{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T06:35:33Z","timestamp":1768804533745,"version":"3.49.0"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T00:00:00Z","timestamp":1737590400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T00:00:00Z","timestamp":1737590400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Optim Theory Appl"],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1007\/s10957-024-02572-6","type":"journal-article","created":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T06:48:16Z","timestamp":1737614896000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["$$H^\\infty $$-Optimal Control via Game-Theoretic Differential Dynamic Programming and Gaussian Processes"],"prefix":"10.1007","volume":"204","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3524-4852","authenticated-orcid":false,"given":"Wei","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Theodore B.","family":"Trafalis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,23]]},"reference":[{"key":"2572_CR1","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Coates, A., Quigley, M., Ng, A.Y.: An application of reinforcement learning to aerobatic helicopter flight. In: Advances in Neural Information Processing Systems, vol.\u00a019, pp. 1\u20138. MIT Press, Vancouver, B.C., Canada (2007)","DOI":"10.7551\/mitpress\/7503.003.0006"},{"issue":"4","key":"2572_CR2","doi-asserted-by":"publisher","first-page":"924","DOI":"10.1109\/TSMCB.2008.926610","volume":"38","author":"C Atkeson","year":"2008","unstructured":"Atkeson, C., Stephens, B.: Random sampling of states in dynamic programming. IEEE Trans. Syst. Man Cybern. B Cybern. 38(4), 924\u2013929 (2008). https:\/\/doi.org\/10.1109\/TSMCB.2008.926610","journal-title":"IEEE Trans. Syst. Man Cybern. B Cybern."},{"key":"2572_CR3","volume-title":"H-infinity optimal control and related minimax design","author":"T Basar","year":"1995","unstructured":"Basar, T., Berhard, P.: H-infinity optimal control and related minimax design. Birkhauser, Boston (1995)"},{"key":"2572_CR4","volume-title":"Dynamic noncooperative game theory","author":"T Ba\u015far","year":"1999","unstructured":"Ba\u015far, T., Olsder, G.J.: Dynamic noncooperative game theory. SIAM, Philadelphia (1999)"},{"key":"2572_CR5","doi-asserted-by":"publisher","unstructured":"Berkenkamp, F., Schoellig, A.P.: Safe and robust learning control with gaussian processes. In: 2015 European Control Conference (ECC), pp. 2496\u20132501. IEEE (2015). https:\/\/doi.org\/10.1109\/ECC.2015.7330913","DOI":"10.1109\/ECC.2015.7330913"},{"key":"2572_CR6","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1007\/s00182-006-0030-9","volume":"34","author":"P Bettiol","year":"2006","unstructured":"Bettiol, P., Cardaliaguet, P., Quincampoix, M.: Zero-sum state constrained differential games: existence of value for bolza problem. Internat. J. Game Theory 34, 495\u2013527 (2006)","journal-title":"Internat. J. Game Theory"},{"key":"2572_CR7","doi-asserted-by":"publisher","unstructured":"Book, W.J.: Modeling design, and control of flexible manipulator arms: a tutorial review. In: Proceedings of the 29th IEEE Conference on Decision and Control, pp. 500\u2013506. IEEE, Honolulu, Hawaii (1990). https:\/\/doi.org\/10.1109\/CDC.1990.203648","DOI":"10.1109\/CDC.1990.203648"},{"key":"2572_CR8","unstructured":"Deisenroth, M., Rasmussen, C.E.: Pilco: A model-based and data-efficient approach to policy search. In: Proceedings of the 28th International Conference on Machine Learning (ICML-11), pp. 465\u2013472. Omnipress (2011)"},{"key":"2572_CR9","doi-asserted-by":"publisher","unstructured":"Deisenroth, M.P., Peters, J., Rasmussen, C.E.: Approximate dynamic programming with gaussian processes. In: 2008 American Control Conference, pp. 4480\u20134485. IEEE (2008). https:\/\/doi.org\/10.1109\/ACC.2008.4587201","DOI":"10.1109\/ACC.2008.4587201"},{"issue":"8","key":"2572_CR10","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1109\/9.29425","volume":"34","author":"JC Doyle","year":"1989","unstructured":"Doyle, J.C., Glover, K., Khargonekar, P.P., Francis, B.A.: State-space solutions to standard H$$_2$$ and H$$_\\infty $$ control problems. IEEE Trans. Autom. Control 34(8), 831\u2013847 (1989). https:\/\/doi.org\/10.1109\/9.29425","journal-title":"IEEE Trans. Autom. Control"},{"key":"2572_CR11","doi-asserted-by":"publisher","first-page":"2093","DOI":"10.1007\/s00521-012-1156-2","volume":"23","author":"S Effati","year":"2013","unstructured":"Effati, S., Pakdaman, M.: Optimal control problem via neural networks. Neural Comput. Appl. 23, 2093\u20132100 (2013)","journal-title":"Neural Comput. Appl."},{"key":"2572_CR12","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2011.VII.010","author":"T Erez","year":"2012","unstructured":"Erez, T., Tassa, Y., Todorov, E.: Infinite-horizon model predictive control for periodic tasks with contacts. Robot. Sci. Syst. VII (2012). https:\/\/doi.org\/10.15607\/RSS.2011.VII.010","journal-title":"Robot. Sci. Syst. VII"},{"key":"2572_CR13","volume-title":"Dynamics of atmospheric fight","author":"B Etkin","year":"2012","unstructured":"Etkin, B.: Dynamics of atmospheric fight. Courier Corporation, North Chelmsford (2012)"},{"issue":"1","key":"2572_CR14","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1016\/0022-247X(61)90009-9","volume":"3","author":"WH Fleming","year":"1961","unstructured":"Fleming, W.H.: The convergence problem for differential games. J. Math. Anal. Appl. 3(1), 102\u2013116 (1961)","journal-title":"J. Math. Anal. Appl."},{"key":"2572_CR15","unstructured":"Heinonen, M., Mannerstr\u00f6m, H., Rousu, J., Kaski, S., L\u00e4hdesm\u00e4ki, H.: Non-stationary Gaussian process regression with hamiltonian monte carlo. In: Artificial Intelligence and Statistics, pp. 732\u2013740. PMLR (2016)"},{"key":"2572_CR16","unstructured":"Isaacs, R.: Differential Games: A Mathematical Theory with Applications to Warfare and Pursuit, Control and Optimization, Courier Dover Publications, Mineola, NY (1999)"},{"key":"2572_CR17","volume-title":"Differential dynamic programming","author":"DH Jacobson","year":"1970","unstructured":"Jacobson, D.H., Mayne, D.Q.: Differential dynamic programming. American Elsevier Pub. Co., New York (1970)"},{"issue":"4","key":"2572_CR18","doi-asserted-by":"publisher","first-page":"1342","DOI":"10.1137\/S0363012994273337","volume":"34","author":"MR James","year":"1996","unstructured":"James, M.R., Baras, J.S.: Partially observed differential games, infinite-dimensional Hamilton-Jacobi-Isaacs equations, and nonlinear $$h_\\infty $$ control. SIAM J. Control. Optim. 34(4), 1342\u20131364 (1996)","journal-title":"SIAM J. Control. Optim."},{"key":"2572_CR19","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/10187.001.0001","volume-title":"Decision making under uncertainty: theory and application","author":"MJ Kochenderfer","year":"2015","unstructured":"Kochenderfer, M.J.: Decision making under uncertainty: theory and application. MIT press, Cambridge (2015)"},{"key":"2572_CR20","doi-asserted-by":"publisher","unstructured":"Kocijan, J., Murray-Smith, R., Rasmussen, C.E., Girard, A.: Gaussian process model based predictive control. In: Proceedings of the 2004 American Control Conference, vol.\u00a03, pp. 2214\u20132219. IEEE (2004). https:\/\/doi.org\/10.23919\/ACC.2004.1383790","DOI":"10.23919\/ACC.2004.1383790"},{"key":"2572_CR21","unstructured":"Kokolakis, N.M.T., Vamvoudakis, K.G.: Safety-aware pursuit-evasion games in unknown environments using gaussian processes and finite-time convergent reinforcement learning. IEEE Transactions on Neural Networks and Learning Systems (2022)"},{"issue":"6","key":"2572_CR22","doi-asserted-by":"publisher","first-page":"692","DOI":"10.1109\/9.86943","volume":"36","author":"LZ Liao","year":"1991","unstructured":"Liao, L.Z., Shoemaker, C.A.: Convergence in unconstrained discrete-time differential dynamic programming. IEEE Trans. Autom. Control 36(6), 692\u2013706 (1991). https:\/\/doi.org\/10.1109\/9.86943","journal-title":"IEEE Trans. Autom. Control"},{"issue":"2","key":"2572_CR23","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1137\/0330017","volume":"30","author":"DJ Limebeer","year":"1992","unstructured":"Limebeer, D.J., Anderson, B.D., Khargonekar, P.P., Green, M.: A game theoretic approach to $$h^{\\infty }$$ control for time-varying systems. SIAM J. Control. Optim. 30(2), 262\u2013283 (1992)","journal-title":"SIAM J. Control. Optim."},{"issue":"1","key":"2572_CR24","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1080\/00207176608921369","volume":"3","author":"D Mayne","year":"1966","unstructured":"Mayne, D.: A second-order gradient method for determining optimal trajectories of non-linear discrete-time systems. Int. J. Control 3(1), 85\u201395 (1966). https:\/\/doi.org\/10.1080\/00207176608921369","journal-title":"Int. J. Control"},{"key":"2572_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2023.112340","volume":"490","author":"R Meng","year":"2023","unstructured":"Meng, R., Yang, X.: Sparse gaussian processes for solving nonlinear PDEs. J. Comput. Phys. 490, 112340 (2023)","journal-title":"J. Comput. Phys."},{"issue":"3","key":"2572_CR26","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1109\/MRA.2010.937855","volume":"17","author":"N Michael","year":"2010","unstructured":"Michael, N., Mellinger, D., Lindsey, Q., Kumar, V.: The GRASP multiple micro-UAV testbed. IEEE Robot. Autom. Mag. 17(3), 56\u201365 (2010)","journal-title":"IEEE Robot. Autom. Mag."},{"key":"2572_CR27","doi-asserted-by":"crossref","unstructured":"Mikolov, T., Karafi\u00e1t, M., Burget, L., \u010cernock\u1ef3, J., Khudanpur, S.: Recurrent neural network based language model. In: Eleventh Annual Conference of the International Speech Communication Association, pp. 1045\u20131048. ISCA (2010)","DOI":"10.21437\/Interspeech.2010-343"},{"key":"2572_CR28","doi-asserted-by":"publisher","unstructured":"Morimoto, J., Zeglin, G., Atkeson, C.: Minimax differential dynamic programming: application to a biped walking robot. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems, vol.\u00a02, pp. 1927\u20131932 (2003). https:\/\/doi.org\/10.1109\/IROS.2003.1248926","DOI":"10.1109\/IROS.2003.1248926"},{"issue":"1","key":"2572_CR29","doi-asserted-by":"publisher","first-page":"325","DOI":"10.3182\/20020721-6-ES-1901.01040","volume":"35","author":"R Murray-Smith","year":"2002","unstructured":"Murray-Smith, R., Sbarbaro, D.: Nonlinear adaptive control using nonparametric Gaussian process prior models. IFAC Proc. Vol. 35(1), 325\u2013330 (2002). https:\/\/doi.org\/10.3182\/20020721-6-ES-1901.01040","journal-title":"IFAC Proc. Vol."},{"key":"2572_CR30","doi-asserted-by":"crossref","unstructured":"\u00d8ksendal, B., Sulem, A.: Stochastic control of jump diffusions stochastic control. In: Applied Stochastic Control of Jump Diffusions, pp. 93\u2013155. Springer (2019)","DOI":"10.1007\/978-3-030-02781-0_5"},{"key":"2572_CR31","unstructured":"Paciorek, C., Schervish, M.: Nonstationary covariance functions for Gaussian process regression. Advances in neural information processing systems (2003)"},{"key":"2572_CR32","unstructured":"Pan, Y., Theodorou, E.: Probabilistic differential dynamic programming. In: Advances in Neural Information Processing Systems, pp. 1907\u20131915. Montreal, Canada (2014)"},{"issue":"5","key":"2572_CR33","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1109\/TAC.1987.1104609","volume":"32","author":"I Petersen","year":"1987","unstructured":"Petersen, I.: Disturbance attenuation and H$$^\\infty $$ optimization: a design method based on the algebraic Riccati equation. IEEE Trans. Autom. Control 32(5), 427\u2013429 (1987). https:\/\/doi.org\/10.1109\/TAC.1987.1104609","journal-title":"IEEE Trans. Autom. Control"},{"key":"2572_CR34","doi-asserted-by":"crossref","unstructured":"Rottmann, A., Burgard, W.: Learning non-stationary system dynamics online using Gaussian processes. In: Joint pattern recognition symposium, pp. 192\u2013201. Springer (2010)","DOI":"10.1007\/978-3-642-15986-2_20"},{"issue":"5","key":"2572_CR35","doi-asserted-by":"publisher","first-page":"1122","DOI":"10.2514\/1.G002357","volume":"41","author":"C S\u00e1nchez-S\u00e1nchez","year":"2018","unstructured":"S\u00e1nchez-S\u00e1nchez, C., Izzo, D.: Real-time optimal control via deep neural networks: study on landing problems. J. Guid. Control. Dyn. 41(5), 1122\u20131135 (2018)","journal-title":"J. Guid. Control. Dyn."},{"issue":"6","key":"2572_CR36","doi-asserted-by":"publisher","first-page":"568","DOI":"10.1109\/72.97934","volume":"2","author":"DF Specht","year":"1991","unstructured":"Specht, D.F., et al.: A general regression neural network. IEEE Trans. Neural Netw. 2(6), 568\u2013576 (1991). https:\/\/doi.org\/10.1109\/72.97934","journal-title":"IEEE Trans. Neural Netw."},{"issue":"12","key":"2572_CR37","doi-asserted-by":"publisher","first-page":"2568","DOI":"10.2514\/1.G003516","volume":"41","author":"W Sun","year":"2018","unstructured":"Sun, W., Pan, Y., Lim, J., Theodorou, E.A., Tsiotras, P.: Min-max differential dynamic programming: continuous and discrete time formulations. J. Guid. Control. Dyn. 41(12), 2568\u20132580 (2018). https:\/\/doi.org\/10.2514\/1.G003516","journal-title":"J. Guid. Control. Dyn."},{"key":"2572_CR38","doi-asserted-by":"publisher","unstructured":"Sun, W., Theodorou, E.A., Tsiotras, P.: Stochastic game theoretic trajectory optimization in continuous time. In: 55th Conference on Decision and Control (CDC), pp. 6167\u20136172. IEEE, Las Vegas, USA (2016). https:\/\/doi.org\/10.1109\/CDC.2016.7799217","DOI":"10.1109\/CDC.2016.7799217"},{"key":"2572_CR39","doi-asserted-by":"crossref","unstructured":"Sweriduk, G., Calise, A.: A differential game approach to the mixed h2\/h-infinity problem. In: Guidance, Navigation, and Control Conference, p. 3660 (1994)","DOI":"10.2514\/6.1994-3660"},{"key":"2572_CR40","unstructured":"Tassa, Y., Erez, T., Smart, W.D.: Receding horizon differential dynamic programming. In: Advances in Neural Information Processing Systems, pp. 1465\u20131472. Curran Associates, Inc., Vancouver, B.C., Canada (2008)"},{"key":"2572_CR41","doi-asserted-by":"publisher","unstructured":"Tassa, Y., Erez, T., Todorov, E.: Synthesis and stabilization of complex behaviors through online trajectory optimization. In: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4906\u20134913. IEEE (2012). https:\/\/doi.org\/10.1109\/IROS.2012.6386025","DOI":"10.1109\/IROS.2012.6386025"},{"key":"2572_CR42","doi-asserted-by":"publisher","unstructured":"Tassa, Y., Mansard, N., Todorov, E.: Control-limited differential dynamic programming. In: 2014 IEEE International Conference on Robotics and Automation (ICRA), pp. 1168\u20131175. Hong Kong, China (2014). https:\/\/doi.org\/10.1109\/ICRA.2014.6907001","DOI":"10.1109\/ICRA.2014.6907001"},{"issue":"4","key":"2572_CR43","doi-asserted-by":"publisher","first-page":"835","DOI":"10.1109\/TAC.2013.2289711","volume":"59","author":"H Tembine","year":"2013","unstructured":"Tembine, H., Zhu, Q., Ba\u015far, T.: Risk-sensitive mean-field games. IEEE Trans. Autom. Control 59(4), 835\u2013850 (2013)","journal-title":"IEEE Trans. Autom. Control"},{"key":"2572_CR44","doi-asserted-by":"publisher","unstructured":"Theodorou, E., Tassa, Y., Todorov, E.: Stochastic differential dynamic programming. In: American Control Conference, pp. 1125\u20131132. Baltimore, MD (2010). https:\/\/doi.org\/10.1109\/ACC.2010.5530971","DOI":"10.1109\/ACC.2010.5530971"},{"key":"2572_CR45","doi-asserted-by":"publisher","unstructured":"Todorov, E., Li, W.: A generalized iterative LQG method for locally-optimal feedback control of constrained nonlinear stochastic systems. In: Proceedings of the 2005 American Control Conference, pp. 300\u2013306. IEEE (2005). https:\/\/doi.org\/10.1109\/ACC.2005.1469949","DOI":"10.1109\/ACC.2005.1469949"},{"key":"2572_CR46","doi-asserted-by":"crossref","unstructured":"Van Den\u00a0Berg, J., Patil, S., Alterovitz, R.: Motion planning under uncertainty using differential dynamic programming in belief space. In: Robotics Research, pp. 473\u2013490. Springer (2017)","DOI":"10.1007\/978-3-319-29363-9_27"},{"issue":"6","key":"2572_CR47","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/9.256331","volume":"37","author":"AJ Van Der Schaft","year":"1992","unstructured":"Van Der Schaft, A.J.: $$\\text{ L}_2$$-gain analysis of nonlinear systems and nonlinear state-feedback H$$_\\infty $$ control. IEEE Trans. Autom. Control 37(6), 770\u2013784 (1992). https:\/\/doi.org\/10.1109\/9.256331","journal-title":"IEEE Trans. Autom. Control"},{"key":"2572_CR48","volume-title":"Biped locomotion: dynamics, stability, control and application","author":"M Vukobratovic","year":"2012","unstructured":"Vukobratovic, M., Borovac, B., Surla, D., Stokic, D.: Biped locomotion: dynamics, stability, control and application, vol. 7. Springer Science & Business Media, Cham (2012)"},{"issue":"1","key":"2572_CR49","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10462-021-10118-9","volume":"55","author":"D Wang","year":"2022","unstructured":"Wang, D., Ha, M., Zhao, M.: The intelligent critic framework for advanced optimal control. Artif. Intell. Rev. 55(1), 1\u201322 (2022)","journal-title":"Artif. Intell. Rev."},{"issue":"2","key":"2572_CR50","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1109\/MCI.2009.932261","volume":"4","author":"FY Wang","year":"2009","unstructured":"Wang, F.Y., Zhang, H., Liu, D.: Adaptive dynamic programming: an introduction. IEEE Comput. Intell. Mag. 4(2), 39\u201347 (2009)","journal-title":"IEEE Comput. Intell. Mag."},{"key":"2572_CR51","unstructured":"Wang, J., Hertzmann, A., Fleet, D.J.: Gaussian process dynamical models. Advances in neural information processing systems (2005)"},{"key":"2572_CR52","volume-title":"Gaussian processes for machine learning","author":"C Williams","year":"2006","unstructured":"Williams, C., Rasmussen, C.: Gaussian processes for machine learning. MIT Press, Cambridge (2006)"},{"key":"2572_CR53","volume-title":"Robust and optimal control","author":"K Zhou","year":"1996","unstructured":"Zhou, K., Doyle, J.C., Glover, K.: Robust and optimal control, vol. 40. Prentice Hall, New Jersey (1996)"}],"container-title":["Journal of Optimization Theory and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10957-024-02572-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10957-024-02572-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10957-024-02572-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T07:27:24Z","timestamp":1741073244000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10957-024-02572-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,23]]},"references-count":53,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["2572"],"URL":"https:\/\/doi.org\/10.1007\/s10957-024-02572-6","relation":{},"ISSN":["0022-3239","1573-2878"],"issn-type":[{"value":"0022-3239","type":"print"},{"value":"1573-2878","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,23]]},"assertion":[{"value":"27 March 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 November 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 January 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"40"}}