{"project":[{"grant_number":"101020093","call_identifier":"H2020","_id":"62781420-2b32-11ec-9570-8d9b63373d4d","name":"Vigilant Algorithmic Monitoring of Software"},{"grant_number":"863818","_id":"0599E47C-7A3F-11EA-A408-12923DDC885E","name":"Formal Methods for Stochastic Models: Algorithms and Applications","call_identifier":"H2020"},{"call_identifier":"H2020","name":"International IST Doctoral Program","_id":"2564DBCA-B435-11E9-9278-68D0E5697425","grant_number":"665385"}],"main_file_link":[{"url":"https://arxiv.org/abs/2112.09495","open_access":"1"}],"publication_identifier":{"isbn":["9781577358350"],"eissn":["2374-3468"],"issn":["2159-5399"]},"language":[{"iso":"eng"}],"oa":1,"related_material":{"record":[{"relation":"dissertation_contains","status":"public","id":"14539"}]},"keyword":["General Medicine"],"_id":"12511","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","external_id":{"arxiv":["2112.09495"]},"quality_controlled":"1","doi":"10.1609/aaai.v36i7.20695","publication":"Proceedings of the AAAI Conference on Artificial Intelligence","article_type":"original","issue":"7","title":"Stability verification in stochastic control systems via neural network supermartingales","ec_funded":1,"author":[{"first_name":"Mathias","full_name":"Lechner, Mathias","id":"3DC22916-F248-11E8-B48F-1D18A9856A87","last_name":"Lechner"},{"first_name":"Dorde","last_name":"Zikelic","orcid":"0000-0002-4681-1699","full_name":"Zikelic, Dorde","id":"294AA7A6-F248-11E8-B48F-1D18A9856A87"},{"last_name":"Chatterjee","id":"2E5DCA20-F248-11E8-B48F-1D18A9856A87","full_name":"Chatterjee, Krishnendu","orcid":"0000-0002-4561-241X","first_name":"Krishnendu"},{"first_name":"Thomas A","orcid":"0000-0002-2985-7724","full_name":"Henzinger, Thomas A","id":"40876CD8-F248-11E8-B48F-1D18A9856A87","last_name":"Henzinger"}],"article_processing_charge":"No","status":"public","department":[{"_id":"ToHe"},{"_id":"KrCh"}],"date_created":"2023-02-05T17:29:50Z","type":"journal_article","citation":{"short":"M. Lechner, D. Zikelic, K. Chatterjee, T.A. Henzinger, Proceedings of the AAAI Conference on Artificial Intelligence 36 (2022) 7326–7336.","apa":"Lechner, M., Zikelic, D., Chatterjee, K., &#38; Henzinger, T. A. (2022). Stability verification in stochastic control systems via neural network supermartingales. <i>Proceedings of the AAAI Conference on Artificial Intelligence</i>. Association for the Advancement of Artificial Intelligence. <a href=\"https://doi.org/10.1609/aaai.v36i7.20695\">https://doi.org/10.1609/aaai.v36i7.20695</a>","ista":"Lechner M, Zikelic D, Chatterjee K, Henzinger TA. 2022. Stability verification in stochastic control systems via neural network supermartingales. Proceedings of the AAAI Conference on Artificial Intelligence. 36(7), 7326–7336.","chicago":"Lechner, Mathias, Dorde Zikelic, Krishnendu Chatterjee, and Thomas A Henzinger. “Stability Verification in Stochastic Control Systems via Neural Network Supermartingales.” <i>Proceedings of the AAAI Conference on Artificial Intelligence</i>. Association for the Advancement of Artificial Intelligence, 2022. <a href=\"https://doi.org/10.1609/aaai.v36i7.20695\">https://doi.org/10.1609/aaai.v36i7.20695</a>.","mla":"Lechner, Mathias, et al. “Stability Verification in Stochastic Control Systems via Neural Network Supermartingales.” <i>Proceedings of the AAAI Conference on Artificial Intelligence</i>, vol. 36, no. 7, Association for the Advancement of Artificial Intelligence, 2022, pp. 7326–36, doi:<a href=\"https://doi.org/10.1609/aaai.v36i7.20695\">10.1609/aaai.v36i7.20695</a>.","ieee":"M. Lechner, D. Zikelic, K. Chatterjee, and T. A. Henzinger, “Stability verification in stochastic control systems via neural network supermartingales,” <i>Proceedings of the AAAI Conference on Artificial Intelligence</i>, vol. 36, no. 7. Association for the Advancement of Artificial Intelligence, pp. 7326–7336, 2022.","ama":"Lechner M, Zikelic D, Chatterjee K, Henzinger TA. Stability verification in stochastic control systems via neural network supermartingales. <i>Proceedings of the AAAI Conference on Artificial Intelligence</i>. 2022;36(7):7326-7336. doi:<a href=\"https://doi.org/10.1609/aaai.v36i7.20695\">10.1609/aaai.v36i7.20695</a>"},"year":"2022","publisher":"Association for the Advancement of Artificial Intelligence","volume":36,"day":"28","oa_version":"Preprint","date_updated":"2023-11-30T10:55:37Z","acknowledgement":"This work was supported in part by the ERC-2020-AdG 101020093, ERC CoG 863818 (FoRM-SMArt) and the European Union’s Horizon 2020 research and innovation programme\r\nunder the Marie Skłodowska-Curie Grant Agreement No. 665385.","scopus_import":"1","intvolume":"        36","page":"7326-7336","abstract":[{"lang":"eng","text":"We consider the problem of formally verifying almost-sure (a.s.) asymptotic stability in discrete-time nonlinear stochastic control systems. While verifying stability in deterministic control systems is extensively studied in the literature, verifying stability in stochastic control systems is an open problem. The few existing works on this topic either consider only specialized forms of stochasticity or make restrictive assumptions on the system, rendering them inapplicable to learning algorithms with neural network policies. \r\n In this work, we present an approach for general nonlinear stochastic control problems with two novel aspects: (a) instead of classical stochastic extensions of Lyapunov functions, we use ranking supermartingales (RSMs) to certify a.s. asymptotic stability, and (b) we present a method for learning neural network RSMs. \r\n We prove that our approach guarantees a.s. asymptotic stability of the system and\r\n provides the first method to obtain bounds on the stabilization time, which stochastic Lyapunov functions do not.\r\n Finally, we validate our approach experimentally on a set of nonlinear stochastic reinforcement learning environments with neural network policies."}],"date_published":"2022-06-28T00:00:00Z","publication_status":"published","month":"06"}