{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T22:50:13Z","timestamp":1725490213483},"publisher-location":"Berlin, Heidelberg","reference-count":11,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540747680"},{"type":"electronic","value":"9783540747697"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-74769-7_22","type":"book-chapter","created":{"date-parts":[[2007,8,24]],"date-time":"2007-08-24T15:27:53Z","timestamp":1187969273000},"page":"191-204","source":"Crossref","is-referenced-by-count":0,"title":["Reinforcement Learning Algorithms Based on mGA and EA with Policy Iterations"],"prefix":"10.1007","author":[{"given":"Changming","family":"Yin","sequence":"first","affiliation":[]},{"given":"Liyun","family":"Li","sequence":"additional","affiliation":[]},{"given":"Hanxing","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"issue":"11","key":"22_CR1","doi-asserted-by":"publisher","first-page":"1804","DOI":"10.1109\/TAC.2005.858644","volume":"50","author":"H.S. Chang","year":"2005","unstructured":"Chang, H.S., Lee, H-G., Fu, M., Marcus, S.I.: Evolutionary Policy Iteration for Solving Markov Decision Processes. IEEE Trans. on Automatic Control\u00a050(11), 1804\u20131808 (2005)","journal-title":"IEEE Trans. on Automatic Control"},{"key":"22_CR2","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1613\/jair.548","volume":"11","author":"E.M. David","year":"1999","unstructured":"David, E.M., Alan, C.S., John, J.G.: Evolutionary Algorithms for Reinforcement Learning. Journal of Artificial Intelligence Research\u00a011, 199\u2013229 (1999)","journal-title":"Journal of Artificial Intelligence Research"},{"issue":"6","key":"22_CR3","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1287\/opre.51.6.850.24925","volume":"51","author":"D.P. Farias De","year":"2003","unstructured":"De Farias, D.P., Van Roy, B.: The linear programming approach to approximate dynamic programming. Operations Research\u00a051(6), 850\u2013865 (2003)","journal-title":"Operations Research"},{"key":"22_CR4","unstructured":"Hu, J., Fu, M.C., Ramezani, V., Marcus, S.I.: An Evolutionary Random Search Algorithm for Solving Markov Decision Processes. TR2005-3, Institute for Systems Research, University of Maryland (2005)"},{"key":"22_CR5","volume-title":"Genetic Algorithms and Soft Computing","author":"F. Hoffmann","year":"1996","unstructured":"Hoffmann, F., Pfister, G.: Learning of a Fuzzy Control Rule Base Using Messy Genetic Algorithms. In: Herrera, F., Verdegay, J.L. (eds.) Genetic Algorithms and Soft Computing, Physica-Verlag, Heidelberg (1996)"},{"key":"22_CR6","first-page":"191","volume-title":"Proceedings of the Fifth International Conference on Genetic Algorithms","author":"L.D. Merkle","year":"1993","unstructured":"Merkle, L.D., Lamont, G.B.: Comparison of parallel messy genetic algorithm data distribution strategies. In: Forrest, S. (ed.) Proceedings of the Fifth International Conference on Genetic Algorithms, pp. 191\u2013198. Morgan Kaufmann, San Mateo, CA (1993)"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"McMahan, H.B., Likhachev, M., Gordon, G.J.: Bounded Real-Time Dynamic Programming:RTDP with monotone upper bounds and performance guartees. In: Proceedings of the 22nd International Conference on Machine Learning, Bonn, Germany (2005)","DOI":"10.1145\/1102351.1102423"},{"key":"22_CR8","first-page":"274","volume-title":"Proceedings of the IEEE International Conference on Industrial Technology","author":"M.M.M. Chowdhury","year":"1996","unstructured":"Chowdhury, M.M.M., Li, Y.: Messy genetic algorithm-based new learning-method for structurally optimized neurofuzzy controllers. In: Proceedings of the IEEE International Conference on Industrial Technology, Shanghai, China, pp. 274\u2013278. IEEE Computer Society Press, Los Alamitos (1996)"},{"key":"22_CR9","unstructured":"Dymek, A.: An examination of hypercube implementations of genetic algorithms. umt,Air Force Institute of Technology, Wright-Patterson Air Force Base, OH (1992)"},{"key":"22_CR10","volume-title":"Reinforcement Learning: An Introduction","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge MA (1998)"},{"key":"22_CR11","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1613\/jair.946","volume":"16","author":"X. Xu","year":"2002","unstructured":"Xu, X., He, H., Hu, D.: Efficient Reinforcement Learning Using Recursive Least-Squares Methods. Journal of Artificial Intelligence Research\u00a016, 259\u2013292 (2002)","journal-title":"Journal of Artificial Intelligence Research"}],"container-title":["Lecture Notes in Computer Science","Bio-Inspired Computational Intelligence and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-74769-7_22.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T10:36:57Z","timestamp":1619519817000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-74769-7_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540747680","9783540747697"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-74769-7_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[]}}