{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T07:01:03Z","timestamp":1742972463761,"version":"3.40.3"},"publisher-location":"Cham","reference-count":14,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319466743"},{"type":"electronic","value":"9783319466750"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","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":[[2016]]},"DOI":"10.1007\/978-3-319-46675-0_24","type":"book-chapter","created":{"date-parts":[[2016,9,28]],"date-time":"2016-09-28T09:55:47Z","timestamp":1475056547000},"page":"211-220","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Kernel-Based Sarsa( $$\\lambda $$ ) Algorithm with Clustering-Based Sample Sparsification"],"prefix":"10.1007","author":[{"given":"Haijun","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchen","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwei","family":"Zhai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cijia","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,9,29]]},"reference":[{"key":"24_CR1","volume-title":"Dynamic Programming","author":"R Bellman","year":"1957","unstructured":"Bellman, R.: Dynamic Programming. Princeton University Press, Princeton (1957)"},{"issue":"12","key":"24_CR2","doi-asserted-by":"publisher","first-page":"1944","DOI":"10.1109\/TNNLS.2013.2270561","volume":"24","author":"X Chen","year":"2013","unstructured":"Chen, X., Gao, Y., Wang, R.: Online selective kernel-based temporal difference learning. IEEE Trans. Neural Netw. Learn. Syst. 24(12), 1944\u20131956 (2013)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"8","key":"24_CR3","doi-asserted-by":"publisher","first-page":"2275","DOI":"10.1109\/TSP.2004.830985","volume":"52","author":"Y Engel","year":"2004","unstructured":"Engel, Y., Mannor, S., Meir, R.: The kernel recursive least-squares algorithm. IEEE Trans. Signal Process. 52(8), 2275\u20132285 (2004)","journal-title":"IEEE Trans. Signal Process."},{"issue":"2","key":"24_CR4","first-page":"503","volume":"6","author":"D Ernst","year":"2005","unstructured":"Ernst, D., Geurts, P., Wehenkel, L.: Tree-based batch mode reinforcement learning. J. Mach. Learn. Res. 6(2), 503\u2013556 (2005)","journal-title":"J. Mach. Learn. Res."},{"key":"24_CR5","unstructured":"Fan-Cheng, M., Ya-Ping, D.: Reinforcement learning adaptive control for upper limb rehabilitation robot based on fuzzy neural network. In: Control Conference (CCC), pp. 5157\u20135161 (2012)"},{"issue":"2\u20133","key":"24_CR6","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1023\/A:1017928328829","volume":"49","author":"D Ormoneit","year":"2002","unstructured":"Ormoneit, D., Sen, \u015a.: Kernel-based reinforcement learning. Mach. Learn. 49(2\u20133), 161\u2013178 (2002)","journal-title":"Mach. Learn."},{"key":"24_CR7","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"ML Puterman","year":"2014","unstructured":"Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. Wiley, New York (2014)"},{"key":"24_CR8","unstructured":"van Seijen, H., Sutton, R.S.: True online TD(\n                      \n                        \n                      \n                      $$\\lambda $$\n                    ). In: Proceedings of the 31st International Conference on Machine Learning (ICML), pp. 692\u2013700 (2014)"},{"issue":"7587","key":"24_CR9","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., Huang, A., Maddison, C.J., Guez, A., Sifre, L., Driessche, G.V.D., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016)","journal-title":"Nature"},{"key":"24_CR10","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"issue":"5","key":"24_CR11","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1109\/9.580874","volume":"42","author":"JN Tsitsiklis","year":"1996","unstructured":"Tsitsiklis, J.N., Van Roy, B.: An analysis of temporal-difference learning with function approximation. IEEE Trans. Autom. Control 42(5), 674\u2013690 (1996)","journal-title":"IEEE Trans. Autom. Control"},{"issue":"4","key":"24_CR12","doi-asserted-by":"publisher","first-page":"875","DOI":"10.1109\/TNN.2005.849817","volume":"16","author":"T Xiaoyang","year":"2005","unstructured":"Xiaoyang, T., Songcan, C., Zhi-Hua, Z., Fuyan, Z.: Recognizing partially occluded, expression variant faces from single training image per person with som and soft \n                      \n                        \n                      \n                      $$k$$\n                    -NN ensemble. IEEE Trans. Neural Netw. 16(4), 875\u2013886 (2005)","journal-title":"IEEE Trans. Neural Netw."},{"issue":"12","key":"24_CR13","doi-asserted-by":"publisher","first-page":"2613","DOI":"10.1109\/TCYB.2014.2311824","volume":"44","author":"X Xu","year":"2014","unstructured":"Xu, X., Huang, Z., Graves, D., Pedrycz, W.: A clustering-based graph Laplacian framework for value function approximation in reinforcement learning. IEEE Trans. Cybern. 44(12), 2613\u20132625 (2014)","journal-title":"IEEE Trans. Cybern."},{"issue":"4","key":"24_CR14","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1109\/TNN.2007.899161","volume":"18","author":"X Xu","year":"2007","unstructured":"Xu, X., Hu, D., Lu, X.: 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":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-46675-0_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T01:20:59Z","timestamp":1558315259000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46675-0_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319466743","9783319466750"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46675-0_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"29 September 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 October 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}