{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T17:48:59Z","timestamp":1761155339063},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2010,3,28]],"date-time":"2010-03-28T00:00:00Z","timestamp":1269734400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Soft Comput"],"published-print":{"date-parts":[[2011,6]]},"DOI":"10.1007\/s00500-010-0581-3","type":"journal-article","created":{"date-parts":[[2010,3,27]],"date-time":"2010-03-27T02:57:20Z","timestamp":1269658640000},"page":"1055-1070","source":"Crossref","is-referenced-by-count":16,"title":["Continuous-action reinforcement learning with fast policy search and adaptive basis function selection"],"prefix":"10.1007","volume":"15","author":[{"given":"Xin","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunming","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dewen","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2010,3,28]]},"reference":[{"key":"581_CR1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1162\/153244303768966085","volume":"3","author":"FR Bach","year":"2002","unstructured":"Bach FR, Jordan MI (2002) Kernel independent component analysis. J Mach Learn Res 3:1\u201348","journal-title":"J Mach Learn Res"},{"issue":"5","key":"581_CR2","first-page":"835","volume":"13","author":"AG Barto","year":"1983","unstructured":"Barto AG, Sutton RS, Anderson CW (1983) Neuronlike adaptive elements that can solve difficult learning control problems. IEEE Trans Syst Man Cybern 13(5):835\u2013846","journal-title":"IEEE Trans Syst Man Cybern"},{"key":"581_CR3","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1613\/jair.806","volume":"15","author":"J Baxter","year":"2001","unstructured":"Baxter J, Bartlett PL (2001) Infinite-horizon policy-gradient estimation. J Artif Intell Res 15:319\u2013350","journal-title":"J Artif Intell Res"},{"key":"581_CR4","volume-title":"Neurodynamic programming","author":"DP Bertsekas","year":"1996","unstructured":"Bertsekas DP, Tsitsiklis JN (1996) Neurodynamic programming. Athena Scientific, Belmont"},{"issue":"2\u20133","key":"581_CR5","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1023\/A:1017936530646","volume":"49","author":"J Boyan","year":"2002","unstructured":"Boyan J (2002) Technical update: least-squares temporal difference learning. Mach Learn 49(2\u20133):233\u2013246","journal-title":"Mach Learn"},{"issue":"2\u20133","key":"581_CR6","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1023\/A:1007518724497","volume":"33","author":"RH Crites","year":"1998","unstructured":"Crites RH, Barto AG (1998) Elevator group control using multiple reinforcement learning agents. Mach Learn 33(2\u20133):235\u2013262","journal-title":"Mach Learn"},{"key":"581_CR7","first-page":"341","volume":"8","author":"P Dayan","year":"1992","unstructured":"Dayan P (1992) The convergence of TD(\u03bb) for general \u03bb. Mach Learn 8:341\u2013362","journal-title":"Mach Learn"},{"key":"581_CR8","first-page":"295","volume":"14","author":"P Dayan","year":"1994","unstructured":"Dayan P, Sejnowski TJ (1994) TD(\u03bb) converges with probability 1. Mach Learn 14:295\u2013301","journal-title":"Mach Learn"},{"issue":"8","key":"581_CR9","doi-asserted-by":"crossref","first-page":"2275","DOI":"10.1109\/TSP.2004.830985","volume":"52","author":"Y Engel","year":"2004","unstructured":"Engel Y, Mannor S, Meir R (2004) The kernel recursive least-squares algorithm. IEEE Trans Signal Process 52(8):2275\u20132285","journal-title":"IEEE Trans Signal Process"},{"key":"581_CR10","unstructured":"Hasselt HV, Wiering M (2007) Reinforcement learning in continuous action spaces. In: 2007 IEEE symposium on approximate dynamic programming and reinforcement learning, pp 272\u2013279"},{"key":"581_CR11","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"LP Kaelbling","year":"1996","unstructured":"Kaelbling LP, Littman ML, Moore AW (1996) Reinforcement learning: a survey. J Artif Intell Res 4:237\u2013285","journal-title":"J Artif Intell Res"},{"key":"581_CR13","doi-asserted-by":"crossref","first-page":"1107","DOI":"10.1162\/jmlr.2003.4.6.1107","volume":"4","author":"MG Lagoudakis","year":"2003","unstructured":"Lagoudakis MG, Parr R (2003) Least-squares policy iteration. J Mach Learn Res 4:1107\u20131149","journal-title":"J Mach Learn Res"},{"key":"581_CR14","unstructured":"Lazaric A, Restelli M, Bonarini A (2008) Reinforcement learning in continuous action spaces through sequential Monte Carlo methods. In: Advances in neural information processing systems. MIT Press, Cambridge"},{"key":"581_CR15","first-page":"2169","volume":"8","author":"S Mahadevan","year":"2007","unstructured":"Mahadevan S, Maggioni M (2007) Proto-value functions: a Laplacian framework for learning representation and control in Markov decision processes. J Mach Learn Res 8:2169\u20132231","journal-title":"J Mach Learn Res"},{"issue":"2\/3","key":"581_CR16","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1023\/A:1017988514716","volume":"49","author":"JDR Millan","year":"2002","unstructured":"Millan JDR, Posenato D, Dedieu E (2002) Continuous-action q-learning. Mach Learn 49(2\/3):247\u2013265","journal-title":"Mach Learn"},{"issue":"5","key":"581_CR17","doi-asserted-by":"crossref","first-page":"997","DOI":"10.1109\/72.623201","volume":"8","author":"DV Prokhorov","year":"1997","unstructured":"Prokhorov DV, Wunsch DC (1997) Adaptive critic designs. IEEE Trans Neural Netw 8(5):997\u20131007","journal-title":"IEEE Trans Neural Netw"},{"key":"581_CR18","unstructured":"Rasmussen CE, Kuss M (2004) Gaussian processes in reinforcement learning. In: Thrun S, Saul LK, Sch\u00f6lkopf B (eds) Advances in neural information processing systems, vol 16. MIT Press, Cambridge, pp 751\u2013759"},{"key":"581_CR19","volume-title":"Learning with kernels","author":"B Sch\u00f6lkopf","year":"2002","unstructured":"Sch\u00f6lkopf B, Smola A (2002) Learning with kernels. MIT Press, Cambridge"},{"key":"581_CR20","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1023\/A:1007678930559","volume":"38","author":"SP Singh","year":"2000","unstructured":"Singh SP, Jaakkola T, Littman ML, Szepesvari C (2000) Convergence results for single-step on-policy reinforcement-learning algorithms. Mach Learn 38:287\u2013308","journal-title":"Mach Learn"},{"issue":"1","key":"581_CR21","first-page":"9","volume":"3","author":"R Sutton","year":"1988","unstructured":"Sutton R (1988) Learning to predict by the method of temporal differences. Mach Learn 3(1):9\u201344","journal-title":"Mach Learn"},{"key":"581_CR22","unstructured":"Sutton R (1996) Generalization in reinforcement learning: successful examples using sparse coarse coding. In: Advances in neural information processing systems, vol 8. MIT Press, Cambridge, pp 1038\u20131044"},{"key":"581_CR23","volume-title":"Reinforcement learning: an introduction","author":"R Sutton","year":"1998","unstructured":"Sutton R, Barto A (1998) Reinforcement learning: an introduction. MIT Press, Cambridge"},{"key":"581_CR24","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1162\/neco.1994.6.2.215","volume":"6","author":"G Tesauro","year":"1994","unstructured":"Tesauro G (1994) TD-Gammon, a self-teaching backgammon program, achieves master-level play. Neural Comput 6:215\u2013219","journal-title":"Neural Comput"},{"key":"581_CR25","first-page":"185","volume":"16","author":"JN Tsitsiklis","year":"1994","unstructured":"Tsitsiklis JN (1994) Asynchronous stochastic approximation and Q-learning. Mach Learn 16:185\u2013202","journal-title":"Mach Learn"},{"issue":"5","key":"581_CR26","doi-asserted-by":"crossref","first-page":"674","DOI":"10.1109\/9.580874","volume":"42","author":"JN Tsitsiklis","year":"1997","unstructured":"Tsitsiklis JN, Roy BV (1997) An analysis of temporal difference learning with function approximation. IEEE Trans Autom Control 42(5):674\u2013690","journal-title":"IEEE Trans Autom Control"},{"key":"581_CR27","first-page":"279","volume":"8","author":"CJCH Watkins","year":"1992","unstructured":"Watkins CJCH, Dayan P (1992) Q-learning. Mach Learn 8:279\u2013292","journal-title":"Mach Learn"},{"key":"581_CR28","first-page":"877","volume":"7","author":"S Whiteson","year":"2006","unstructured":"Whiteson S, Stone P (2006) Evolutionary function approximation for reinforcement learning. J Mach Learn Res 7:877\u2013917","journal-title":"J Mach Learn Res"},{"key":"581_CR29","first-page":"229","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams RJ (1992) Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach Learn 8:229\u2013256","journal-title":"Mach Learn"},{"issue":"4","key":"581_CR30","doi-asserted-by":"crossref","first-page":"973","DOI":"10.1109\/TNN.2007.899161","volume":"18","author":"X Xu","year":"2007","unstructured":"Xu X, Hu DW, Lu XC (2007) Kernel-based least-squares policy iteration for reinforcement learning. IEEE Trans Neural Netw 18(4):973\u2013997","journal-title":"IEEE Trans Neural Netw"},{"key":"581_CR31","unstructured":"Zhang W, Dietterich T (1995) A reinforcement learning approach to job-shop scheduling. In: Proceedings of the fourteenth international joint conference on artificial intelligence. Morgan Kaufmann, pp 1114\u20131120"}],"container-title":["Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-010-0581-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00500-010-0581-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-010-0581-3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,28]],"date-time":"2019-05-28T21:40:02Z","timestamp":1559079602000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00500-010-0581-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,3,28]]},"references-count":30,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2011,6]]}},"alternative-id":["581"],"URL":"https:\/\/doi.org\/10.1007\/s00500-010-0581-3","relation":{},"ISSN":["1432-7643","1433-7479"],"issn-type":[{"value":"1432-7643","type":"print"},{"value":"1433-7479","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,3,28]]}}}