{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T10:08:07Z","timestamp":1725703687921},"publisher-location":"Berlin, Heidelberg","reference-count":16,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642328909"},{"type":"electronic","value":"9783642328916"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-32891-6_10","type":"book-chapter","created":{"date-parts":[[2012,10,6]],"date-time":"2012-10-06T08:54:11Z","timestamp":1349513651000},"page":"58-67","source":"Crossref","is-referenced-by-count":1,"title":["Intelligent Inventory Control: Is Bootstrapping Worth Implementing?"],"prefix":"10.1007","author":[{"given":"Tatpong","family":"Katanyukul","sequence":"first","affiliation":[]},{"given":"Edwin K. P.","family":"Chong","sequence":"additional","affiliation":[]},{"given":"William S.","family":"Duff","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Baird, L.: Residual Algorithms: Reinforcement Learning with Function Approximation. In: Proceedings of the 12th International Conference on Machine Learning, pp. 30\u201337. Morgan Kaufmann (1995)","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"issue":"4-5","key":"10_CR2","doi-asserted-by":"publisher","first-page":"454","DOI":"10.1016\/j.artint.2007.08.001","volume":"172","author":"A.M.S. Barreto","year":"2008","unstructured":"Barreto, A.M.S., Anderson, C.W.: Restricted gradient-descent algorithm for value-function approximation in reinforcement learning. Artificial Intelligence\u00a0172(4-5), 454\u2013482 (2008)","journal-title":"Artificial Intelligence"},{"issue":"3","key":"10_CR3","doi-asserted-by":"publisher","first-page":"6520","DOI":"10.1016\/j.eswa.2008.07.036","volume":"36","author":"C. Jiang","year":"2009","unstructured":"Jiang, C., Sheng, Z.: Case-based reinforcement learning for dynamic inventory control in a multi-agent supply chain system. Expert Systems with Applications\u00a036(3), 6520\u20136526 (2009)","journal-title":"Expert Systems with Applications"},{"issue":"4","key":"10_CR4","doi-asserted-by":"publisher","first-page":"719","DOI":"10.1016\/j.cie.2011.01.007","volume":"60","author":"T. Katanyukul","year":"2011","unstructured":"Katanyukul, T., Duff, W.S., Chong, E.K.P.: Approximate dynamic programming for an inventory problem: Empirical comparison. Computers & Industrial Engineering\u00a060(4), 719\u2013743 (2011)","journal-title":"Computers & Industrial Engineering"},{"issue":"9-10","key":"10_CR5","doi-asserted-by":"publisher","first-page":"1184","DOI":"10.1007\/s00170-004-2069-8","volume":"26","author":"C.O. Kim","year":"2005","unstructured":"Kim, C.O., Jun, J., Baek, J.K., Smith, R.L., Kim, Y.D.: Adaptive inventory control models for supply chain management. International Journal of Advanced Manufacturing Technology\u00a026(9-10), 1184\u20131192 (2005)","journal-title":"International Journal of Advanced Manufacturing Technology"},{"issue":"1","key":"10_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10489-007-0038-2","volume":"28","author":"C.O. Kim","year":"2008","unstructured":"Kim, C.O., Kwon, I.H., Baek, J.G.: Asynchronous action-reward learning for nonstationary serial supply chain inventory control. Applied Intelligence\u00a028(1), 1\u201316 (2008)","journal-title":"Applied Intelligence"},{"issue":"1-2","key":"10_CR7","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1016\/j.eswa.2007.07.002","volume":"35","author":"I.H. Kwon","year":"2008","unstructured":"Kwon, I.H., Kim, C.O., Jun, J., Lee, J.H.: Case-based myopic reinforcement learning for satisfying target service level in supply chain. Expert Systems with Applications\u00a035(1-2), 389\u2013397 (2008)","journal-title":"Expert Systems with Applications"},{"issue":"1","key":"10_CR8","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1504\/IJKESDP.2009.021982","volume":"1","author":"J. Leng","year":"2009","unstructured":"Leng, J., Jain, L., Fyfe, C.: Experimental analysis of eligibility traces strategies in temporal difference learning. International Journal of Knowledge Engineering and Soft Data Paradigms\u00a01(1), 26\u201339 (2009)","journal-title":"International Journal of Knowledge Engineering and Soft Data Paradigms"},{"key":"10_CR9","volume-title":"Advances in Neural Information Processing Systems","author":"H.R. Maei","year":"2009","unstructured":"Maei, H.R., Szepesvari, C., Bhatnagar, S., Precup, D., Silver, D., Sutton, R.S.: Convergent Temporal-Difference Learning with Arbitrary Smooth Function Approximation. In: Advances in Neural Information Processing Systems. MIT Press, Vancouver (2009)"},{"key":"10_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1007\/978-3-540-88439-2_2","volume-title":"Hybrid Metaheuristics","author":"S.D. Prestwich","year":"2008","unstructured":"Prestwich, S.D., Tarim, S.A., Rossi, R., Hnich, B.: A Cultural Algorithm for POMDPs from Stochastic Inventory Control. In: Blesa, M.J., Blum, C., Cotta, C., Fern\u00e1ndez, A.J., Gallardo, J.E., Roli, A., Sampels, M. (eds.) HM 2008. LNCS, vol.\u00a05296, pp. 16\u201328. Springer, Heidelberg (2008)"},{"key":"10_CR11","unstructured":"Reynolds, R.G.: An Introduction to Cultural Algorithms. In: Proceedings of the 3rd Annual Conference on Evolutionary Programming, pp. 131\u2013139. World Scientific Publishing (1994)"},{"issue":"2","key":"10_CR12","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1109\/TSMCA.2003.809214","volume":"33","author":"S. Shervais","year":"2003","unstructured":"Shervais, S., Shannon, T.T., Lendaris, G.G.: Intelligent Supply Chain Management Using Adaptive Critic Learning. IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans\u00a033(2), 235\u2013244 (2003)","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans"},{"issue":"1-3","key":"10_CR13","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/BF00114726","volume":"22","author":"S.P. Singh","year":"1996","unstructured":"Singh, S.P., Sutton, R.S.: Reinforcement Learning with Replacing Eligibility Traces. Machine Learning\u00a022(1-3), 123\u2013158 (1996)","journal-title":"Machine Learning"},{"key":"10_CR14","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning. MIT Press (1998)"},{"issue":"2","key":"10_CR15","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1162\/neco.1994.6.2.215","volume":"6","author":"G.J. Tesauro","year":"1994","unstructured":"Tesauro, G.J.: TD-Gammon, a self-teaching backgammon program, achieves master level play. Neural Computation\u00a06(2), 215\u2013219 (1994)","journal-title":"Neural Computation"},{"key":"10_CR16","unstructured":"Van Roy, B., Bertsekas, D.P., Lee, Y., Tsitsiklis, J.N.: A Neuro-Dynamic Programming Approach to Retailer Inventory Management. In: Proceedings of the IEEE Conference on Decision and Control (1997)"}],"container-title":["IFIP Advances in Information and Communication Technology","Intelligent Information Processing VI"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-32891-6_10.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T12:19:28Z","timestamp":1620130768000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-32891-6_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642328909","9783642328916"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-32891-6_10","relation":{},"ISSN":["1868-4238","1861-2288"],"issn-type":[{"type":"print","value":"1868-4238"},{"type":"electronic","value":"1861-2288"}],"subject":[],"published":{"date-parts":[[2012]]}}}