{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:48:31Z","timestamp":1730299711419,"version":"3.28.0"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,29]],"date-time":"2021-09-29T00:00:00Z","timestamp":1632873600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,29]],"date-time":"2021-09-29T00:00:00Z","timestamp":1632873600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,29]],"date-time":"2021-09-29T00:00:00Z","timestamp":1632873600000},"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":[[2021,9,29]]},"DOI":"10.1109\/systol52990.2021.9595754","type":"proceedings-article","created":{"date-parts":[[2021,11,9]],"date-time":"2021-11-09T20:44:05Z","timestamp":1636490645000},"page":"25-30","source":"Crossref","is-referenced-by-count":0,"title":["Transfer reinforcement learning for fault-tolerant control by re-using optimal policies"],"prefix":"10.1109","author":[{"given":"Ibrahim","family":"Ahmed","sequence":"first","affiliation":[]},{"given":"Marcos","family":"Quinones-Grueiro","sequence":"additional","affiliation":[]},{"given":"Gautam","family":"Biswas","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2012.06.017"},{"article-title":"Playing atari with deep reinforcement learning","year":"2013","author":"mnih","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2020.106886"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SCISISIS50064.2020.9322775"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref14"},{"key":"ref15","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"99","author":"sutton","year":"1999"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3022893"},{"article-title":"Transfer learning in deep reinforcement learning: A survey","year":"2020","author":"zhu","key":"ref18"},{"key":"ref4","volume":"2","author":"blanke","year":"2006","journal-title":"Diagnosis and Fault-Tolerant Control"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/science.153.3731.34"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2020.3033943"},{"key":"ref5","first-page":"369","article-title":"Generalization in reinforcement learning: Safely approximating the value function","author":"boyan","year":"1995","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196611"},{"key":"ref7","first-page":"56","article-title":"Similarity-Based Methods for Word Sense Disambiguation","author":"dagan","year":"1997","journal-title":"35th Annual Meeting of the Association for Computational Linguistics and 8th Conference of the European Chapter of the Association for Computational Linguistics"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1016\/j.ifacol.2020.12.878","article-title":"Fault-Tolerant Control of Degrading Systems with On-Policy Reinforcement Learning","author":"ahmed","year":"2020","journal-title":"IFAC-PapersOnLine 21st IFAC World Congress"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3724\/SP.J.1004.2009.00739"}],"event":{"name":"2021 5th International Conference on Control and Fault-Tolerant Systems (SysTol)","start":{"date-parts":[[2021,9,29]]},"location":"Saint-Raphael, France","end":{"date-parts":[[2021,10,1]]}},"container-title":["2021 5th International Conference on Control and Fault-Tolerant Systems (SysTol)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9594897\/9594923\/09595754.pdf?arnumber=9595754","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:50:28Z","timestamp":1652201428000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9595754\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,29]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/systol52990.2021.9595754","relation":{},"subject":[],"published":{"date-parts":[[2021,9,29]]}}}