{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T11:46:18Z","timestamp":1725795978650},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319079943"},{"type":"electronic","value":"9783319079950"}],"license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-07995-0_13","type":"book-chapter","created":{"date-parts":[[2014,6,10]],"date-time":"2014-06-10T19:24:31Z","timestamp":1402428271000},"page":"125-133","source":"Crossref","is-referenced-by-count":3,"title":["Effect of Initial Conditioning of Reinforcement Learning Agents on Feedback Control Tasks over Continuous State and Action Spaces"],"prefix":"10.1007","author":[{"given":"Borja","family":"Fernandez-Gauna","sequence":"first","affiliation":[]},{"given":"Juan Luis","family":"Osa","sequence":"additional","affiliation":[]},{"given":"Manuel","family":"Gra\u00f1a","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"issue":"6","key":"13_CR1","doi-asserted-by":"publisher","first-page":"858","DOI":"10.1016\/j.engappai.2007.08.002","volume":"21","author":"M.S. Alam","year":"2008","unstructured":"Alam, M.S., Tokhi, M.O.: Hybrid fuzzy logic control with genetic optimisation for a single-link flexible manipulator. Engineering Applications of Artificial Intelligence\u00a021(6), 858\u2013873 (2008)","journal-title":"Engineering Applications of Artificial Intelligence"},{"issue":"6","key":"13_CR2","doi-asserted-by":"publisher","first-page":"846","DOI":"10.1016\/j.engappai.2007.11.002","volume":"21","author":"D. Bellomo","year":"2008","unstructured":"Bellomo, D., Naso, D., Babuska, R.: Adaptive fuzzy control of a non-linear servo-drive: Theory and experimental results. Engineering Applications of Artificial Intelligence\u00a021(6), 846\u2013857 (2008)","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"13_CR3","unstructured":"Busoniu, L., Babuska, R., De Schutter, B., Ernst, D.: Reinforcement Learning and Dynamic Programming using Function Approximation. CRC Press (2010)"},{"issue":"4","key":"13_CR4","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1016\/S0952-1976(99)00013-5","volume":"12","author":"C. Douligeris","year":"1999","unstructured":"Douligeris, C., Singh, B.K.: Analysis of neural-network-based congestion control algorithms for atm networks. Engineering Applications of Artificial Intelligence\u00a012(4), 453\u2013470 (1999)","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"13_CR5","doi-asserted-by":"publisher","first-page":"667","DOI":"10.1016\/j.engappai.2003.09.008","volume":"16","author":"H. Du","year":"2003","unstructured":"Du, H., Lam, J., Sze, K.Y.: Non-fragile output feedback h vehicle suspension control using genetic algorithm. Engineering Applications of Artificial Intelligence\u00a016, 667\u2013680 (2003)","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"13_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1007\/978-3-642-38622-0_46","volume-title":"Natural and Artificial Computation in Engineering and Medical Applications","author":"B. Fernandez-Gauna","year":"2013","unstructured":"Fernandez-Gauna, B., Ansoategui, I., Etxeberria-Agiriano, I., Gra\u00f1a, M.: An empirical study of actor-critic methods for feedback controllers of ball-screw drivers. In: Ferr\u00e1ndez Vicente, J.M., \u00c1lvarez S\u00e1nchez, J.R., de la Paz L\u00f3pez, F., Toledo Moreo, F. J. (eds.) IWINAC 2013, Part II. LNCS, vol.\u00a07931, pp. 441\u2013450. Springer, Heidelberg (2013)"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Fernandez-Gauna, B., Ansoategui, I., Etxeberria-Agiriano, I., Gra\u00f1a, M.: Reinforcement learning of ball screw feed drive controllers. In: Engineering Applications of Artificial Intelligence (2014) (first online)","DOI":"10.1016\/j.engappai.2014.01.015"},{"issue":"1-2","key":"13_CR8","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/s10994-011-5235-x","volume":"84","author":"R. Hafner","year":"2011","unstructured":"Hafner, R., Riedmiller, M.: Reinforcement learning in feedback control: Challenges and benchmarks from technical process control. Machine Learning\u00a084(1-2), 137\u2013169 (2011)","journal-title":"Machine Learning"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Hasselt, H.: Reinforcement Learning in Continuous State and Action Spaces. In: Reinforcement Learning: State of the art. Adaptation, Learning, and Optimization, pp. 207\u2013251. Springer (2012)","DOI":"10.1007\/978-3-642-27645-3_7"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Hui, Y., Yan, Z., Long, W.Z., Chao, Y.: Adaptive double-loop pid control method of dc motor based on the ga-fnc algorithm. In: 2012 8th IEEE International Symposium on Instrumentation and Control Technology (ISICT), pp. 324\u2013329 (July 2012)","DOI":"10.1109\/ISICT.2012.6291594"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Koren, Y., Lo, C.C.: Advanced controllers for feed drives. In: Annals of the CIRP, vol.\u00a041 (1992)","DOI":"10.1016\/S0007-8506(07)63255-7"},{"issue":"4","key":"13_CR12","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1016\/0952-1976(96)00034-6","volume":"9","author":"S. Kundu","year":"1996","unstructured":"Kundu, S., Kawata, S.: Genetic algorithms for optimal feedback control design. Engineering Applications of Artificial Intelligence\u00a09(4), 403\u2013411 (1996)","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Lewis, F.L., Liu, D., et al.: Reinforcement Learning and Approximate Dynamic Programming for Feedback Control. Wiley (2013)","DOI":"10.1002\/9781118453988"},{"key":"13_CR14","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1109\/MCAS.2009.933854","volume":"9","author":"F.L. Lewis","year":"2012","unstructured":"Lewis, F.L., Vrabie, D., Vamvoudakis, K.G.: Reinforcement learning and feedback control. IEEE Control Systems Magazine\u00a09, 32\u201350 (2012)","journal-title":"IEEE Control Systems Magazine"},{"issue":"3","key":"13_CR15","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1016\/j.engappai.2004.09.006","volume":"18","author":"J. Madar","year":"2005","unstructured":"Madar, J., Abonyi, J., Szeifert, F.: Feedback linearizing control using hybrid neural networks identified by sensitivity approach. Engineering Applications of Artificial Intelligence\u00a018(3), 343\u2013351 (2005)","journal-title":"Engineering Applications of Artificial Intelligence"},{"issue":"1","key":"13_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/S0952-1976(00)00047-6","volume":"14","author":"M.L. Moore","year":"2001","unstructured":"Moore, M.L., Musacchio, J.T., Passino, K.M.: Genetic adaptive control for an inverted wedge: experiments and comparative analyses. Engineering Applications of Artificial Intelligence\u00a014(1), 1\u201314 (2001)","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"13_CR17","unstructured":"Neumann, G.: The Reinforcement Learning Toolbox, Reinforcement Learning for Optimal Control Tasks. PhD thesis, Technischen Universitaet, Graz (2005)"},{"key":"13_CR18","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1016\/S0952-1976(01)00031-8","volume":"14","author":"I.O. Bucak","year":"2001","unstructured":"Bucak, I.O., Zohdy, M.A.: Reinforcement learning control of nonlinear multi-link system. Engineering Applications of Artificial Intelligence\u00a014, 563\u2013575 (2001)","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Senthilkumar, K.S., Bharadwaj, K.K.: Hybrid genetic-fuzzy approach to autonomous mobile robot. In: IEEE International Conference on Technologies for Practical Robot Applications, TePRA 2009, pp. 29\u201334, 9\u201310 (2009)","DOI":"10.1109\/TEPRA.2009.5339649"},{"key":"13_CR20","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1115\/1.2836818","volume":"119","author":"K. Srinivasan","year":"1997","unstructured":"Srinivasan, K., Tsao, T.C.: Machine feed drives and their control - a survey of the state of the art. Journal of Manufacturing Science and Engineering\u00a0119, 743\u2013748 (1997)","journal-title":"Journal of Manufacturing Science and Engineering"},{"key":"13_CR21","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"R. Sutton","year":"1999","unstructured":"Sutton, R., Precup, D., Singh, S.: Between mdps and semi-mdps: A framework for temporal abstraction in reinforcement learning. Artificial Intelligence\u00a0112, 181\u2013211 (1999)","journal-title":"Artificial Intelligence"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press (1998)","DOI":"10.1109\/TNN.1998.712192"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"van Hasselt, H., Wiering, M.A.: Reinforcement learning in continuous action spaces. In: Proceedings of the 2007 IEEE Symposium on Approximate Dynamic Programming and Reinforcement Learning (2007)","DOI":"10.1109\/ADPRL.2007.368199"},{"key":"13_CR24","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1115\/1.2899060","volume":"115","author":"J.G. Ziegler","year":"1993","unstructured":"Ziegler, J.G., Nichols, N.B.: Optimum settings for automatic controllers. Journal of Dynamic Systems, Measurements and Control\u00a0115, 220\u2013222 (1993)","journal-title":"Journal of Dynamic Systems, Measurements and Control"}],"container-title":["Advances in Intelligent Systems and Computing","International Joint Conference SOCO\u201914-CISIS\u201914-ICEUTE\u201914"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-07995-0_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,16]],"date-time":"2023-02-16T15:53:43Z","timestamp":1676562823000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-07995-0_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319079943","9783319079950"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-07995-0_13","relation":{},"ISSN":["2194-5357","2194-5365"],"issn-type":[{"type":"print","value":"2194-5357"},{"type":"electronic","value":"2194-5365"}],"subject":[],"published":{"date-parts":[[2014]]}}}