et al.: Mastering chess and shogi by self-play with a general reinforcement learning algorithm. arXiv preprint arXiv:1712.01815 (2017)"},{"issue":"7676","key":"6_CR30","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., Schrittwieser, J., Simonyan, K., et al.: Mastering the game of Go without human knowledge. Nature 550(7676), 354 (2017)","journal-title":"Nature"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Sim\u00e3o, T.D., Spaan, M.T.J.: Safe policy improvement with baseline bootstrapping in factored environments. In: AAAI, pp. 4967\u20134974. AAAI Press (2019)","DOI":"10.1609\/aaai.v33i01.33014967"},{"key":"6_CR32","volume-title":"Reinforcement Learning: An Introduction","author":"R Sutton","year":"1998","unstructured":"Sutton, R., Barto, A.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"key":"6_CR33","unstructured":"Tessler, C., Mankowitz, D.J., Mannor, S.: Reward constrained policy optimization. arXiv e-prints (2018)"},{"key":"6_CR34","doi-asserted-by":"publisher","unstructured":"Vivekanandan, P., Garcia, G., Yun, H., Keshmiri, S.: A Simplex architecture for intelligent and safe unmanned aerial vehicles. In: 2016 IEEE 22nd International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA), pp. 69\u201375 (2016). https:\/\/doi.org\/10.1109\/RTCSA.2016.17","DOI":"10.1109\/RTCSA.2016.17"},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"Wang, X., Hovakimyan, N., Sha, L.: L1Simplex: fault-tolerant control of cyber-physical systems. In: 2013 ACM\/IEEE International Conference on Cyber-Physical Systems (ICCPS), pp. 41\u201350 (2013)","DOI":"10.1145\/2502524.2502531"},{"key":"6_CR36","unstructured":"Wang, Z., et al.: Sample efficient actor-critic with experience replay. arXiv preprint arXiv:1611.01224 (2016)"},{"key":"6_CR37","doi-asserted-by":"crossref","unstructured":"Wen, M., Ehlers, R., Topcu, U.: Correct-by-synthesis reinforcement learning with temporal logic constraints. In: IROS, pp. 4983\u20134990. IEEE Computer Society Press (2015)","DOI":"10.1109\/IROS.2015.7354078"},{"key":"6_CR38","unstructured":"Xiang, W., et al.: Verification for machine learning, autonomy, and neural networks survey. arXiv e-prints (2018)"}],"container-title":["Lecture Notes in Computer Science","NASA Formal Methods"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-55754-6_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,6]],"date-time":"2022-11-06T09:30:32Z","timestamp":1667727032000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-55754-6_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030557539","9783030557546"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-55754-6_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"10 August 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NFM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"NASA Formal Methods Symposium","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Moffett Field, CA","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":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 May 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 May 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nfm2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ti.arc.nasa.gov\/events\/nfm-2020\/","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":"62","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":"20","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":"5","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":"32% - 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":"3.2","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":"4.5","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)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}