{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T16:50:10Z","timestamp":1770742210915,"version":"3.49.0"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Research Council of Norway (RCN) Project \u201cSafe Reinforcement Learning Using MPC\u201d"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3228922","type":"journal-article","created":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T19:27:38Z","timestamp":1670873258000},"page":"130058-130067","source":"Crossref","is-referenced-by-count":14,"title":["Safe Reinforcement Learning Using Wasserstein Distributionally Robust MPC and Chance Constraint"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8931-5372","authenticated-orcid":false,"given":"Arash Bahari","family":"Kordabad","sequence":"first","affiliation":[{"name":"Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6719-8427","authenticated-orcid":false,"given":"Rafael","family":"Wisniewski","sequence":"additional","affiliation":[{"name":"Department of Electronical Systems, Aalborg University, Aalborg, Denmark"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6054-2133","authenticated-orcid":false,"given":"Sebastien","family":"Gros","sequence":"additional","affiliation":[{"name":"Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619440"},{"key":"ref38","first-page":"3331","article-title":"Finite-sample regret bound for distributionally robust offline tabular reinforcement learning","author":"zhou","year":"2021","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref33","first-page":"52","article-title":"On a space of totally additive functions","volume":"13","author":"kantorovich","year":"1958","journal-title":"Vestnik St Petersburg Univ Math"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611976595"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-4266(02)00271-6"},{"key":"ref30","first-page":"8092","article-title":"A Lyapunov-based approach to safe reinforcement learning","volume":"31","author":"chow","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","first-page":"1199","article-title":"Finite sample analysis of two-timescale stochastic approximation with applications to reinforcement learning","author":"dalal","year":"2018","journal-title":"Proc Conf Learn Theory"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s00440-014-0583-7"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7798822"},{"key":"ref34","article-title":"Distributionally robust stochastic optimization with Wasserstein distance","author":"gao","year":"2016","journal-title":"arXiv 1604 02199"},{"key":"ref10","first-page":"1695","article-title":"Kullback–Leibler divergence constrained distributionally robust optimization","author":"hu","year":"2013","journal-title":"Optim Online"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1080\/14697680701455410"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105343"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-017-1172-1"},{"key":"ref13","volume":"2","author":"rawlings","year":"2017","journal-title":"Model Predictive Control Theory Computation and Design"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3106827"},{"key":"ref15","article-title":"3U: Joint design of UAV-USV-UUV networks for cooperative target hunting","author":"wei","year":"2022","journal-title":"IEEE Trans Veh Technol"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ANZCC47194.2019.8945719"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2913768"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.23919\/ECC54610.2021.9654852"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CCTA48906.2021.9659202"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref4","first-page":"1","article-title":"Algorithms for CVaR optimization in MDPs","volume":"27","author":"chow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.5132"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21314\/JOR.2000.038"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3088279"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3049335"},{"key":"ref5","first-page":"1522","article-title":"Risk-sensitive and robust decision-making: A CVaR optimization approach","volume":"28","author":"chow","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1090.0741"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1137\/S1052623499363220"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/aic.690450811"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793611"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-005-0678-0"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.3012025"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110602"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9303988"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341415"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-8155-7_369"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.2200\/S00268ED1V01Y201005AIM009"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3097706"},{"key":"ref41","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3024161"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.23919\/ECC54610.2021.9654962"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1002\/aic.16546"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9483016"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09982609.pdf?arnumber=9982609","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,23]],"date-time":"2023-01-23T20:02:44Z","timestamp":1674504164000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9982609\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3228922","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}