{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T23:22:06Z","timestamp":1774048926284,"version":"3.50.1"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2009,7,1]],"date-time":"2009-07-01T00:00:00Z","timestamp":1246406400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2009,7,1]],"date-time":"2009-07-01T00:00:00Z","timestamp":1246406400000},"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":[[2009,7]]},"DOI":"10.1109\/cca.2009.5281070","type":"proceedings-article","created":{"date-parts":[[2009,10,12]],"date-time":"2009-10-12T15:41:39Z","timestamp":1255362099000},"page":"582-587","source":"Crossref","is-referenced-by-count":16,"title":["Batch Reinforcement Learning for semi-active suspension control"],"prefix":"10.1109","author":[{"given":"Simone","family":"Tognetti","sequence":"first","affiliation":[{"name":"Politecnico di Milano, Dipartimento di Elettronica e Informazione, P.zza L. da Vinci 32, 20133, ITALY"}]},{"given":"Sergio M.","family":"Savaresi","sequence":"additional","affiliation":[{"name":"Politecnico di Milano, Dipartimento di Elettronica e Informazione, P.zza L. da Vinci 32, 20133, ITALY"}]},{"given":"Cristiano","family":"Spelta","sequence":"additional","affiliation":[{"name":"Dipartimento di Ingegneria dell'Informazione e Metodi Matematici, Universit\u00e0 degli Studi di Bergamo, viale Marconi 5, Dalmine BG) ITALY"}]},{"given":"Marcello","family":"Restelli","sequence":"additional","affiliation":[{"name":"Politecnico di Milano, Dipartimento di Elettronica e Informazione, P.zza L. da Vinci 32, 20133, ITALY"}]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"publisher","DOI":"10.1115\/1.2745846"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1076\/vesd.39.4.279.14149"},{"key":"18","year":"0"},{"key":"15","author":"kiencke","year":"2000","journal-title":"Automotive Control Systems for Engine Driveline and Vehicle"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1177\/1045389X03014003004"},{"key":"13","article-title":"System for Controlling the Transmission of Energy Between Spaced Members","author":"karnopp","year":"1974"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1016\/S0967-0661(98)00070-7"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(97)00101-5"},{"key":"12","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"Reinforcement Learning: A Survey","volume":"4","author":"kaelbing","year":"1996","journal-title":"Journal of Artificial Intelligence Research11"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1076\/vesd.32.4.421.2082"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2008.906313"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1115\/1.1898241"},{"key":"23","year":"0"},{"key":"24","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"25","doi-asserted-by":"publisher","DOI":"10.1080\/00423119408969074"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.1016\/S0967-0661(98)00079-3"},{"key":"27","doi-asserted-by":"publisher","DOI":"10.1243\/0954407971526551"},{"key":"28","article-title":"Learning from delayed rewards","author":"watkins","year":"1989"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.3166\/ejc.9.66-76"},{"key":"2","first-page":"9","article-title":"Fitted q-iteration in continuous action-space mdps","author":"antos","year":"2008","journal-title":"Advances in Neural Information Processing Sys-tems 20 J"},{"key":"10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S0005-1098(00)00117-5","article-title":"Approximate Linearization via Feedback - an Overview","volume":"27","author":"guardabassi","year":"2001","journal-title":"Survey paper on Automatica"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1155\/2001\/350235"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1016\/S0967-0661(02)00008-4"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1076\/vesd.31.4.213.4233"},{"key":"5","first-page":"503","article-title":"Tree-based batch mode reinforcement learning","volume":"6","author":"ernst","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2003.819592"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1109\/ISIE.2005.1528942"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-006-6226-1"}],"event":{"name":"2009 IEEE Control Applications, (CCA) & Intelligent Control, (ISIC)","location":"St. Petersburg, Russia","start":{"date-parts":[[2009,7,8]]},"end":{"date-parts":[[2009,7,10]]}},"container-title":["2009 IEEE Control Applications, (CCA) & Intelligent Control, (ISIC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5268173\/5280693\/05281070.pdf?arnumber=5281070","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T22:45:27Z","timestamp":1774046727000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/5281070\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,7]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/cca.2009.5281070","relation":{},"subject":[],"published":{"date-parts":[[2009,7]]}}}