{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T17:09:08Z","timestamp":1765040948026},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2019,6,19]],"date-time":"2019-06-19T00:00:00Z","timestamp":1560902400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2019,6,19]],"date-time":"2019-06-19T00:00:00Z","timestamp":1560902400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Genet Program Evolvable Mach"],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1007\/s10710-019-09357-1","type":"journal-article","created":{"date-parts":[[2019,6,19]],"date-time":"2019-06-19T17:02:42Z","timestamp":1560963762000},"page":"479-501","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["A covariance matrix adaptation evolution strategy in reproducing kernel Hilbert space"],"prefix":"10.1007","volume":"20","author":[{"given":"Viet-Hung","family":"Dang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ngo Anh","family":"Vien","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"TaeChoong","family":"Chung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,6,19]]},"reference":[{"key":"9357_CR1","volume-title":"The Geometry of Random Fields","author":"RJ Adler","year":"1981","unstructured":"R.J. Adler, The Geometry of Random Fields (Wiley, New York, 1981)"},{"key":"9357_CR2","unstructured":"J.A.D. Bagnell, J. Schneider, Policy search in reproducing kernel Hilbert space. Technical Report CMU-RI-TR-03-45, Robotics Institute, Pittsburgh, PA (2003)"},{"key":"9357_CR3","volume-title":"A Course in Functional Analysis","author":"JB Conway","year":"2013","unstructured":"J.B. Conway, A Course in Functional Analysis, vol. 96 (Springer, Berlin, 2013)"},{"issue":"1\u20132","key":"9357_CR4","first-page":"1","volume":"2","author":"MP Deisenroth","year":"2013","unstructured":"M.P. Deisenroth, G. Neumann, J. Peters et al., A survey on policy search for robotics. Found. Trends\u00ae Robot. 2(1\u20132), 1\u2013142 (2013)","journal-title":"Found. Trends\u00ae Robot."},{"key":"9357_CR5","doi-asserted-by":"crossref","unstructured":"A. Doerr, N.D. Ratliff, J. Bohg, M. Toussaint, S. Schaal, Direct loss minimization inverse optimal control, in Robotics: Science and Systems XI, Sapienza University of Rome, Rome, Italy, July 13\u201317 (2015)","DOI":"10.15607\/RSS.2015.XI.013"},{"key":"9357_CR6","unstructured":"J. Dong, M. Mukadam, F. Dellaert, B. Boots, Motion planning as probabilistic inference using Gaussian processes and factor graphs, in Robotics: Science and Systems XII, University of Michigan, Ann Arbor, Michigan, USA, June 18\u2013June 22 (2016)"},{"issue":"1","key":"9357_CR7","first-page":"2319","volume":"17","author":"M Ghavamzadeh","year":"2016","unstructured":"M. Ghavamzadeh, Y. Engel, M. Valko, Bayesian policy gradient and actor-critic algorithms. J. Mach. Learn. Res. 17(1), 2319\u20132371 (2016)","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"9357_CR8","doi-asserted-by":"publisher","first-page":":1","DOI":"10.1145\/2682626","volume":"34","author":"S Ha","year":"2014","unstructured":"S. Ha, C.K. Liu, Iterative training of dynamic skills inspired by human coaching techniques. ACM Trans. Graph. 34(1), :1\u20131:11 (2014)","journal-title":"ACM Trans. Graph."},{"key":"9357_CR9","unstructured":"S. Ha, C.K. Liu, Evolutionary optimization for parameterized whole-body dynamic motor skills, in IEEE International Conference on Robotics and Automation (ICRA), pp. 1390\u20131397 (2016)"},{"key":"9357_CR10","unstructured":"N. Hansen, The CMA evolution strategy: a tutorial. CoRR \n                    arXiv:1604.00772\n                    \n                   (2016)"},{"key":"9357_CR11","first-page":"145","volume-title":"Theory and Principled Methods for the Design of Metaheuristics","author":"Nikolaus Hansen","year":"2013","unstructured":"N. Hansen, A. Auger, Principled design of continuous stochastic search: from theory to practice, in Theory and principled methods for the design of metaheuristics, ed. by Y. Borenstein, A. Moraglio,  pp. 145\u2013180 (Springer, Berlin, 2014)"},{"issue":"1","key":"9357_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/106365603321828970","volume":"11","author":"N Hansen","year":"2003","unstructured":"N. Hansen, S.D. M\u00fcller, P. Koumoutsakos, Reducing the time complexity of the derandomized evolution strategy with covariance matrix adaptation (CMA-ES). Evol. Comput. 11(1), 1\u201318 (2003)","journal-title":"Evol. Comput."},{"key":"9357_CR13","unstructured":"V. Heidrich-Meisner, C. Igel, Similarities and differences between policy gradient methods and evolution strategies, in The European Symposium on Artificial Neural Networks (ESANN), pp. 149\u2013154 (2008)"},{"key":"9357_CR14","doi-asserted-by":"crossref","unstructured":"V. Heidrich-Meisner, C. Igel, Hoeffding and Bernstein races for selecting policies in evolutionary direct policy search, in Proceedings of the International Conference on Machine Learning, ICML, pp. 401\u2013408 (2009)","DOI":"10.1145\/1553374.1553426"},{"issue":"4","key":"9357_CR15","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1016\/j.jalgor.2009.04.002","volume":"64","author":"V Heidrich-Meisner","year":"2009","unstructured":"V. Heidrich-Meisner, C. Igel, Neuroevolution strategies for episodic reinforcement learning. J. Algorithms 64(4), 152\u2013168 (2009)","journal-title":"J. Algorithms"},{"key":"9357_CR16","first-page":"1","volume":"16","author":"H Kadri","year":"2015","unstructured":"H. Kadri, E. Duflos, P. Preux, S. Canu, A. Rakotomamonjy, J. Audiffren, Operator-valued kernels for learning from functional response data. J. Mach. Learn. Res. 16, 1\u201354 (2015)","journal-title":"J. Mach. Learn. Res."},{"key":"9357_CR17","unstructured":"M.F. Kasim, P.A. Norreys, Infinite dimensional optimistic optimisation with applications on physical systems. arXiv preprint \n                    arXiv:1611.05845\n                    \n                   (2016)"},{"key":"9357_CR18","volume-title":"Introductory Functional Analysis with Applications","author":"E Kreyszig","year":"1989","unstructured":"E. Kreyszig, Introductory Functional Analysis with Applications (Wiley, New York, 1989)"},{"key":"9357_CR19","unstructured":"G. Lever, R. Stafford, Modelling policies in mdps in reproducing kernel Hilbert space, in Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics, AISTATS 2015, San Diego, California, USA, May 9\u201312 (2015)"},{"key":"9357_CR20","unstructured":"S. Mannor, R.Y. Rubinstein, Y. Gat, The cross entropy method for fast policy search, in Machine Learning, Proceedings of the Twentieth International Conference (ICML), pp. 512\u2013519 (2003)"},{"key":"9357_CR21","unstructured":"Z. Marinho, B. Boots, A.D. Dragan, A. Byravan, G.J. Gordon, S. Srinivasa, Functional gradient motion planning in reproducing kernel hilbert spaces, in Robotics: Science and Systems XII, University of Michigan, Ann Arbor, Michigan, USA, June 18\u201322 (2016)"},{"issue":"1","key":"9357_CR22","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1162\/0899766052530802","volume":"17","author":"CA Micchelli","year":"2005","unstructured":"C.A. Micchelli, M. Pontil, On learning vector-valued functions. Neural Comput. 17(1), 177\u2013204 (2005)","journal-title":"Neural Comput."},{"issue":"7","key":"9357_CR23","doi-asserted-by":"publisher","first-page":"1180","DOI":"10.1016\/j.neucom.2007.11.026","volume":"71","author":"J Peters","year":"2008","unstructured":"J. Peters, S. Schaal, Natural actor-critic. Neurocomputing 71(7), 1180\u20131190 (2008)","journal-title":"Neurocomputing"},{"key":"9357_CR24","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"ML Puterman","year":"2014","unstructured":"M.L. Puterman, Markov Decision Processes: Discrete Stochastic Dynamic Programming (Wiley, New York, 2014)"},{"key":"9357_CR25","volume-title":"Gaussian Processes for Machine Learning","author":"CE Rasmussen","year":"2006","unstructured":"C.E. Rasmussen, C.K.I. Williams, Gaussian Processes for Machine Learning (The MIT Press, Cambridge, 2006)"},{"issue":"2","key":"9357_CR26","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1023\/A:1010091220143","volume":"1","author":"R Rubinstein","year":"1999","unstructured":"R. Rubinstein, The cross-entropy method for combinatorial and continuous optimization. Methodol. Comput. Appl. Probab. 1(2), 127\u2013190 (1999)","journal-title":"Methodol. Comput. Appl. Probab."},{"key":"9357_CR27","volume-title":"The Cross-Entropy Method: A Unified Approach to Combinatorial Optimization, Monte-Carlo Simulation and Machine Learning","author":"RY Rubinstein","year":"2013","unstructured":"R.Y. Rubinstein, D.P. Kroese, The Cross-Entropy Method: A Unified Approach to Combinatorial Optimization, Monte-Carlo Simulation and Machine Learning (Springer, Berlin, 2013)"},{"key":"9357_CR28","doi-asserted-by":"publisher","first-page":"97","DOI":"10.3389\/fncom.2012.00097","volume":"6","author":"EA R\u00fcckert","year":"2013","unstructured":"E.A. R\u00fcckert, G. Neumann, M. Toussaint, W. Maass, Learned graphical models for probabilistic planning provide a new class of movement primitives. Front. Comput. Neurosci. 6, 97 (2013)","journal-title":"Front. Comput. Neurosci."},{"key":"9357_CR29","volume-title":"Learning with Kernels Support Vector Machines, Regularization, Optimization, and Beyond. Adaptive Computation and Machine Learning Series","author":"B Sch\u00f6lkopf","year":"2002","unstructured":"B. Sch\u00f6lkopf, A.J. Smola, Learning with Kernels Support Vector Machines, Regularization, Optimization, and Beyond. Adaptive Computation and Machine Learning Series (MIT Press, Cambridge, 2002)"},{"key":"9357_CR30","first-page":"583","volume-title":"Lecture Notes in Computer Science","author":"Bernhard Sch\u00f6lkopf","year":"1997","unstructured":"B. Sch\u00f6lkopf, A.J. Smola, K. M\u00fcller, Kernel principal component analysis, in The International Conference on Artificial Neural Networks (ICANN), pp. 583\u2013588 (1997)"},{"key":"9357_CR31","unstructured":"F. Stulp, O. Sigaud, Path integral policy improvement with covariance matrix adaptation, in Proceedings of the 29th International Conference on Machine Learning, ICML 2012, Edinburgh, Scotland, UK, June 26\u2013July 1 (2012)"},{"key":"9357_CR32","volume-title":"Reinforcement Learning: An Introduction","author":"R Sutton","year":"1998","unstructured":"R. Sutton, A. Barto, Reinforcement Learning: An Introduction (Cambridge University Press, Cambridge, 1998)"},{"key":"9357_CR33","unstructured":"R.S. Sutton, D.A. McAllester, S.P. Singh, Y. Mansour, Policy gradient methods for reinforcement learning with function approximation, in Conference on Neural Information Processing Systems (NIPS), pp. 1057\u20131063 (1999)"},{"issue":"4","key":"9357_CR34","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1145\/2010324.1964953","volume":"30","author":"J Tan","year":"2011","unstructured":"J. Tan, Y. Gu, G. Turk, C.K. Liu, Articulated swimming creatures. ACM Trans. Graph. 30(4), 58 (2011)","journal-title":"ACM Trans. Graph."},{"key":"9357_CR35","unstructured":"M. Toussaint, Newton methods for k-order Markov constrained motion problems. CoRR \n                    arXiv:abs\/1407.0414\n                    \n                   (2014)"},{"key":"9357_CR36","doi-asserted-by":"publisher","first-page":"49089","DOI":"10.1109\/ACCESS.2018.2854283","volume":"6","author":"LP Tuyen","year":"2018","unstructured":"L.P. Tuyen, N.A. Vien, T. Chung, A deep hierarchical reinforcement learning algorithm in partially observable markov decision processes. IEEE Access 6, 49089\u201349102 (2018)","journal-title":"IEEE Access"},{"key":"9357_CR37","doi-asserted-by":"crossref","unstructured":"M. Ulbrich, Optimization methods in Banach spaces, in Optimization with PDE Constraints, ed. by Y. Borenstein,  A. Moraglio, pp. 97\u2013156 (Springer, Berlin, 2009)","DOI":"10.1007\/978-1-4020-8839-1_2"},{"key":"9357_CR38","unstructured":"H. van Hoof, J. Peters, G. Neumann, Learning of non-parametric control policies with high-dimensional state features, in Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics, AISTATS 2015, San Diego, California, USA, May 9\u201312 (2015)"},{"key":"9357_CR39","unstructured":"N.A. Vien, V.-H. Dang, T. Chung, A covariance matrix adaptation evolution strategy for direct policy search in reproducing kernel Hilbert space, in The 9th Asian Conference on Machine Learning (ACML) (2017)"},{"key":"9357_CR40","unstructured":"N.A. Vien, P. Englert, M. Toussaint, Policy search in reproducing kernel Hilbert space, in International Joint Conferences on Artificial Intelligence (IJCAI), pp. 2089\u20132096 (2016)"},{"issue":"9","key":"9357_CR41","doi-asserted-by":"publisher","first-page":"1671","DOI":"10.1016\/j.ins.2011.01.001","volume":"181","author":"NA Vien","year":"2011","unstructured":"N.A. Vien, H. Yu, T. Chung, Hessian matrix distribution for bayesian policy gradient reinforcement learning. Inf. Sci. 181(9), 1671\u20131685 (2011)","journal-title":"Inf. Sci."},{"issue":"1\u20133","key":"9357_CR42","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1023\/A:1013955821559","volume":"48","author":"P Vincent","year":"2002","unstructured":"P. Vincent, Y. Bengio, Kernel matching pursuit. Mach. Learn. 48(1\u20133), 165\u2013187 (2002)","journal-title":"Mach. Learn."},{"issue":"4","key":"9357_CR43","first-page":"25:1","volume":"31","author":"JM Wang","year":"2012","unstructured":"J.M. Wang, S.R. Hamner, S.L. Delp, V. Koltun, Optimizing locomotion controllers using biologically-based actuators and objectives. ACM Trans. Graph. 31(4), 25:1\u201325:11 (2012)","journal-title":"ACM Trans. Graph."},{"issue":"1","key":"9357_CR44","first-page":"949","volume":"15","author":"D Wierstra","year":"2014","unstructured":"D. Wierstra, T. Schaul, T. Glasmachers, Y. Sun, J. Peters, J. Schmidhuber, Natural evolution strategies. J. Mach. Learn. Res. 15(1), 949\u2013980 (2014)","journal-title":"J. Mach. Learn. Res."},{"issue":"3\u20134","key":"9357_CR45","first-page":"229","volume":"8","author":"RJ Williams","year":"1992","unstructured":"R.J. Williams, Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3\u20134), 229\u2013256 (1992)","journal-title":"Mach. Learn."},{"issue":"4","key":"9357_CR46","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1109\/TNN.2007.899161","volume":"18","author":"X Xu","year":"2007","unstructured":"X. Xu, D. Hu, X. Lu, Kernel-based least squares policy iteration for reinforcement learning. IEEE Trans. Neural Netw. 18(4), 973\u2013992 (2007)","journal-title":"IEEE Trans. Neural Netw."}],"container-title":["Genetic Programming and Evolvable Machines"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10710-019-09357-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10710-019-09357-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10710-019-09357-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,6,17]],"date-time":"2020-06-17T23:31:39Z","timestamp":1592436699000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10710-019-09357-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6,19]]},"references-count":46,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["9357"],"URL":"https:\/\/doi.org\/10.1007\/s10710-019-09357-1","relation":{},"ISSN":["1389-2576","1573-7632"],"issn-type":[{"value":"1389-2576","type":"print"},{"value":"1573-7632","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,6,19]]},"assertion":[{"value":"22 August 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 May 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 June 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}