{"type":"preprint","date_updated":"2023-11-30T10:55:37Z","user_id":"8b945eb4-e2f2-11eb-945a-df72226e66a9","project":[{"name":"Vigilant Algorithmic Monitoring of Software","_id":"62781420-2b32-11ec-9570-8d9b63373d4d","call_identifier":"H2020","grant_number":"101020093"},{"_id":"0599E47C-7A3F-11EA-A408-12923DDC885E","name":"Formal Methods for Stochastic Models: Algorithms and Applications","call_identifier":"H2020","grant_number":"863818"},{"name":"International IST Doctoral Program","_id":"2564DBCA-B435-11E9-9278-68D0E5697425","call_identifier":"H2020","grant_number":"665385"}],"department":[{"_id":"KrCh"},{"_id":"ToHe"}],"doi":"10.48550/arXiv.2205.11991","oa_version":"Preprint","ec_funded":1,"title":"Learning stabilizing policies in stochastic control systems","citation":{"ista":"Zikelic D, Lechner M, Chatterjee K, Henzinger TA. Learning stabilizing policies in stochastic control systems. arXiv, <a href=\"https://doi.org/10.48550/arXiv.2205.11991\">10.48550/arXiv.2205.11991</a>.","mla":"Zikelic, Dorde, et al. “Learning Stabilizing Policies in Stochastic Control Systems.” <i>ArXiv</i>, doi:<a href=\"https://doi.org/10.48550/arXiv.2205.11991\">10.48550/arXiv.2205.11991</a>.","apa":"Zikelic, D., Lechner, M., Chatterjee, K., &#38; Henzinger, T. A. (n.d.). Learning stabilizing policies in stochastic control systems. <i>arXiv</i>. <a href=\"https://doi.org/10.48550/arXiv.2205.11991\">https://doi.org/10.48550/arXiv.2205.11991</a>","chicago":"Zikelic, Dorde, Mathias Lechner, Krishnendu Chatterjee, and Thomas A Henzinger. “Learning Stabilizing Policies in Stochastic Control Systems.” <i>ArXiv</i>, n.d. <a href=\"https://doi.org/10.48550/arXiv.2205.11991\">https://doi.org/10.48550/arXiv.2205.11991</a>.","ama":"Zikelic D, Lechner M, Chatterjee K, Henzinger TA. Learning stabilizing policies in stochastic control systems. <i>arXiv</i>. doi:<a href=\"https://doi.org/10.48550/arXiv.2205.11991\">10.48550/arXiv.2205.11991</a>","short":"D. Zikelic, M. Lechner, K. Chatterjee, T.A. Henzinger, ArXiv (n.d.).","ieee":"D. Zikelic, M. Lechner, K. Chatterjee, and T. A. Henzinger, “Learning stabilizing policies in stochastic control systems,” <i>arXiv</i>. ."},"related_material":{"record":[{"status":"public","relation":"dissertation_contains","id":"14539"}]},"article_processing_charge":"No","_id":"14601","status":"public","date_published":"2022-05-24T00:00:00Z","year":"2022","external_id":{"arxiv":["2205.11991"]},"abstract":[{"lang":"eng","text":"In this work, we address the problem of learning provably stable neural\r\nnetwork policies for stochastic control systems. While recent work has\r\ndemonstrated the feasibility of certifying given policies using martingale\r\ntheory, the problem of how to learn such policies is little explored. Here, we\r\nstudy the effectiveness of jointly learning a policy together with a martingale\r\ncertificate that proves its stability using a single learning algorithm. We\r\nobserve that the joint optimization problem becomes easily stuck in local\r\nminima when starting from a randomly initialized policy. Our results suggest\r\nthat some form of pre-training of the policy is required for the joint\r\noptimization to repair and verify the policy successfully."}],"oa":1,"publication_status":"submitted","date_created":"2023-11-24T13:22:30Z","month":"05","main_file_link":[{"url":"https://arxiv.org/abs/2205.11991","open_access":"1"}],"author":[{"id":"294AA7A6-F248-11E8-B48F-1D18A9856A87","full_name":"Zikelic, Dorde","orcid":"0000-0002-4681-1699","last_name":"Zikelic","first_name":"Dorde"},{"full_name":"Lechner, Mathias","id":"3DC22916-F248-11E8-B48F-1D18A9856A87","first_name":"Mathias","last_name":"Lechner"},{"full_name":"Chatterjee, Krishnendu","id":"2E5DCA20-F248-11E8-B48F-1D18A9856A87","first_name":"Krishnendu","last_name":"Chatterjee","orcid":"0000-0002-4561-241X"},{"full_name":"Henzinger, Thomas A","id":"40876CD8-F248-11E8-B48F-1D18A9856A87","first_name":"Thomas A","last_name":"Henzinger","orcid":"0000-0002-2985-7724"}],"language":[{"iso":"eng"}],"day":"24","publication":"arXiv"}