{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T18:49:05Z","timestamp":1770749345837,"version":"3.50.0"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032111753","type":"print"},{"value":"9783032111760","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T00:00:00Z","timestamp":1763856000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T00:00:00Z","timestamp":1763856000000},"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\/978-3-032-11176-0_28","type":"book-chapter","created":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T20:11:32Z","timestamp":1763842292000},"page":"468-478","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Safe Multi-agent Reinforcement Learning Using Formal Runtime Enforcement: A Case Study"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8840-2116","authenticated-orcid":false,"given":"Vedanta","family":"Mohapatra","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3754-630X","authenticated-orcid":false,"given":"Ayush","family":"Anand","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7779-8231","authenticated-orcid":false,"given":"Srinivas","family":"Pinisetty","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,23]]},"reference":[{"key":"28_CR1","doi-asserted-by":"crossref","unstructured":"Aceto, L., Ing\u00f3lfsd\u00f3ttir, A., Larsen, K.G., Srba, J.: Reactive Systems: Modelling. Specification and Verification. Cambridge University Press, Cambridge (2007)","DOI":"10.1017\/CBO9780511814105"},{"key":"28_CR2","doi-asserted-by":"publisher","unstructured":"Alshiekh, M., Bloem, R., Ehlers, R., K\u00f6nighofer, B., Niekum, S., Topcu, U.: Safe reinforcement learning via shielding. In: Proceedings of the Thirty-Second AAAI 2018, New Orleans, Louisiana, USA, February 2\u20137, 2018, pp. 2669\u20132678 (2018). https:\/\/doi.org\/10.1609\/AAAI.V32I1.11797","DOI":"10.1609\/AAAI.V32I1.11797"},{"key":"28_CR3","unstructured":"Amir, G., Schapira, M., Katz, G.: Towards scalable verification of deep reinforcement learning. In: 2021 Formal Methods in Computer Aided Design (FMCAD) (2021)"},{"key":"28_CR4","doi-asserted-by":"publisher","unstructured":"Busoniu, L., Babuska, R., De\u00a0Schutter, B.: A comprehensive survey of multiagent reinforcement learning. IEEE Trans. Syst. Man Cybern. Part C (Appl. Rev.) 38(2), 156\u2013172 (2008). https:\/\/doi.org\/10.1109\/TSMCC.2007.913919","DOI":"10.1109\/TSMCC.2007.913919"},{"issue":"03","key":"28_CR5","doi-asserted-by":"publisher","first-page":"1750012","DOI":"10.1142\/S2424862217500129","volume":"02","author":"H Chen","year":"2017","unstructured":"Chen, H.: Applications of cyber-physical system: a literature review. J. Ind. Integr. Manage. 02(03), 1750012 (2017). https:\/\/doi.org\/10.1142\/S2424862217500129","journal-title":"J. Ind. Integr. Manage."},{"key":"28_CR6","unstructured":"Falcone, Y., Havelund, K., Reger, G.: A tutorial on runtime verification. Eng. Dependable Softw. Syst. 141\u2013175 (2013)"},{"issue":"3","key":"28_CR7","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1007\/s10703-011-0114-4","volume":"38","author":"Y Falcone","year":"2011","unstructured":"Falcone, Y., Mounier, L., Fernandez, J.C., Richier, J.L.: Runtime enforcement monitors: composition, synthesis, and enforcement abilities. Formal Methods Syst. Design 38(3), 223\u2013262 (2011)","journal-title":"Formal Methods Syst. Design"},{"key":"28_CR8","doi-asserted-by":"publisher","unstructured":"Falc\u00e3o, R.L., de\u00a0Oliveira, J.C.C., Andrade, P.H.B.A., Rodrigues, R.R., Barth, F.J., Brancalion, J.F.B.: DSSE: an environment for simulation of reinforcement learning-empowered drone swarm maritime search and rescue missions. J. Open Source Softw. 9(99), 6746 (2024). https:\/\/doi.org\/10.21105\/joss.06746","DOI":"10.21105\/joss.06746"},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Harel, D., Pnueli, A.: On the development of reactive systems. In: Logics and Models of Concurrent Systems, pp. 477\u2013498. Springer (1984)","DOI":"10.1007\/978-3-642-82453-1_17"},{"key":"28_CR10","doi-asserted-by":"crossref","unstructured":"Herdel, V., Yamin, L.J., Cauchard, J.R.: Above and beyond: a scoping review of domains and applications for human-drone interaction. In: Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems, pp. 1\u201322 (2022)","DOI":"10.1145\/3491102.3501881"},{"key":"28_CR11","doi-asserted-by":"publisher","unstructured":"Jansen, N., K\u00f6nighofer, B., Junges, S., Serban, A., Bloem, R.: Safe reinforcement learning using probabilistic shields (invited paper). In: 31st International Conference on Concurrency Theory, CONCUR 2020, September 1\u20134, 2020, Vienna, Austria (Virtual Conference), pp. 3:1\u20133:16 (2020). https:\/\/doi.org\/10.4230\/LIPICS.CONCUR.2020.3","DOI":"10.4230\/LIPICS.CONCUR.2020.3"},{"key":"28_CR12","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"LP Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: a survey. J. Artif. Intell. Res. 4, 237\u2013285 (1996)","journal-title":"J. Artif. Intell. Res."},{"issue":"14s","key":"28_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3596444","volume":"55","author":"M Landers","year":"2023","unstructured":"Landers, M., Doryab, A.: Deep reinforcement learning verification: a survey. ACM Comput. Surv. 55(14s), 1\u201331 (2023)","journal-title":"ACM Comput. Surv."},{"key":"28_CR14","doi-asserted-by":"publisher","unstructured":"Lee, E.A.: Cyber physical systems: design challenges. In: 2008 11th IEEE International Symposium on Object and Component-Oriented Real-Time Distributed Computing (ISORC), pp. 363\u2013369 (2008).https:\/\/doi.org\/10.1109\/ISORC.2008.25","DOI":"10.1109\/ISORC.2008.25"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Ligatti, J., Bauer, L., Walker, D.: Run-time enforcement of nonsafety policies. ACM Trans. Inf. Syst. Secur. 12(3) (2009)","DOI":"10.1145\/1455526.1455532"},{"key":"28_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/978-3-642-15497-3_6","volume-title":"Computer Security \u2013 ESORICS 2010","author":"J Ligatti","year":"2010","unstructured":"Ligatti, J., Reddy, S.: A theory of runtime enforcement, with results. In: Gritzalis, D., Preneel, B., Theoharidou, M. (eds.) ESORICS 2010. LNCS, vol. 6345, pp. 87\u2013100. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15497-3_6"},{"key":"28_CR17","doi-asserted-by":"publisher","unstructured":"Panda, A., Baird, A., Pinisetty, S., Roop, P.S.: Incremental security enforcement for cyber-physical systems. IEEE Access 11, 18475\u201318498 (2023). https:\/\/doi.org\/10.1109\/ACCESS.2023.3246121","DOI":"10.1109\/ACCESS.2023.3246121"},{"issue":"7","key":"28_CR18","doi-asserted-by":"publisher","first-page":"4659","DOI":"10.1109\/TII.2019.2945520","volume":"16","author":"HA Pearce","year":"2020","unstructured":"Pearce, H.A., Pinisetty, S., Roop, P.S., Kuo, M.M.Y., Ukil, A.: Smart I\/O modules for mitigating cyber-physical attacks on industrial control systems. IEEE Trans. Ind. Informatics 16(7), 4659\u20134669 (2020). https:\/\/doi.org\/10.1109\/TII.2019.2945520","journal-title":"IEEE Trans. Ind. Informatics"},{"issue":"3","key":"28_CR19","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1007\/s10703-014-0215-y","volume":"45","author":"S Pinisetty","year":"2014","unstructured":"Pinisetty, S., Falcone, Y., J\u00e9ron, T., Marchand, H., Rollet, A., Nguena Timo, O.: Runtime enforcement of timed properties revisited. Formal Methods Syst. Design 45(3), 381\u2013422 (2014). https:\/\/doi.org\/10.1007\/s10703-014-0215-y","journal-title":"Formal Methods Syst. Design"},{"key":"28_CR20","doi-asserted-by":"publisher","unstructured":"Pinisetty, S., Roop, P.S., Smyth, S., Allen, N., Tripakis, S., von Hanxleden, R.: Runtime enforcement of cyber-physical systems. ACM Trans. Embed. Comput. Syst. 16(5s), 178:1\u2013178:25 (2017). https:\/\/doi.org\/10.1145\/3126500","DOI":"10.1145\/3126500"},{"key":"28_CR21","doi-asserted-by":"publisher","unstructured":"Pinisetty, S., Roop, P.S., Smyth, S., Tripakis, S., von Hanxleden, R.: Runtime enforcement of reactive systems using synchronous enforcers. Proceedings of the 24th ACM SIGSOFT International SPIN Symposium on Model Checking of Software, Santa Barbara, CA, USA, July 10\u201314, 2017, pp. 80\u201389 (2017). https:\/\/doi.org\/10.1145\/3092282.3092291","DOI":"10.1145\/3092282.3092291"},{"key":"28_CR22","doi-asserted-by":"publisher","unstructured":"Pradhan, A., Akil, C.G.M., Pinisetty, S.: Runtime enforcement with event reordering. In: Anutariya, C., Bonsangue, M.M. (eds.) Theoretical Aspects of Computing - ICTAC 2024 - 21st International Colloquium, Bangkok, Thailand, November 25\u201329, 2024, Proceedings. Lecture Notes in Computer Science, vol. 15373, pp. 386\u2013407. Springer (2024). https:\/\/doi.org\/10.1007\/978-3-031-77019-7_22","DOI":"10.1007\/978-3-031-77019-7_22"},{"issue":"1","key":"28_CR23","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1145\/353323.353382","volume":"3","author":"FB Schneider","year":"2000","unstructured":"Schneider, F.B.: Enforceable security policies. ACM Trans. Inf. Syst. Secur. 3(1), 30\u201350 (2000). https:\/\/doi.org\/10.1145\/353323.353382","journal-title":"ACM Trans. Inf. Syst. Secur."},{"key":"28_CR24","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"28_CR25","first-page":"259","volume":"6","author":"S Sen","year":"1999","unstructured":"Sen, S., Weiss, G.: Learning in multiagent systems. Multiagent Syst. Mod. Approach Distrib. Artif. Intell. 6, 259\u2013298 (1999)","journal-title":"Multiagent Syst. Mod. Approach Distrib. Artif. Intell."},{"key":"28_CR26","unstructured":"Sutton, R.S., Barto, A.G., et\u00a0al.: Reinforcement Learning: An Introduction, vol.\u00a01. MIT Press, Cambridge (1998)"},{"issue":"10","key":"28_CR27","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1109\/JAS.2021.1004129","volume":"8","author":"J Tang","year":"2021","unstructured":"Tang, J., Liu, G., Pan, Q.: A review on representative swarm intelligence algorithms for solving optimization problems: applications and trends. IEEE\/CAA J. Automatica Sinica 8(10), 1627\u20131643 (2021)","journal-title":"IEEE\/CAA J. Automatica Sinica"},{"key":"28_CR28","doi-asserted-by":"publisher","unstructured":"Vuppala, S.R.H., Allen, N., Pinisetty, S., Roop, P.S.: A formal approach for safe reinforcement learning: a rate-adaptive pacemaker case study. In: Runtime Verification - 24th International Conference, RV 2024, Istanbul, Turkey, October 15\u201317, 2024, Proceedings, pp. 3\u201321 (2024). https:\/\/doi.org\/10.1007\/978-3-031-74234-7_1","DOI":"10.1007\/978-3-031-74234-7_1"},{"key":"28_CR29","unstructured":"Weiss, G.: Multiagent Systems: a Modern Approach to Distributed Artificial Intelligence. MIT Press, Cambridge (1999)"},{"key":"28_CR30","doi-asserted-by":"crossref","unstructured":"Zeng, Q., Nait-Abdesselam, F.: Multi-agent reinforcement learning-based extended boid modeling for drone swarms. In: ICC 2024-IEEE International Conference on Communications, pp. 1551\u20131556. IEEE (2024)","DOI":"10.1109\/ICC51166.2024.10622479"}],"container-title":["Lecture Notes in Computer Science","Theoretical Aspects of Computing \u2013 ICTAC 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-11176-0_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T11:09:56Z","timestamp":1770721796000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-11176-0_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,23]]},"ISBN":["9783032111753","9783032111760"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-11176-0_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,23]]},"assertion":[{"value":"23 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICTAC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Colloquium on Theoretical Aspects of Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Marrakesh","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Morocco","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":"24 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ictac2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ictac2025.digital-hub.sh\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}