{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:42:06Z","timestamp":1767339726340},"publisher-location":"Berlin, Heidelberg","reference-count":11,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540441267"},{"type":"electronic","value":"9783540461463"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2002]]},"DOI":"10.1007\/3-540-46146-9_16","type":"book-chapter","created":{"date-parts":[[2010,3,29]],"date-time":"2010-03-29T17:14:30Z","timestamp":1269882870000},"page":"153-162","source":"Crossref","is-referenced-by-count":11,"title":["A Multi-agent Q-learning Framework for Optimizing Stock Trading Systems"],"prefix":"10.1007","author":[{"given":"Jae Won","family":"Lee","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jangmin","family":"O","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2002,8,20]]},"reference":[{"key":"16_CR1","volume-title":"Time Series","author":"S. M. Kendall","year":"1997","unstructured":"Kendall, S. M., Ord, K.: Time Series. Oxford, New York. (1997)"},{"key":"16_CR2","first-page":"936","volume-title":"Advances in Neural Information Processing Systems 10","author":"R. Neuneier","year":"1998","unstructured":"Neuneier, R.: Enhancing Q-Learning for Optimal Asset Allocation. Advances in Neural Information Processing Systems 10. MIT Press, Cambridge. (1998) 936\u2013942"},{"key":"16_CR3","unstructured":"Lee, J.: Stock Price Prediction using Reinforcement Learning. In Proceedings of the 6th IEEE International Symposium on Industrial Electronics. (2001)"},{"key":"16_CR4","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. (1998)"},{"key":"16_CR5","unstructured":"Baird, L. C.: Residual Algorithms: Reinforcement learning with Function Approximation. In Proceedings of Twelfth International Conference on Machine Learning. Morgan Kaufmann, San Fransisco. (1995) 30\u201337"},{"issue":"2","key":"16_CR6","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1109\/72.279181","volume":"5","author":"Y. Bengio","year":"1994","unstructured":"Bengio, Y., Simard, P., Frasconi, P.: Learning Long-Term Dependencies with Gradient is Dificult. IEEE Transactions on Neural Networks 5(2). (1994) 157\u2013166","journal-title":"IEEE Transactions on Neural Networks"},{"issue":"6","key":"16_CR7","doi-asserted-by":"publisher","first-page":"1185","DOI":"10.1162\/neco.1994.6.6.1185","volume":"6","author":"M. Jaakkola","year":"1994","unstructured":"Jaakkola, M., Jordan, M., Singh, S.: On the Convergence of Stochastic Iterative Dynamic Programming Algorithms. Neural Computation, 6(6). (1994) 1185\u20132201","journal-title":"Neural Computation"},{"key":"16_CR8","unstructured":"Xiu, G., Laiwan, C.: Algorithm for Trading and Portfolio Management Using Qlearning and Sharpe Ratio Maximization. In Proceedings of ICONIP 2000, Korea. (2000) 832\u2013837"},{"issue":"5","key":"16_CR9","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1002\/(SICI)1099-131X(1998090)17:5\/6<441::AID-FOR707>3.0.CO;2-#","volume":"17","author":"J. Moody","year":"1998","unstructured":"Moody, J., Wu, Y., Liao, Y., Saffell, M.: Performance Functions and Reinforcement Learning for Trading Systems and Portfolios. Journal of Forecasting, 17(5\u20136). (1998) 441\u2013470","journal-title":"Journal of Forecasting"},{"issue":"4","key":"16_CR10","doi-asserted-by":"publisher","first-page":"875","DOI":"10.1109\/72.935097","volume":"12","author":"J. Moody","year":"2001","unstructured":"Moody, J., Saffell, M.: Learning to Trade via Direct Reinforcement. IEEE Transactions on Neural Networks, 12(4). (2001) 875\u2013889","journal-title":"IEEE Transactions on Neural Networks"},{"key":"16_CR11","first-page":"1031","volume-title":"Advances in Neural Information Processing Systems 11","author":"R. Neuneier","year":"1999","unstructured":"Neuneier, R., Mihatsch., O.: Risk Sensitive Reinforcement Learning. Advances in Neural Information Processing Systems 11. MIT Press, Cambridge. (1999) 1031\u20131037"}],"container-title":["Lecture Notes in Computer Science","Database and Expert Systems Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/3-540-46146-9_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,2,23]],"date-time":"2019-02-23T18:27:43Z","timestamp":1550946463000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/3-540-46146-9_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2002]]},"ISBN":["9783540441267","9783540461463"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/3-540-46146-9_16","relation":{},"ISSN":["0302-9743"],"issn-type":[{"type":"print","value":"0302-9743"}],"subject":[],"published":{"date-parts":[[2002]]}}}