{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T05:54:51Z","timestamp":1725861291192},"reference-count":27,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"7","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Fundamentals"],"published-print":{"date-parts":[[2020,7,1]]},"DOI":"10.1587\/transfun.2019eap1154","type":"journal-article","created":{"date-parts":[[2020,6,30]],"date-time":"2020-06-30T18:11:48Z","timestamp":1593540708000},"page":"885-892","source":"Crossref","is-referenced-by-count":1,"title":["Control of Discrete-Time Chaotic Systems with Policy-Based Deep Reinforcement Learning"],"prefix":"10.1587","volume":"E103.A","author":[{"given":"Junya","family":"IKEMOTO","sequence":"first","affiliation":[{"name":"Graduate School of Engineering Science, Osaka University"}]},{"given":"Toshimitsu","family":"USHIO","sequence":"additional","affiliation":[{"name":"Graduate School of Engineering Science, Osaka University"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] E. Ott, C. Grebogi, and J.A. Yorke, \u201cControlling chaos,\u201d Phys. Rev. Lett., vol.64, no.11, pp.1196-1199, March 1990. 10.1103\/physrevlett.64.1196","DOI":"10.1103\/PhysRevLett.64.1196"},{"key":"2","doi-asserted-by":"publisher","unstructured":"[2] K. Pyragas, \u201cContinuous control of chaos by self-controlling feedback,\u201d Phys. Lett. A, vol.170, no.6, pp.421-428, Nov. 1992. 10.1016\/0375-9601(92)90745-8","DOI":"10.1016\/0375-9601(92)90745-8"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] T. Ushio, \u201cLimitation of delayed feedback control in nonlinear discrete-time systems,\u201d IEEE Trans. Circuits Syst. I, Fundam. Theory Appl., vol.43, no.9, pp.815-816, Sept. 1996. 10.1109\/81.536757","DOI":"10.1109\/81.536757"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] H. Nakajima, \u201cOn analytical properties of delayed feedback control of chaos,\u201d Phys. Lett. A, vol.232, no.3-4, pp.207-210, July 1997. 10.1016\/s0375-9601(97)00362-9","DOI":"10.1016\/S0375-9601(97)00362-9"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] K. Pyragas, \u201cControl of chaos via extended delay feedback,\u201d Phys. Lett. A, vol.206, no.5-6, pp.323-330, Oct. 1995. 10.1016\/0375-9601(95)00654-l","DOI":"10.1016\/0375-9601(95)00654-L"},{"key":"6","doi-asserted-by":"publisher","unstructured":"[6] S. Yamamoto, T. Hino, and T. Ushio, \u201cDynamic delayed feedback controllers for chaotic discrete-time systems,\u201d IEEE Trans. Circuits Syst. I, Fundam. Theory Appl., vol.48, no.6, pp.785-789, June 2001. 10.1109\/81.928162","DOI":"10.1109\/81.928162"},{"key":"7","doi-asserted-by":"publisher","unstructured":"[7] H. Nakajima and Y. Ueda, \u201cHalf-period delayed feedback control for dynamical systems with symmetries,\u201d Phys. Rev. E, vol.58, no.2, pp.1757-1763, Aug. 1998. 10.1103\/physreve.58.1757","DOI":"10.1103\/PhysRevE.58.1757"},{"key":"8","doi-asserted-by":"publisher","unstructured":"[8] T. Ushio and S. Yamamoto, \u201cPrediction-based control of chaos,\u201d Phys. Lett. A, vol.264, no.1, pp.30-35, Dec. 1999. 10.1016\/s0375-9601(99)00782-3","DOI":"10.1016\/S0375-9601(99)00782-3"},{"key":"9","unstructured":"[9] H. Nakajima and Y. Ueda, \u201cAutomatic adjustment of feedback gain in controlling chaos by Pyragas's method,\u201d IEICE Technical Report, NLP95-32, Nov. 1995."},{"key":"10","unstructured":"[10] H. Nakajima, H. Ito, and Y. Ueda, \u201cAutomatic adjustment of delay time and feedback gain in delayed feedback control of chaos,\u201d IEICE Trans. Fundamentals, vol.E80-A, no.9, pp.1554-1559, Sept. 1997."},{"key":"11","doi-asserted-by":"publisher","unstructured":"[11] A. Boukabou and N. Mansouri, \u201cNeural predictive control of unknown chaotic systems,\u201d Nonlinear Analysis: Modeling and Control, vol.10, no.2, pp.95-106, Jan. 2005. 10.15388\/na.2005.10.2.15125","DOI":"10.15388\/NA.2005.10.2.15125"},{"key":"12","doi-asserted-by":"publisher","unstructured":"[12] L. Shen, M. Wang, W. Liu, and G. Sun, \u201cPrediction based chaos control via a new neural network,\u201d Phys. Lett. A, vol.372, no.46, pp.6916-6921, Nov. 2008. 10.1016\/j.physleta.2008.10.012","DOI":"10.1016\/j.physleta.2008.10.012"},{"key":"13","unstructured":"[13] R.S. Sutton and A.G. Barto, Reinforcement Learning, 2nd ed., MIT Press, 2018."},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] R. Der and M. Herrmann, \u201cQ-learning chaos controller,\u201d Proc. IEEE International Conference on Neural Networks, vol.4, pp.2472-2475, July 1994. 10.1109\/icnn.1994.374608","DOI":"10.1109\/ICNN.1994.374608"},{"key":"15","doi-asserted-by":"publisher","unstructured":"[15] S. Gadaleta and G. Dangelmayr, \u201cOptimal chaos control through reinforcement learning,\u201d Chaos: An Interdisciplinary Journal of Nonlinear Science, vol.9, no.3, pp.775-788, Sept. 1999. 10.1063\/1.166451","DOI":"10.1063\/1.166451"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] S. Gadaleta and G. Dangelmayr, \u201cReinforcement learning chaos control using value sensitive vector-quantization,\u201d Proc. IEEE International Joint Conference on Neural Networks, vol.2, pp.996-1001, July 2001. 10.1109\/ijcnn.2001.939496","DOI":"10.1109\/IJCNN.2001.939496"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] B. Fritzke, \u201cA growing neural gas network learns topologies,\u201d Proc. 7th NIPS, pp.625-632, Jan. 1994.","DOI":"10.1016\/0893-6080(94)90091-4"},{"key":"18","doi-asserted-by":"publisher","unstructured":"[18] V. Mnih, K. Kavukcuoglu, D. Silver, A.A. Rusu, J. Veness, M.G. Bellemare, A. Graves, M. Riedmiller, A.K. Fidjeland, G. Ostrovski, S. Petersen, C. Beattie, A. Sadik, I. Antonoglou, H. King, D. Kumaran, D. Wierstra, S. Legg, and D. Hassabis, \u201cHuman-level control through deep reinforcement learning,\u201d Nature, vol.518, pp.529-533, Feb. 2015. 10.1038\/nature14236","DOI":"10.1038\/nature14236"},{"key":"19","doi-asserted-by":"publisher","unstructured":"[19] D. Silver, A. Huang, C.J. Maddison, A. Guez, L. Sifre, G. van den Driessche, J. Schrittwieser, I. Antonoglou, V. Panneershelvam, M. Lanctot, S. Dieleman, D. Grewe, J. Nham, N. Kalchbrenner, I. Sutskever, T. Lillicrap, M. Leach, K. Kavukcuoglu, T. Graepel, and D. Hassabis, \u201cMastering the game Go with deep neural networks and tree search,\u201d Nature, vol.529, pp.484-489, Jan. 2016. 10.1038\/nature16961","DOI":"10.1038\/nature16961"},{"key":"20","unstructured":"[20] N. Masuda and T. Ushio, \u201cControl of nonholonomic vehicle system using hierarchical deep reinforcement learning,\u201d Proc. NOLTA 2017, pp.26-29, Dec. 2017."},{"key":"21","unstructured":"[21] T.P. Lillicrap, J.J. Hunt, A. Pritzel, N. Heess, T. Erez, Y. Tassa, D. Silver, and D. Wierstra, \u201cContinuous control with deep reinforcement learning,\u201d arXiv preprint, arXiv:1509.02971, Sept. 2015."},{"key":"22","unstructured":"[22] M.A. Bucci, O. Semeraro, A. Allauzen, G. Wisniewski, L. Cordier, and L. Mathelin, \u201cControl of chaotic systems by deep reinforcement learning,\u201d arXiv preprint, arXiv:1906.07672, June 2019."},{"key":"23","doi-asserted-by":"publisher","unstructured":"[23] K. Arulkumaran, M.P. Deisenroth, M. Brundage, and A.A. Bharath, \u201cDeep reinforcement learning: A brief survey,\u201d IEEE Signal Process. Mag., vol.34, no.6, pp.26-38, Nov. 2017. 10.1109\/msp.2017.2743240","DOI":"10.1109\/MSP.2017.2743240"},{"key":"24","unstructured":"[24] R.S. Sutton, D. McAllester, S. Singh, and Y. Mansour, \u201cPolicy gradient method for reinforcement learning with function approximation,\u201d Proc. 12th NIPS, pp.1057-1063, Nov. 1999."},{"key":"25","unstructured":"[25] D. Silver, G. Lever, N. Heess, T. Degris, D Wierstra, and M. Riedmiller, \u201cDeterministic policy gradient algorithms,\u201d Proc. 31st ICML, vol.32, pp.387-395, June 2014."},{"key":"26","unstructured":"[26] D.P. Kingma and J. Ba, \u201cAdam: A method for stochastic optimization,\u201d arXiv preprint, arXiv:1412.6980, Dec. 2014."},{"key":"27","doi-asserted-by":"publisher","unstructured":"[27] G.E. Uhlenbeck and L.S. Ornstein, \u201cOn the theory of the Brownian motion,\u201d Phys. Rev., vol.36, no.5, pp.823-841, Sept. 1930. 10.1103\/physrev.36.823","DOI":"10.1103\/PhysRev.36.823"}],"container-title":["IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transfun\/E103.A\/7\/E103.A_2019EAP1154\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T19:05:44Z","timestamp":1723143944000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transfun\/E103.A\/7\/E103.A_2019EAP1154\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,1]]},"references-count":27,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2020]]}},"URL":"https:\/\/doi.org\/10.1587\/transfun.2019eap1154","relation":{},"ISSN":["0916-8508","1745-1337"],"issn-type":[{"type":"print","value":"0916-8508"},{"type":"electronic","value":"1745-1337"}],"subject":[],"published":{"date-parts":[[2020,7,1]]}}}