{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T17:48:12Z","timestamp":1725558492191},"publisher-location":"Berlin, Heidelberg","reference-count":22,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642141553"},{"type":"electronic","value":"9783642141560"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-14156-0_17","type":"book-chapter","created":{"date-parts":[[2010,6,24]],"date-time":"2010-06-24T15:01:45Z","timestamp":1277391705000},"page":"194-205","source":"Crossref","is-referenced-by-count":4,"title":["On the Characteristics of Sequential Decision Problems and Their Impact on Evolutionary Computation and Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Andr\u00e9 M. S.","family":"Barreto","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Douglas A.","family":"Augusto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Helio J. C.","family":"Barbosa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"4-5","key":"17_CR1","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"},{"key":"17_CR2","first-page":"369","volume-title":"Advances in Neural Information Processing Systems","author":"J.A. Boyan","year":"1995","unstructured":"Boyan, J.A., Moore, A.W.: Generalization in reinforcement learning: Safely approximating the value function. In: Advances in Neural Information Processing Systems, pp. 369\u2013376. MIT Press, Cambridge (1995)"},{"key":"17_CR3","doi-asserted-by":"crossref","unstructured":"Bull, L., Kovacs, T. (eds.): Foundations of Learning Classifier Systems (Spring 2005)","DOI":"10.1007\/b100387"},{"key":"17_CR4","volume-title":"Design and Analysis of Learning Classifier Systems\u2014A Probabilistic Approach","author":"J. Drugowitsch","year":"2008","unstructured":"Drugowitsch, J.: Design and Analysis of Learning Classifier Systems\u2014A Probabilistic Approach. Springer, Heidelberg (2008)"},{"key":"17_CR5","volume-title":"Genetic algorithms in search, optimization, and machine learning","author":"D. Goldberg","year":"1989","unstructured":"Goldberg, D.: Genetic algorithms in search, optimization, and machine learning. Addison-Wesley, Reading (1989)"},{"key":"17_CR6","first-page":"937","volume":"9","author":"F. Gomez","year":"2008","unstructured":"Gomez, F., Schmidhuber, J., Miikkulainen, R.: Accelerated neural evolution through cooperatively coevolved synapses. Journal of Machine Learning Research\u00a09, 937\u2013965 (2008)","journal-title":"Journal of Machine Learning Research"},{"key":"17_CR7","unstructured":"Gomez, F.J.: Robust non-linear control through neuroevolution. Ph.D. thesis, The University of Texas at Austin (2003), Technical Report AI-TR-03-303"},{"key":"17_CR8","volume-title":"The Elements of Statistical Learning: Data Mining, Inference, and Prediction","author":"T. Hastie","year":"2002","unstructured":"Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer, Heidelberg (2002)"},{"key":"17_CR9","doi-asserted-by":"publisher","first-page":"1107","DOI":"10.1162\/jmlr.2003.4.6.1107","volume":"4","author":"M.G. Lagoudakis","year":"2003","unstructured":"Lagoudakis, M.G., Parr, R.: Least-squares policy iteration. Journal of Machine Learning Research\u00a04, 1107\u20131149 (2003)","journal-title":"Journal of Machine Learning Research"},{"key":"17_CR10","unstructured":"Moriarty, D.E.: Symbiotic Evolution of Neural Networks in Sequential Decision Tasks. Ph.D. thesis, The University of Texas at Austin (1997), Technical Report UT-AI97-257"},{"issue":"1\u20133","key":"17_CR11","first-page":"11","volume":"22","author":"D.E. Moriarty","year":"1996","unstructured":"Moriarty, D.E., Miikkulainen, R.: Efficient reinforcement learning through symbiotic evolution. Machine Learning\u00a022(1\u20133), 11\u201332 (1996)","journal-title":"Machine Learning"},{"key":"17_CR12","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1613\/jair.613","volume":"11","author":"D.E. Moriarty","year":"1999","unstructured":"Moriarty, D.E., Schultz, A.C., Grefenstette, J.J.: Evolutionary algorithms for reinforcement learning. Journal of Artificial Intelligence Research\u00a011, 241\u2013276 (1999)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"17_CR13","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","volume-title":"Markov Decision Processes\u2014Discrete Stochastic Dynamic Programming","author":"M.L. Puterman","year":"1994","unstructured":"Puterman, M.L.: Markov Decision Processes\u2014Discrete Stochastic Dynamic Programming. John Wiley & Sons, Inc., Chichester (1994)"},{"key":"17_CR14","first-page":"463","volume-title":"Proceedings of the Fifteenth International Conference on Machine Learning","author":"J. Randl\u00f8v","year":"1998","unstructured":"Randl\u00f8v, J., Alstr\u00f8m, P.: Learning to drive a bicycle using reinforcement learning and shaping. In: Proceedings of the Fifteenth International Conference on Machine Learning, pp. 463\u2013471. Morgan Kaufmann Publishers Inc., San Francisco (1998)"},{"key":"17_CR15","unstructured":"Stanley, K.O.: Efficient evolution of neural networks through complexification. Ph.D. thesis, The University of Texas at Austin (2004), Technical Report AI-TR-04-314"},{"key":"17_CR16","first-page":"9","volume":"3","author":"R.S. Sutton","year":"1988","unstructured":"Sutton, R.S.: Learning to predict by the methods of temporal differences. Machine Learning\u00a03, 9\u201344 (1988)","journal-title":"Machine Learning"},{"key":"17_CR17","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":"17_CR18","first-page":"59","volume":"22","author":"J.N. Tsitsiklis","year":"1996","unstructured":"Tsitsiklis, J.N., Roy, B.V.: Feature-based methods for large scale dynamic programming. Machine Learning\u00a022, 59\u201394 (1996)","journal-title":"Machine Learning"},{"key":"17_CR19","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1109\/9.580874","volume":"42","author":"J.N. Tsitsiklis","year":"1997","unstructured":"Tsitsiklis, J.N., Roy, B.V.: An analysis of temporal-difference learning with function approximation. IEEE Transactions on Automatic Control\u00a042, 674\u2013690 (1997)","journal-title":"IEEE Transactions on Automatic Control"},{"key":"17_CR20","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1287\/inte.15.6.73","volume":"15","author":"D.J. White","year":"1985","unstructured":"White, D.J.: Real applications of Markov decision processes. Interfaces\u00a015, 73\u201383 (1985)","journal-title":"Interfaces"},{"key":"17_CR21","first-page":"116","volume-title":"Proceedings of the Third International Conference on Genetic Algorithms and their Applications","author":"D. Whitley","year":"1989","unstructured":"Whitley, D.: The GENITOR algorithm and selective pressure:why rank-based allocation of reproductive trials is best. In: Schaffer, J. (ed.) Proceedings of the Third International Conference on Genetic Algorithms and their Applications, pp. 116\u2013121. Morgan Kaufmann, San Francisco (1989)"},{"issue":"2-3","key":"17_CR22","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1007\/BF00993045","volume":"13","author":"D. PWhitley","year":"1993","unstructured":"PWhitley, D., Dominic, S., Das, R., Anderson, C.W.: Genetic reinforcement learning for neurocontrol problems. Machine Learning\u00a013(2-3), 259\u2013284 (1993)","journal-title":"Machine Learning"}],"container-title":["Lecture Notes in Computer Science","Artifical Evolution"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-14156-0_17.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,30]],"date-time":"2021-10-30T02:49:36Z","timestamp":1635562176000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-14156-0_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642141553","9783642141560"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-14156-0_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2010]]}}}