{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T17:12:12Z","timestamp":1771348332708,"version":"3.50.1"},"reference-count":22,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T00:00:00Z","timestamp":1748217600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T00:00:00Z","timestamp":1748217600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Quality &amp; Reliability Eng"],"published-print":{"date-parts":[[2025,10]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>In this paper, we propose a new maintenance strategy considering \u201cdo nothing\u201d, \u201cimperfect repair\u201d, and \u201creplace\u201d as alternative actions on a deteriorating system. The system is subject to random shocks that accelerate degradation. Unlike most existing works regarding maintenance with imperfect repair actions, we propose a dynamic improvement factor that changes according to the state of the system at maintenance time. The proposed improvement factor is considered to have a random rejuvenating effect on the system, which reduces its degradation level (state) by reducing age. Such degradation state\u2010dependent improvement factor is more realistic than a fixed or random one, since the amount of improvement (rejuvenation) and the cost associated with maintenance are proportional to the system needs as described by the degradation levels. A Markov decision process is formulated to model the maintenance problem with a continuous state space and a Deep Reinforcement Learning algorithm is used to optimize the maintenance policy where the decision maker is trained by a Deep Q\u2010network. Central to this study is the comparison of three distinct models: a state\u2010independent improvement factor (Model I) versus two state\u2010dependent ones (Models II and III) with deterministic and stochastic repair effects, respectively. Through numerical and illustrative examples, this comparison underscores the importance of selecting the appropriate model when system condition data are available, demonstrating that state\u2010dependent models outperform their state\u2010independent counterparts in terms of cost\u2010efficiency and effectiveness. A sensitivity analysis is also conducted to examine the influence of the model's parameters on model\u00a0selection.<\/jats:p>","DOI":"10.1002\/qre.3806","type":"journal-article","created":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T03:06:31Z","timestamp":1748228791000},"page":"2715-2728","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimal Dynamic State\u2010Dependent Maintenance Policy by Deep Reinforcement Learning"],"prefix":"10.1002","volume":"41","author":[{"given":"Shaghayegh","family":"Eidi","sequence":"first","affiliation":[{"name":"School of Mathematics Statistics and Computer Science College of Science University of Tehran Tehran Iran"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1880-937X","authenticated-orcid":false,"given":"Firoozeh","family":"Haghighi","sequence":"additional","affiliation":[{"name":"School of Mathematics Statistics and Computer Science College of Science University of Tehran Tehran Iran"}]},{"given":"Abdollah","family":"Safari","sequence":"additional","affiliation":[{"name":"School of Mathematics Statistics and Computer Science College of Science University of Tehran Tehran Iran"}]},{"given":"Enrico","family":"Zio","sequence":"additional","affiliation":[{"name":"Center for Research on Risks and Crises (CRC) Mines Paris\u2010PSL University Paris France"},{"name":"Energy Department Politecnico di Milano Milan Italy"}]}],"member":"311","published-online":{"date-parts":[[2025,5,26]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/0377-2217(92)90309-W"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1080\/05695557908974463"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0951-8320(03)00173-X"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2017.03.015"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2021.107905"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2021.107592"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2018.05.002"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2018.12.029"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2016.10.008"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2020.106994"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2015.02.050"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2011.2167779"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2014.08.011"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1002\/qre.1431"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1080\/08982112.2021.1977950"},{"issue":"1","key":"e_1_2_8_17_1","first-page":"16","article-title":"Deep Reinforcement Learning for Condition\u2010Based Maintenance Planning of Multi\u2010Component Systems Under Dependent Competing Risks","volume":"34","author":"Zhang N.","year":"2020","journal-title":"Reliability Engineering and System Safety"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.renene.2021.11.052"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2022.108613"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2022.3197322"},{"key":"e_1_2_8_21_1","volume-title":"Statistical Methods for Reliability Data","author":"Meeker W.","year":"2022"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2021.107298"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2017.05.004"}],"container-title":["Quality and Reliability Engineering International"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/qre.3806","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/qre.3806","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/qre.3806","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T16:19:01Z","timestamp":1771345141000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/qre.3806"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,26]]},"references-count":22,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["10.1002\/qre.3806"],"URL":"https:\/\/doi.org\/10.1002\/qre.3806","archive":["Portico"],"relation":{},"ISSN":["0748-8017","1099-1638"],"issn-type":[{"value":"0748-8017","type":"print"},{"value":"1099-1638","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,26]]},"assertion":[{"value":"2025-03-19","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-07","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}