{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T01:50:18Z","timestamp":1742953818505,"version":"3.40.3"},"publisher-location":"London","reference-count":20,"publisher":"Springer London","isbn-type":[{"type":"electronic","value":"9781447151029"}],"license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-1-4471-5102-9_224-2","type":"book-chapter","created":{"date-parts":[[2014,12,15]],"date-time":"2014-12-15T09:19:59Z","timestamp":1418635199000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Neural Control and Approximate Dynamic Programming"],"prefix":"10.1007","author":[{"given":"Frank L.","family":"Lewis","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyriakos G.","family":"Vamvoudakis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,12,8]]},"reference":[{"issue":"5","key":"224-2_CR1","doi-asserted-by":"publisher","first-page":"779","DOI":"10.1016\/j.automatica.2004.11.034","volume":"41","author":"M Abu-Khalaf","year":"2005","unstructured":"Abu-Khalaf M, Lewis FL (2005) Nearly optimal control laws for nonlinear systems with saturating actuators using a neural network HJB approach. Automatica 41(5):779\u2013791","journal-title":"Automatica"},{"issue":"4","key":"224-2_CR2","doi-asserted-by":"publisher","first-page":"943","DOI":"10.1109\/TSMCB.2008.926614","volume":"38","author":"A Al-Tamimi","year":"2008","unstructured":"Al-Tamimi A, Lewis FL, Abu-Khalaf M (2008) Discrete-time nonlinear HJB solution using approximate dynamic programming: convergence proof. IEEE Trans Syst Man Cybern Part B 38(4):943\u2013949","journal-title":"IEEE Trans Syst Man Cybern Part B"},{"key":"224-2_CR3","doi-asserted-by":"publisher","DOI":"10.1002\/9781118453988","volume-title":"Reinforcement learning and approximate dynamic programming for feedback control. IEEE Press computational intelligence series","author":"FL Lewis","year":"2012","unstructured":"Lewis FL, Liu D (2012) Reinforcement learning and approximate dynamic programming for feedback control. IEEE Press computational intelligence series. Wiley-Blackwell, Oxford"},{"issue":"1","key":"224-2_CR4","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/TSMCB.2010.2043839","volume":"41","author":"FL Lewis","year":"2011","unstructured":"Lewis FL, Vamvoudakis KG (2011) Reinforcement learning for partially observable dynamic processes: adaptive dynamic programming using measured output data. IEEE Trans Syst Man Cybern Part B 41(1):14\u201325","journal-title":"IEEE Trans Syst Man Cybern Part B"},{"key":"224-2_CR5","volume-title":"Neural network control of robot manipulators and nonlinear systems","author":"FL Lewis","year":"1999","unstructured":"Lewis FL, Jagannathan S, Yesildirek A (1999) Neural network control of robot manipulators and nonlinear systems. Taylor and Francis, London"},{"key":"224-2_CR6","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898717563","volume-title":"Neuro-fuzzy control of industrial systems with actuator nonlinearities. Society of Industrial and Applied Mathematics","author":"FL Lewis","year":"2002","unstructured":"Lewis FL, Campos J, Selmic R (2002) Neuro-fuzzy control of industrial systems with actuator nonlinearities. Society of Industrial and Applied Mathematics Press, Philadelphia"},{"key":"224-2_CR7","doi-asserted-by":"publisher","DOI":"10.1002\/9781118122631","volume-title":"Optimal control","author":"FL Lewis","year":"2012","unstructured":"Lewis FL, Vrabie D, Syrmos VL (2012a) Optimal control. Wiley, New York"},{"issue":"6","key":"224-2_CR8","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1109\/MCS.2012.2214134","volume":"32","author":"FL Lewis","year":"2012","unstructured":"Lewis FL, Vrabie D, Vamvoudakis KG (2012b) Reinforcement learning and feedback control: using natural decision methods to design optimal adaptive controllers. IEEE Control Syst Mag 32(6):76\u2013105","journal-title":"IEEE Control Syst Mag"},{"issue":"3","key":"224-2_CR9","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1177\/027836498700600303","volume":"6","author":"JJE Slotine","year":"1987","unstructured":"Slotine JJE, Li W (1987) On the adaptive control of robot manipulators. Int J Robot Res 6(3):49\u201359","journal-title":"Int J Robot Res"},{"key":"224-2_CR10","volume-title":"Reinforcement learning \u2013 an introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton RS, Barto AG (1998) Reinforcement learning \u2013 an introduction. MIT, Cambridge"},{"issue":"5","key":"224-2_CR11","doi-asserted-by":"publisher","first-page":"878","DOI":"10.1016\/j.automatica.2010.02.018","volume":"46","author":"KG Vamvoudakis","year":"2010","unstructured":"Vamvoudakis KG, Lewis FL (2010) Online actor-critic algorithm to solve the continuous-time infinite horizon optimal control problem. Automatica 46(5):878\u2013888","journal-title":"Automatica"},{"issue":"8","key":"224-2_CR12","doi-asserted-by":"publisher","first-page":"1556","DOI":"10.1016\/j.automatica.2011.03.005","volume":"47","author":"KG Vamvoudakis","year":"2011","unstructured":"Vamvoudakis KG, Lewis FL (2011) Multi-player non zero sum games: online adaptive learning solution of coupled Hamilton-Jacobi equations. Automatica 47(8):1556\u20131569","journal-title":"Automatica"},{"issue":"13","key":"224-2_CR13","doi-asserted-by":"publisher","first-page":"1460","DOI":"10.1002\/rnc.1760","volume":"22","author":"KG Vamvoudakis","year":"2012","unstructured":"Vamvoudakis KG, Lewis FL (2012) Online solution of nonlinear two-player zero-sum games using synchronous policy iteration. Int J Robust Nonlinear Control 22(13):1460\u20131483","journal-title":"Int J Robust Nonlinear Control"},{"issue":"8","key":"224-2_CR14","doi-asserted-by":"publisher","first-page":"1598","DOI":"10.1016\/j.automatica.2012.05.074","volume":"48","author":"KG Vamvoudakis","year":"2012","unstructured":"Vamvoudakis KG, Lewis FL, Hudas GR (2012a) Multi-agent differential graphical games: online adaptive learning solution for synchronization with optimality. Automatica 48(8):1598\u20131611","journal-title":"Automatica"},{"key":"224-2_CR15","doi-asserted-by":"crossref","unstructured":"Vamvoudakis KG, Lewis FL, Johnson M, Dixon WE (2012b) Online learning algorithm for Stackelberg games in problems with hierarchy. In: Proceedings of the 51st IEEE conference on decision and control, Maui pp\u00a01883\u20131889","DOI":"10.1109\/CDC.2012.6426969"},{"key":"224-2_CR16","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.3018","author":"KG Vamvoudakis","year":"2013","unstructured":"Vamvoudakis KG, Vrabie D, Lewis FL (2013) Online adaptive algorithm for optimal control with integral reinforcement learning. Int J Robust Nonlinear Control, Wiley. doi: 10.1002\/rnc.3018","journal-title":"Int J Robust Nonlinear Control, Wiley."},{"issue":"2","key":"224-2_CR17","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1016\/j.automatica.2008.08.017","volume":"45","author":"D Vrabie","year":"2009","unstructured":"Vrabie D, Pastravanu O, Lewis FL, Abu-Khalaf M (2009) Adaptive optimal control for continuous-time linear systems based on policy iteration. Automatica 45(2):477\u2013484","journal-title":"Automatica"},{"key":"224-2_CR18","doi-asserted-by":"crossref","DOI":"10.1049\/PBCE081E","volume-title":"Optimal adaptive control and differential games by reinforcement learning principles","author":"D Vrabie","year":"2012","unstructured":"Vrabie D, Vamvoudakis KG, Lewis FL (2012) Optimal adaptive control and differential games by reinforcement learning principles. Control engineering series. IET Press, London"},{"key":"224-2_CR19","volume-title":"Neural networks for control and system identification","author":"PJ Werbos","year":"1989","unstructured":"Werbos PJ (1989) Neural networks for control and system identification. In: Proceedings of the IEEE conference on decision and control, Tampa"},{"key":"224-2_CR20","volume-title":"Handbook of intelligent control","author":"PJ Werbos","year":"1992","unstructured":"Werbos PJ (1992) Approximate dynamic programming for real-time control and neural modeling. In: White DA, Sofge DA (eds) Handbook of intelligent control. Van Nostrand Reinhold, New\u00a0York"}],"container-title":["Encyclopedia of Systems and Control"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-1-4471-5102-9_224-2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T13:40:23Z","timestamp":1675258823000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-1-4471-5102-9_224-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9781447151029"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-1-4471-5102-9_224-2","relation":{},"subject":[],"published":{"date-parts":[[2014]]},"assertion":[{"value":"22 September 2014, 11:51:08","order":1,"name":"received","label":"Received","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"22 September 2014, 11:51:08","order":2,"name":"accepted","label":"Accepted","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"8 December 2014","order":3,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}