{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T12:24:55Z","timestamp":1730204695174,"version":"3.28.0"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T00:00:00Z","timestamp":1607904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T00:00:00Z","timestamp":1607904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T00:00:00Z","timestamp":1607904000000},"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":[[2020,12,14]]},"DOI":"10.1109\/cdc42340.2020.9303981","type":"proceedings-article","created":{"date-parts":[[2021,1,13]],"date-time":"2021-01-13T07:27:32Z","timestamp":1610522852000},"page":"585-590","source":"Crossref","is-referenced-by-count":0,"title":["Learning Feedforward Control of a Hydraulic Clutch Actuation Path Based on Policy Gradients"],"prefix":"10.1109","author":[{"given":"Felix","family":"Mesmer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomas","family":"Szabo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Knut","family":"Graichen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1088\/0964-1726\/18\/4\/045001"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1049\/ip-cta:20010375"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-61068-4_7"},{"key":"ref13","first-page":"538","article-title":"The optimal reward baseline for gradient-based reinforcement learning","author":"weaver","year":"2001","journal-title":"Proceedings of the Conference on Uncertainty in Artificial Intelligence"},{"key":"ref14","article-title":"Machine learning and pattern recognition","author":"bishop","year":"2006","journal-title":"Information Science and Statistics"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/BF00992696","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"williams","year":"1992","journal-title":"Machine Learning"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1007\/978-3-642-35289-8_25","article-title":"Stochastic gradient descent tricks","author":"bottou","year":"2012","journal-title":"Neural Networks Tricks of the Trade"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1524\/auto.2009.0767"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/AIM.2019.8868433"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1080\/00207179508921959"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref8","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proceedings of the Conference on Advances in Neural Information Processing Systems"},{"key":"ref7","first-page":"14","article-title":"Reinforcement learning: An overview","author":"glorennec","year":"2000","journal-title":"Proceedings European Symposium on Intelligent Techniques (ESIT-00)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2019.8795978"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2018.03.012"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.12.004"}],"event":{"name":"2020 59th IEEE Conference on Decision and Control (CDC)","start":{"date-parts":[[2020,12,14]]},"location":"Jeju, Korea (South)","end":{"date-parts":[[2020,12,18]]}},"container-title":["2020 59th IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9303728\/9303729\/09303981.pdf?arnumber=9303981","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T15:54:01Z","timestamp":1656345241000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9303981\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,14]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/cdc42340.2020.9303981","relation":{},"subject":[],"published":{"date-parts":[[2020,12,14]]}}}