{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T04:53:12Z","timestamp":1725511992724},"publisher-location":"Berlin, Heidelberg","reference-count":31,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540712305"},{"type":"electronic","value":"9783540712312"}],"license":[{"start":{"date-parts":[[2007,1,1]],"date-time":"2007-01-01T00:00:00Z","timestamp":1167609600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2007]]},"DOI":"10.1007\/978-3-540-71231-2_10","type":"book-chapter","created":{"date-parts":[[2007,6,10]],"date-time":"2007-06-10T13:50:57Z","timestamp":1181483457000},"page":"128-143","source":"Crossref","is-referenced-by-count":0,"title":["Counter Example for Q-Bucket-Brigade Under Prediction Problem"],"prefix":"10.1007","author":[{"given":"Atsushi","family":"Wada","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keiki","family":"Takadama","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Katsunori","family":"Shimohara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"10_CR1","first-page":"593","volume":"2","author":"J.H. Holland","year":"1986","unstructured":"Holland, J.H.: Escaping brittleness: the possibilities of general-purpose. Machine Learning, an artificial intelligence approach\u00a02, 593\u2013623 (1986)","journal-title":"Machine Learning, an artificial intelligence approach"},{"key":"10_CR2","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1162\/evco.1995.3.2.149","volume":"3","author":"S.W. Wilson","year":"1995","unstructured":"Wilson, S.W.: Classifier fitness based on accuracy. Evolutionary Computation\u00a03, 149\u2013175 (1995)","journal-title":"Evolutionary Computation"},{"key":"10_CR3","unstructured":"Kovacs, T.: Evolving optimal populations with xcs classifier systems. Technical Report CSRP-96-17, University of Birmingham, School of Computer Science (1996)"},{"key":"10_CR4","first-page":"935","volume-title":"Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2001)","author":"M.V. Butz","year":"2001","unstructured":"Butz, M.V., Pelikan, M.: Analyzing the evolutionary pressures in XCS. In: Spector, L., et al. (eds.) Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2001), pp. 935\u2013942. Morgan Kaufmann, San Francisco (2001)"},{"key":"10_CR5","doi-asserted-by":"crossref","first-page":"739","DOI":"10.1007\/978-3-540-24855-2_89","volume-title":"Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2004)","author":"M.V. Butz","year":"2004","unstructured":"Butz, M.V., Goldberg, D.E., Lanzi, P.L.: Bounding learning time in XCS. In: Deb, K., et al. (eds.) Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2004), pp. 739\u2013750. Springer, Heidelberg (2004)"},{"key":"10_CR6","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1109\/TEVC.2003.818194","volume":"8","author":"M.V. Butz","year":"2004","unstructured":"Butz, M.V., et al.: Toward a theory of generalization and learning in XCS. IEEE Transactions on Evolutionary Computation\u00a08, 28\u201346 (2004)","journal-title":"IEEE Transactions on Evolutionary Computation"},{"key":"10_CR7","volume-title":"An introduction to reinforcement learning","author":"R. Sutton","year":"1998","unstructured":"Sutton, R., Barto, A.: An introduction to reinforcement learning. MIT Press, Cambridge (1998)"},{"key":"10_CR8","doi-asserted-by":"crossref","first-page":"248","DOI":"10.7551\/mitpress\/3117.003.0042","volume-title":"Proceedings of From Animals to Animats, Third International Conference on Simulation of Adaptive Behavior","author":"M. Dorigo","year":"1994","unstructured":"Dorigo, M., Bersini, H.: A comparison of Q-learning and classifier systems. In: Cliff, D., et al. (eds.) Proceedings of From Animals to Animats, Third International Conference on Simulation of Adaptive Behavior, pp. 248\u2013255. MIT Press, Cambridge (1994)"},{"key":"10_CR9","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1007\/s005000100113","volume":"6","author":"P.L. Lanzi","year":"2002","unstructured":"Lanzi, P.L.: Learning classifier systems from a reinforcement learning perspective. Soft Computing\u00a06, 162\u2013170 (2002)","journal-title":"Soft Computing"},{"key":"10_CR10","doi-asserted-by":"publisher","first-page":"452","DOI":"10.1109\/TEVC.2005.850265","volume":"9","author":"M.V. Butz","year":"2005","unstructured":"Butz, M.V., Lanzi, P.L., Goldberg, D.E.: Gradient descent methods in learning classifier systems: Improving xcs performance in multistep problems. IEEE Transactions on Evolutionary Computation\u00a09, 452\u2013473 (2005)","journal-title":"IEEE Transactions on Evolutionary Computation"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Booker, L.: Adaptive value function approximations in classifier systems. In: The Eighth International Workshop on Learning Classifier Systems (IWLCS2005), pp. 90\u201391 (2005)","DOI":"10.1145\/1102256.1102276"},{"key":"10_CR12","doi-asserted-by":"publisher","first-page":"2040","DOI":"10.1109\/CEC.2005.1554946","volume-title":"Proceedings of the IEEE Congress on Evolutionary Computation","author":"T. O\u2019Hara","year":"2005","unstructured":"O\u2019Hara, T., Bull, L.: A memetic accuracy-based neural learning classifier system. In: Proceedings of the IEEE Congress on Evolutionary Computation, pp. 2040\u20132045. IEEE Computer Society Press, Los Alamitos (2005)"},{"key":"10_CR13","unstructured":"Wada, A., et al.: Comparison between Q-learning and ZCS Learning Classifier System: From aspect of function approximation. In: The 8th Conference on Intelligent Autonomous Systems (2004)"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Wada, A., et al.: Learning classifier system equivalent with reinforcement learning with function approximation. In: The Eighth International Workshop on Learning Classifier Systems (IWLCS2005), pp. 24\u201329 (2005)","DOI":"10.1145\/1102256.1102277"},{"key":"10_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/evco.1994.2.1.1","volume":"2","author":"S.W. Wilson","year":"1994","unstructured":"Wilson, S.W.: ZCS: A zeroth level classifier system. Evolutionary Computation\u00a02, 1\u201318 (1994)","journal-title":"Evolutionary Computation"},{"key":"10_CR16","first-page":"1038","volume-title":"Advances in Neural Information Processing Systems, vol. 8","author":"R.S. Sutton","year":"1996","unstructured":"Sutton, R.S.: Generalization in reinforcement learning: Successful examples using sparse coarse coding. In: Touretzky, D.S., Mozer, M.C., Hasselmo, M.E. (eds.) Advances in Neural Information Processing Systems, vol. 8, pp. 1038\u20131044. MIT Press, Cambridge (1996)"},{"key":"10_CR17","first-page":"30","volume-title":"Machine Learning, Proceedings of the Twelfth International Conference on Machine Learning (ICML1995)","author":"L.C. Baird","year":"1995","unstructured":"Baird, L.C.: Residual algorithms: Reinforcement learning with function approximation. In: Prieditis, A., Russell, S.J. (eds.) Machine Learning, Proceedings of the Twelfth International Conference on Machine Learning (ICML1995), pp. 30\u201337. Morgan Kaufmann, San Francisco (1995)"},{"key":"10_CR18","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1007\/11319122_11","volume-title":"Foundations on Learning Classifier Systems","author":"A. Wada","year":"2005","unstructured":"Wada, A., et al.: Learning Classifier Systems with Convergence and Generalization. In: Foundations on Learning Classifier Systems, pp. 285\u2013304. Springer, London (2005)"},{"key":"10_CR19","first-page":"295","volume":"14","author":"P. Dayan","year":"1994","unstructured":"Dayan, P., Sejnowski, T.J.: TD(\u03bb) converges with probability 1. Machine Learning\u00a014, 295\u2013301 (1994)","journal-title":"Machine Learning"},{"key":"10_CR20","first-page":"1185","volume":"6","author":"T.S. Jaakkola","year":"1994","unstructured":"Jaakkola, T.S., Jorda, M.I., Singh, S.P.: On the convergence of stochastic iterative dynamic programming algorithms. IEEE Transactions on Automatic Control\u00a06, 1185\u20131201 (1994)","journal-title":"IEEE Transactions on Automatic Control"},{"key":"10_CR21","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1177\/105971239300100403","volume":"1","author":"J. Peng","year":"1993","unstructured":"Peng, J., Williams, R.J.: On the convergence of stochastic iterative dynamic programming algorithms. Adaptive Behavior\u00a01, 437\u2013454 (1993)","journal-title":"Adaptive Behavior"},{"key":"10_CR22","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":"10_CR23","first-page":"185","volume":"16","author":"J.N. Tsitsiklis","year":"1994","unstructured":"Tsitsiklis, J.N.: Asynchronous stochastic approximation and q-learning. Machine Learning\u00a016, 185\u2013202 (1994)","journal-title":"Machine Learning"},{"key":"10_CR24","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":"10_CR25","first-page":"261","volume-title":"Proceedings of the Twelfth International Conference on Machine Learning","author":"G.J. Gordon","year":"1995","unstructured":"Gordon, G.J.: Stable function approximation in dynamic programming. In: Prieditis, A., Russell, S. (eds.) Proceedings of the Twelfth International Conference on Machine Learning, pp. 261\u2013268. Morgan Kaufmann, San Francisco (1995)"},{"key":"10_CR26","first-page":"361","volume-title":"Advances in Neural Information Processing Systems 7","author":"S.P. Singh","year":"1995","unstructured":"Singh, S.P., Jaakkola, T., Jordan, M.I.: Reinforcement learning with soft state aggregation. In: Tesauro, G., Touretzky, D., Leen, T. (eds.) Advances in Neural Information Processing Systems 7, pp. 361\u2013368. MIT Press, Cambridge (1995)"},{"key":"10_CR27","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1023\/A:1007678930559","volume":"38","author":"S.P. Singh","year":"2000","unstructured":"Singh, S.P., et al.: Convergence results for single-step on-policy reinforcement-learning algorithms. Machine Learning\u00a038, 287\u2013308 (2000)","journal-title":"Machine Learning"},{"key":"10_CR28","unstructured":"Watkins, J.C.H.: Learning from delayed rewards. PhD thesis, Cambridge University (1989)"},{"key":"10_CR29","series-title":"Lecture Notes in Artificial Intelligence","first-page":"253","volume-title":"Advances in Learning Classifier Systems","author":"M.V. Butz","year":"2002","unstructured":"Butz, M.V., Wilson, S.W.: An Algorithmic Description of XCS. In: Lanzi, P.L., Stolzmann, W., Wilson, S.W. (eds.) IWLCS 2001. LNCS (LNAI), vol.\u00a02321, pp. 253\u2013272. Springer, Heidelberg (2002)"},{"key":"10_CR30","unstructured":"Baird, L.C.: Reinforcement Learning Through Gradient Descent. PhD thesis, Carnegie Mellon University, Pittsburgh, PA (1999)"},{"key":"10_CR31","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1145\/1015330.1015390","volume-title":"ICML \u201904: Proceedings of the twenty-first international conference on Machine learning","author":"A. Merke","year":"2004","unstructured":"Merke, A., Schoknecht, R.: Convergence of synchronous reinforcement learning with linear function approximation. In: ICML \u201904: Proceedings of the twenty-first international conference on Machine learning, p. 75. ACM Press, New York (2004)"}],"container-title":["Lecture Notes in Computer Science","Learning Classifier Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-71231-2_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,15]],"date-time":"2024-02-15T00:53:34Z","timestamp":1707958414000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-71231-2_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007]]},"ISBN":["9783540712305","9783540712312"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-71231-2_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2007]]}}}