{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T08:24:15Z","timestamp":1774599855887,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,11]],"date-time":"2020-10-11T00:00:00Z","timestamp":1602374400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,11]],"date-time":"2020-10-11T00:00:00Z","timestamp":1602374400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,11]],"date-time":"2020-10-11T00:00:00Z","timestamp":1602374400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,10,11]]},"DOI":"10.1109\/smc42975.2020.9282929","type":"proceedings-article","created":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T21:44:48Z","timestamp":1607982288000},"page":"3543-3550","source":"Crossref","is-referenced-by-count":12,"title":["A Reinforcement Learning Approach to Design Verification Strategies of Engineered Systems"],"prefix":"10.1109","author":[{"given":"Peng","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alejandro","family":"Salado","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangrui","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","author":"henderson","year":"2006","journal-title":"Handbooks in Operations Research and Management Science Simulation"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1007\/3-540-45435-7_18","article-title":"PAC bounds for multi-armed bandit and markov decision processes","author":"even-dar","year":"2002","journal-title":"Conference on Computational Learning Theory"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/0377-2217(89)90348-2"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1002\/9780470182963","volume":"703","author":"powell","year":"2007","journal-title":"Approximate Dynamic Programming Solving the Curses of Dimensionality"},{"key":"ref14","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref15","article-title":"Learning from delayed rewards","author":"watkins","year":"1989"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1126\/science.153.3731.34","article-title":"Dynamic programming","volume":"153","author":"bellman","year":"1966","journal-title":"Science"},{"key":"ref17","article-title":"Deep reinforcement learning and the deadly triad","author":"van hasselt","year":"2018"},{"key":"ref18","first-page":"1075","article-title":"Analysis of temporal-diffference learning with function approximation","author":"tsitsiklis","year":"1997","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref4","article-title":"Applying tradespace exploration to verification engineering: From practice to theory and back again","author":"salado","year":"2016","journal-title":"Conference on Systems Engineering Research (CSER)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SysEng.2018.8544446"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2017.2695583"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1002\/j.2334-5837.2019.00608.x"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1002\/sys.21481"},{"key":"ref7","author":"isermann","year":"2006","journal-title":"Fault-Diagnosis Systems An Introduction from Fault Detection to Fault Tolerance"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/sys.21463"},{"key":"ref9","author":"koller","year":"2009","journal-title":"Probabilistic Graphical Models Principles and Techniques"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/9780470618851"},{"key":"ref20","volume":"14","author":"hu","year":"2007","journal-title":"Markov Decision Processes With Their Applications"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MASSP.1987.1165576"},{"key":"ref24","author":"pearl","year":"2014","journal-title":"Probabilistic Reasoning in Intelligent Systems Networks of Plausible Inference"},{"key":"ref23","article-title":"Neural networks for machine learning lecture 6a overview of mini-batch gradient descent","volume":"14","author":"hinton","year":"2012","journal-title":"CITE"},{"key":"ref26","author":"heaton","year":"2015","journal-title":"Volume 3 Deep Learning and Neural Networks"},{"key":"ref25","volume":"4","author":"blanchard","year":"1990","journal-title":"Systems Engineering and Analysis"}],"event":{"name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Toronto, ON, Canada","start":{"date-parts":[[2020,10,11]]},"end":{"date-parts":[[2020,10,14]]}},"container-title":["2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9282733\/9282811\/09282929.pdf?arnumber=9282929","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T15:15:56Z","timestamp":1656602156000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9282929\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,11]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/smc42975.2020.9282929","relation":{},"subject":[],"published":{"date-parts":[[2020,10,11]]}}}