{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T23:10:14Z","timestamp":1769814614841,"version":"3.49.0"},"reference-count":28,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2015,5,1]],"date-time":"2015-05-01T00:00:00Z","timestamp":1430438400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2015,5]]},"DOI":"10.1109\/tcyb.2014.2343194","type":"journal-article","created":{"date-parts":[[2014,8,26]],"date-time":"2014-08-26T18:36:32Z","timestamp":1409078192000},"page":"1017-1027","source":"Crossref","is-referenced-by-count":40,"title":["Reinforcement Learning for Port-Hamiltonian Systems"],"prefix":"10.1109","volume":"45","author":[{"given":"Olivier","family":"Sprangers","sequence":"first","affiliation":[]},{"given":"Robert","family":"Babuska","sequence":"additional","affiliation":[]},{"given":"Subramanya P.","family":"Nageshrao","sequence":"additional","affiliation":[]},{"given":"Gabriel A. D.","family":"Lopes","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"crossref","first-page":"2008","DOI":"10.1016\/j.automatica.2010.08.001","article-title":"Stabilization and ${H}^\\infty $ control of nonlinear port-controlled Hamiltonian systems subject to actuator saturation","volume":"46","author":"wei","year":"2010","journal-title":"Automatica"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2007.10.040"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/87.748155"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2003.817908"},{"key":"ref14","article-title":"Port Hamiltonian systems: A unified approach for modeling and control finite and infinite dimensional physical systems","author":"macchelli","year":"2002"},{"key":"ref15","article-title":"A variable structure approach to energy shaping","author":"macchelli","year":"2003","journal-title":"Proc Eur Control Conf"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2009.5160232"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1002\/acs.714"},{"key":"ref18","first-page":"15678","article-title":"Iterative feedback tuning for Hamiltonian systems","author":"fujimoto","year":"2008","journal-title":"Proc 17th World Congr Int Fed Autom Control"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2013.2273477"},{"key":"ref28","article-title":"Value function approximation in reinforcement learning using the Fourier basis","author":"konidaris","year":"2008"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/37.915398"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.3182\/20120829-3-IT-4022.00046","article-title":"Casimir-based control beyond the dissipation obstacle","author":"koopman","year":"2012"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4471-0507-7","author":"van der schaft","year":"2000","journal-title":"L2-Gain and Passivity Techniques in Nonlinear Control"},{"key":"ref6","author":"secchi","year":"2007","journal-title":"Control of Interactive Robotic Interfaces A Port-Hamiltonian Approach"},{"key":"ref5","author":"duindam","year":"2009","journal-title":"Port-based modeling and control for efficient bipedal walking robots"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012901385691"},{"key":"ref7","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.2006930"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2011.2170565"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(89)90054-X"},{"key":"ref20","first-page":"282","article-title":"Port-controlled Hamiltonian systems: Modelling origins and system theoretic properties","author":"maschke","year":"1992","journal-title":"Proc 3rd Conf Nonlin Control Syst (NOLCOS)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2012.6426427"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/0034-4877(94)90038-8"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"ref26","first-page":"19","article-title":"A Bayesian sampling approach to exploration in reinforcement learning","author":"asmuth","year":"2009","journal-title":"Proc 25th Conf Uncertainty Artif Intell"},{"key":"ref25","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/7084711\/06883207.pdf?arnumber=6883207","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:41:50Z","timestamp":1642005710000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6883207"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,5]]},"references-count":28,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2014.2343194","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,5]]}}}