{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T09:55:42Z","timestamp":1771840542820,"version":"3.50.1"},"publisher-location":"Berlin, Heidelberg","reference-count":145,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642276446","type":"print"},{"value":"9783642276453","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-27645-3_10","type":"book-chapter","created":{"date-parts":[[2012,3,5]],"date-time":"2012-03-05T22:18:12Z","timestamp":1330985892000},"page":"325-355","source":"Crossref","is-referenced-by-count":30,"title":["Evolutionary Computation for Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Shimon","family":"Whiteson","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"10_CR1","first-page":"487","volume":"10","author":"D. Ackley","year":"1991","unstructured":"Ackley, D., Littman, M.: Interactions between learning and evolution. Artificial Life II, SFI Studies in the Sciences of Complexity\u00a010, 487\u2013509 (1991)","journal-title":"Artificial Life II, SFI Studies in the Sciences of Complexity"},{"issue":"2","key":"10_CR2","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1162\/evco.2008.16.2.257","volume":"16","author":"A.K. Agogino","year":"2008","unstructured":"Agogino, A.K., Tumer, K.: Efficient evaluation functions for evolving coordination. Evolutionary Computation\u00a016(2), 257\u2013288 (2008)","journal-title":"Evolutionary Computation"},{"key":"10_CR3","first-page":"196","volume":"7","author":"T. Arita","year":"2000","unstructured":"Arita, T., Suzuki, R.: Interactions between learning and evolution: The outstanding strategy generated by the Baldwin Effect. Artificial Life\u00a07, 196\u2013205 (2000)","journal-title":"Artificial Life"},{"key":"10_CR4","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1086\/276408","volume":"30","author":"J.M. Baldwin","year":"1896","unstructured":"Baldwin, J.M.: A new factor in evolution. The American Naturalist\u00a030, 441\u2013451 (1896)","journal-title":"The American Naturalist"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Boers, E., Borst, M., Sprinkhuizen-Kuyper, I.: Evolving Artificial Neural Networks using the \u201cBaldwin Effect\u201d. In: Proceedings of the International Conference Artificial Neural Nets and Genetic Algorithms in Ales, France (1995)","DOI":"10.1007\/978-3-7091-7535-4_87"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Bonarini, A.: An introduction to learning fuzzy classifier systems. Learning Classifier Systems, 83\u2013104 (2000)","DOI":"10.1007\/3-540-45027-0_4"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Bull, L., Kovacs, T.: Foundations of learning classifier systems: An introduction. Foundations of Learning Classifier Systems, 1\u201317 (2005)","DOI":"10.1007\/11319122_1"},{"key":"10_CR8","unstructured":"Bull, L., O\u2019Hara, T.: Accuracy-based neuro and neuro-fuzzy classifier systems. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 905\u2013911 (2002)"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Butz, M.: Anticipatory learning classifier systems. Kluwer Academic Publishers (2002)","DOI":"10.1007\/978-1-4615-0891-5"},{"key":"10_CR10","volume-title":"Rule-based evolutionary online learning systems: A principled approach to LCS analysis and design","author":"M. Butz","year":"2006","unstructured":"Butz, M.: Rule-based evolutionary online learning systems: A principled approach to LCS analysis and design. Springer, Heidelberg (2006)"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Butz, M., Herbort, O.: Context-dependent predictions and cognitive arm control with XCSF. In: Proceedings of the 10th Annual Conference on Genetic and Evolutionary Computation, pp. 1357\u20131364. ACM (2008)","DOI":"10.1145\/1389095.1389360"},{"issue":"3","key":"10_CR12","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1007\/s12065-009-0019-y","volume":"2","author":"M. Butz","year":"2009","unstructured":"Butz, M., Lanzi, P.: Sequential problems that test generalization in learning classifier systems. Evolutionary Intelligence\u00a02(3), 141\u2013147 (2009)","journal-title":"Evolutionary Intelligence"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Butz, M., Goldberg, D., Lanzi, P.: Gradient descent methods in learning classifier systems: Improving XCS performance in multistep problems. IEEE Transactions on Evolutionary Computation\u00a09(5) (2005)","DOI":"10.1109\/TEVC.2005.850265"},{"issue":"3","key":"10_CR14","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1109\/TEVC.2007.903551","volume":"12","author":"M. Butz","year":"2008","unstructured":"Butz, M., Lanzi, P., Wilson, S.: Function approximation with XCS: Hyperellipsoidal conditions, recursive least squares, and compaction. IEEE Transactions on Evolutionary Computation\u00a012(3), 355\u2013376 (2008)","journal-title":"IEEE Transactions on Evolutionary Computation"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Butz, M., Pedersen, G., Stalph, P.: Learning sensorimotor control structures with XCSF: Redundancy exploitation and dynamic control. In: Proceedings of the 11th Annual Conference on Genetic and Evolutionary Computation, pp. 1171\u20131178 (2009)","DOI":"10.1145\/1569901.1570059"},{"issue":"1","key":"10_CR16","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1023\/A:1014463014150","volume":"33","author":"Z. Cai","year":"2002","unstructured":"Cai, Z., Peng, Z.: Cooperative coevolutionary adaptive genetic algorithm in path planning of cooperative multi-mobile robot systems. Journal of Intelligent and Robotic Systems\u00a033(1), 61\u201371 (2002)","journal-title":"Journal of Intelligent and Robotic Systems"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Cardamone, L., Loiacono, D., Lanzi, P.: On-line neuroevolution applied to the open racing car simulator. In: Proceedings of the Congress on Evolutionary Computation (CEC), pp. 2622\u20132629 (2009)","DOI":"10.1109\/CEC.2009.4983271"},{"issue":"3","key":"10_CR18","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1109\/TCIAIG.2010.2052102","volume":"2","author":"L. Cardamone","year":"2010","unstructured":"Cardamone, L., Loiacono, D., Lanzi, P.L.: Learning to drive in the open racing car simulator using online neuroevolution. IEEE Transactions on Computational Intelligence and AI in Games\u00a02(3), 176\u2013190 (2010)","journal-title":"IEEE Transactions on Computational Intelligence and AI in Games"},{"issue":"4","key":"10_CR19","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1109\/4235.942536","volume":"5","author":"K. Chellapilla","year":"2001","unstructured":"Chellapilla, K., Fogel, D.: Evolving an expert checkers playing program without using human expertise. IEEE Transactions on Evolutionary Computation\u00a05(4), 422\u2013428 (2001)","journal-title":"IEEE Transactions on Evolutionary Computation"},{"key":"10_CR20","volume-title":"Evolutionary algorithms for solving multi-objective problems","author":"C. Coello","year":"2007","unstructured":"Coello, C., Lamont, G., Van Veldhuizen, D.: Evolutionary algorithms for solving multi-objective problems. Springer, Heidelberg (2007)"},{"key":"10_CR21","unstructured":"D\u2019Ambrosio, D., Lehman, J., Risi, S., Stanley, K.O.: Evolving policy geometry for scalable multiagent learning. In: Proceedings of the Ninth International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2010), pp. 731\u2013738 (2010)"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Darwen, P., Yao, X.: Automatic modularization by speciation. In: Proceedings of the 1996 IEEE International Conference on Evolutionary Computation (ICEC 1996), pp. 88\u201393 (1996)","DOI":"10.1109\/ICEC.1996.542339"},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Dasgupta, D., McGregor, D.: Designing application-specific neural networks using the structured genetic algorithm. In: Proceedings of the International Conference on Combinations of Genetic Algorithms and Neural Networks, pp. 87\u201396 (1992)","DOI":"10.1109\/COGANN.1992.273946"},{"issue":"1161","key":"10_CR24","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1098\/rspb.1979.0081","volume":"205","author":"R. Dawkins","year":"1979","unstructured":"Dawkins, R., Krebs, J.: Arms races between and within species. Proceedings of the Royal Society of London Series B, Biological Sciences\u00a0205(1161), 489\u2013511 (1979)","journal-title":"Proceedings of the Royal Society of London Series B, Biological Sciences"},{"key":"10_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1007\/978-3-540-24854-5_55","volume-title":"Genetic and Evolutionary Computation \u2013 GECCO 2004","author":"E.D. Jong de","year":"2004","unstructured":"de Jong, E.D.: The Incremental Pareto-coevolution Archive. In: Deb, K., et al. (eds.) GECCO 2004. LNCS, vol.\u00a03102, pp. 525\u2013536. Springer, Heidelberg (2004)"},{"issue":"1","key":"10_CR26","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1162\/evco.2007.15.1.61","volume":"15","author":"E. Jong de","year":"2007","unstructured":"de Jong, E.: A monotonic archive for Pareto-coevolution. Evolutionary Computation\u00a015(1), 61\u201393 (2007)","journal-title":"Evolutionary Computation"},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"De Jong, K., Spears, W.: An analysis of the interacting roles of population size and crossover in genetic algorithms. In: Parallel Problem Solving from Nature, pp. 38\u201347 (1991)","DOI":"10.1007\/BFb0029729"},{"issue":"2","key":"10_CR28","first-page":"161","volume":"13","author":"K. Jong De","year":"1993","unstructured":"De Jong, K., Spears, W., Gordon, D.: Using genetic algorithms for concept learning. Machine learning\u00a013(2), 161\u2013188 (1993)","journal-title":"Machine learning"},{"key":"10_CR29","unstructured":"Deb, K.: Multi-objective optimization using evolutionary algorithms. Wiley (2001)"},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"Dorigo, M., Colombetti, M.: Robot shaping: An experiment in behavior engineering. The MIT Press (1998)","DOI":"10.7551\/mitpress\/5988.001.0001"},{"issue":"3","key":"10_CR31","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1023\/A:1011953410319","volume":"2","author":"K.L. Downing","year":"2001","unstructured":"Downing, K.L.: Reinforced genetic programming. Genetic Programming and Evolvable Machines\u00a02(3), 259\u2013288 (2001)","journal-title":"Genetic Programming and Evolvable Machines"},{"issue":"1","key":"10_CR32","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1162\/089976600300015961","volume":"12","author":"K. Doya","year":"2000","unstructured":"Doya, K.: Reinforcement learning in continuous time and space. Neural Computation\u00a012(1), 219\u2013245 (2000)","journal-title":"Neural Computation"},{"key":"10_CR33","volume-title":"Design and analysis of learning classifier systems: A probabilistic approach","author":"J. Drugowitsch","year":"2008","unstructured":"Drugowitsch, J.: Design and analysis of learning classifier systems: A probabilistic approach. Springer, Heidelberg (2008)"},{"key":"10_CR34","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1007\/3-540-45356-3_46","volume-title":"Parallel Problem Solving from Nature PPSN VI","author":"S. Ficici","year":"2000","unstructured":"Ficici, S., Pollack, J.: A game-theoretic approach to the simple coevolutionary algorithm. In: Parallel Problem Solving from Nature PPSN VI, pp. 467\u2013476. Springer, Heidelberg (2000)"},{"key":"10_CR35","doi-asserted-by":"crossref","unstructured":"Ficici, S., Pollack, J.: Pareto optimality in coevolutionary learning. Advances in Artificial Life, 316\u2013325 (2001)","DOI":"10.1007\/3-540-44811-X_34"},{"issue":"3","key":"10_CR36","doi-asserted-by":"crossref","first-page":"396","DOI":"10.1109\/3477.499791","volume":"26","author":"D. Floreano","year":"2002","unstructured":"Floreano, D., Mondada, F.: Evolution of homing navigation in a real mobile robot. IEEE Transactions on Systems, Man, and Cybernetics, Part B\u00a026(3), 396\u2013407 (2002)","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics, Part B"},{"issue":"3","key":"10_CR37","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1023\/A:1012459627968","volume":"11","author":"D. Floreano","year":"2001","unstructured":"Floreano, D., Urzelai, J.: Evolution of plastic control networks. Autonomous Robots\u00a011(3), 311\u2013317 (2001)","journal-title":"Autonomous Robots"},{"key":"10_CR38","first-page":"277","volume":"4","author":"R. French","year":"1994","unstructured":"French, R., Messinger, A.: Genes, phenes and the Baldwin effect: Learning and evolution in a simulated population. Artificial Life\u00a04, 277\u2013282 (1994)","journal-title":"Artificial Life"},{"key":"10_CR39","doi-asserted-by":"crossref","unstructured":"Gaskett, C., Wettergreen, D., Zelinsky, A.: Q-learning in continuous state and action spaces. Advanced Topics in Artificial Intelligence, 417\u2013428 (1999)","DOI":"10.1007\/3-540-46695-9_35"},{"key":"10_CR40","unstructured":"Gauci, J., Stanley, K.O.: A case study on the critical role of geometric regularity in machine learning. In: Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence, AAAI 2008 (2008)"},{"issue":"7","key":"10_CR41","doi-asserted-by":"crossref","first-page":"1860","DOI":"10.1162\/neco.2010.06-09-1042","volume":"22","author":"J. Gauci","year":"2010","unstructured":"Gauci, J., Stanley, K.O.: Autonomous evolution of topographic regularities in artificial neural networks. Neural Computation\u00a022(7), 1860\u20131898 (2010)","journal-title":"Neural Computation"},{"issue":"3","key":"10_CR42","first-page":"216","volume":"6","author":"P. Gerard","year":"2002","unstructured":"Gerard, P., Stolzmann, W., Sigaud, O.: YACS: a new learning classifier system using anticipation. Soft Computing-A Fusion of Foundations, Methodologies and Applications\u00a06(3), 216\u2013228 (2002)","journal-title":"Soft Computing-A Fusion of Foundations, Methodologies and Applications"},{"issue":"3","key":"10_CR43","doi-asserted-by":"crossref","first-page":"614","DOI":"10.1016\/j.ejor.2003.10.004","volume":"160","author":"P. Gerard","year":"2005","unstructured":"Gerard, P., Meyer, J., Sigaud, O.: Combining latent learning with dynamic programming in the modular anticipatory classifier system. European Journal of Operational Research\u00a0160(3), 614\u2013637 (2005)","journal-title":"European Journal of Operational Research"},{"key":"10_CR44","unstructured":"Giraud-Carrier, C.: Unifying learning with evolution through Baldwinian evolution and Lamarckism: A case study. In: Proceedings of the Symposium on Computational Intelligence and Learning (CoIL 2000), pp. 36\u201341 (2000)"},{"key":"10_CR45","unstructured":"Goldberg, D.: Genetic Algorithms in Search. In: Optimization and Machine Learning, Addison-Wesley (1989)"},{"key":"10_CR46","first-page":"69","volume":"1","author":"D. Goldberg","year":"1991","unstructured":"Goldberg, D., Deb, K.: A comparative analysis of selection schemes used in genetic algorithms. Foundations of genetic algorithms\u00a01, 69\u201393 (1991)","journal-title":"Foundations of genetic algorithms"},{"key":"10_CR47","unstructured":"Goldberg, D., Richardson, J.: Genetic algorithms with sharing for multimodal function optimization. In: Proceedings of the Second International Conference on Genetic Algorithms and their Application, p. 49 (1987)"},{"key":"10_CR48","unstructured":"Gomez, F., Miikkulainen, R.: Solving non-Markovian control tasks with neuroevolution. In: Proceedings of the International Joint Conference on Artificial Intelligence, pp. 1356\u20131361 (1999)"},{"key":"10_CR49","doi-asserted-by":"crossref","unstructured":"Gomez, F., Miikkulainen, R.: Active guidance for a finless rocket using neuroevolution. In: GECCO 2003: Proceedings of the Genetic and Evolutionary Computation Conference (2003)","DOI":"10.1007\/3-540-45110-2_105"},{"key":"10_CR50","doi-asserted-by":"crossref","unstructured":"Gomez, F., Schmidhuber, J.: Co-evolving recurrent neurons learn deep memory POMDPs. In: GECCO 2005: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 491\u2013498 (2005a)","DOI":"10.1145\/1068009.1068092"},{"key":"10_CR51","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1007\/b136731","volume-title":"Artificial Neural Networks: Formal Models and Their Applications \u2013 ICANN 2005","author":"F.J. Gomez","year":"2005","unstructured":"Gomez, F.J., Schmidhuber, J.: Evolving Modular Fast-Weight Networks for Control. In: Duch, W., Kacprzyk, J., Oja, E., Zadro\u017cny, S. (eds.) ICANN 2005. LNCS, vol.\u00a03697, pp. 383\u2013389. Springer, Heidelberg (2005b)"},{"key":"10_CR52","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"crossref","first-page":"654","DOI":"10.1007\/11871842_64","volume-title":"Machine Learning: ECML 2006","author":"F.J. Gomez","year":"2006","unstructured":"Gomez, F.J., Schmidhuber, J., Miikkulainen, R.: Efficient Non-Linear Control Through Neuroevolution. In: F\u00fcrnkranz, J., Scheffer, T., Spiliopoulou, M. (eds.) ECML 2006. LNCS (LNAI), vol.\u00a04212, pp. 654\u2013662. Springer, Heidelberg (2006)"},{"key":"10_CR53","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"},{"issue":"2","key":"10_CR54","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1177\/105971239400300202","volume":"3","author":"F. Gruau","year":"1994","unstructured":"Gruau, F.: Automatic definition of modular neural networks. Adaptive Behavior\u00a03(2), 151 (1994)","journal-title":"Adaptive Behavior"},{"key":"10_CR55","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1162\/evco.1993.1.3.213","volume":"1","author":"F. Gruau","year":"1993","unstructured":"Gruau, F., Whitley, D.: Adding learning to the cellular development of neural networks: Evolution and the Baldwin effect. Evolutionary Computation\u00a01, 213\u2013233 (1993)","journal-title":"Evolutionary Computation"},{"issue":"1","key":"10_CR56","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1162\/106365603321828970","volume":"11","author":"N. Hansen","year":"2003","unstructured":"Hansen, N., M\u00fcller, S., Koumoutsakos, P.: Reducing the time complexity of the derandomized evolution strategy with covariance matrix adaptation (CMA-ES). Evolutionary Computation\u00a011(1), 1\u201318 (2003)","journal-title":"Evolutionary Computation"},{"key":"10_CR57","doi-asserted-by":"crossref","unstructured":"van Hasselt, H., Wiering, M.: Reinforcement learning in continuous action spaces. In: IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning, ADPRL, pp. 272\u2013279 (2007)","DOI":"10.1109\/ADPRL.2007.368199"},{"key":"10_CR58","unstructured":"Haykin, S.: Neural networks: a comprehensive foundation. Prentice-Hall (1994)"},{"key":"10_CR59","doi-asserted-by":"crossref","unstructured":"Heidrich-Meisner, V., Igel, C.: Variable metric reinforcement learning methods applied to the noisy mountain car problem. Recent Advances in Reinforcement Learning, 136\u2013150 (2008)","DOI":"10.1007\/978-3-540-89722-4_11"},{"key":"10_CR60","doi-asserted-by":"crossref","unstructured":"Heidrich-Meisner, V., Igel, C.: Hoeffding and Bernstein races for selecting policies in evolutionary direct policy search. In: Proceedings of the 26th Annual International Conference on Machine Learning, pp. 401\u2013408 (2009a)","DOI":"10.1145\/1553374.1553426"},{"issue":"4","key":"10_CR61","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1016\/j.jalgor.2009.04.002","volume":"64","author":"V. Heidrich-Meisner","year":"2009","unstructured":"Heidrich-Meisner, V., Igel, C.: Neuroevolution strategies for episodic reinforcement learning. Journal of Algorithms\u00a064(4), 152\u2013168 (2009b)","journal-title":"Journal of Algorithms"},{"key":"10_CR62","doi-asserted-by":"crossref","unstructured":"Heidrich-Meisner, V., Igel, C.: Uncertainty handling CMA-ES for reinforcement learning. In: Proceedings of the 11th Annual Conference on Genetic and Evolutionary Computation, pp. 1211\u20131218 (2009c)","DOI":"10.1145\/1569901.1570064"},{"issue":"1-3","key":"10_CR63","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1016\/0167-2789(90)90076-2","volume":"42","author":"W. Hillis","year":"1990","unstructured":"Hillis, W.: Co-evolving parasites improve simulated evolution as an optimization procedure. Physica D: Nonlinear Phenomena\u00a042(1-3), 228\u2013234 (1990)","journal-title":"Physica D: Nonlinear Phenomena"},{"key":"10_CR64","first-page":"495","volume":"1","author":"G.E. Hinton","year":"1987","unstructured":"Hinton, G.E., Nowlan, S.J.: How learning can guide evolution. Complex Systems\u00a01, 495\u2013502 (1987)","journal-title":"Complex Systems"},{"key":"10_CR65","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1145\/1045343.1045373","volume":"63","author":"J. Holland","year":"1977","unstructured":"Holland, J., Reitman, J.: Cognitive systems based on adaptive algorithms. ACM SIGART Bulletin\u00a063, 49\u201349 (1977)","journal-title":"ACM SIGART Bulletin"},{"key":"10_CR66","unstructured":"Holland, J.H.: Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology. In: Control and Artificial Intelligence. University of Michigan Press (1975)"},{"issue":"3","key":"10_CR67","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1162\/106454602320991837","volume":"8","author":"G. Hornby","year":"2002","unstructured":"Hornby, G., Pollack, J.: Creating high-level components with a generative representation for body-brain evolution. Artificial Life\u00a08(3), 223\u2013246 (2002)","journal-title":"Artificial Life"},{"key":"10_CR68","doi-asserted-by":"crossref","unstructured":"Igel, C.: Neuroevolution for reinforcement learning using evolution strategies. In: Congress on Evolutionary Computation, vol.\u00a04, pp. 2588\u20132595 (2003)","DOI":"10.1109\/CEC.2003.1299414"},{"issue":"4","key":"10_CR69","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1162\/1063656043138905","volume":"12","author":"T. Jansen","year":"2004","unstructured":"Jansen, T., Wiegand, R.P.: The cooperative coevolutionary (1+1) EA. Evolutionary Computation\u00a012(4), 405\u2013434 (2004)","journal-title":"Evolutionary Computation"},{"key":"10_CR70","doi-asserted-by":"crossref","unstructured":"Kaelbling, L.P.: Learning in Embedded Systems. MIT Press (1993)","DOI":"10.7551\/mitpress\/4168.001.0001"},{"key":"10_CR71","doi-asserted-by":"crossref","unstructured":"Kernbach, S., Meister, E., Scholz, O., Humza, R., Liedke, J., Ricotti, L., Jemai, J., Havlik, J., Liu, W.: Evolutionary robotics: The next-generation-platform for on-line and on-board artificial evolution. In: CEC 2009: IEEE Congress on Evolutionary Computation, pp. 1079\u20131086 (2009)","DOI":"10.1109\/CEC.2009.4983066"},{"key":"10_CR72","doi-asserted-by":"crossref","unstructured":"Kohl, N., Miikkulainen, R.: Evolving neural networks for fractured domains. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 1405\u20131412 (2008)","DOI":"10.1145\/1389095.1389366"},{"key":"10_CR73","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1016\/j.neunet.2009.03.001","volume":"22","author":"N. Kohl","year":"2009","unstructured":"Kohl, N., Miikkulainen, R.: Evolving neural networks for strategic decision-making problems. Neural Networks\u00a022, 326\u2013337 (2009); (special issue on Goal-Directed Neural Systems)","journal-title":"Neural Networks"},{"key":"10_CR74","doi-asserted-by":"crossref","unstructured":"Koppejan, R., Whiteson, S.: Neuroevolutionary reinforcement learning for generalized helicopter control. In: GECCO 2009: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 145\u2013152 (2009)","DOI":"10.1145\/1569901.1569922"},{"key":"10_CR75","volume-title":"Strength or accuracy: credit assignment in learning classifier systems","author":"T. Kovacs","year":"2003","unstructured":"Kovacs, T.: Strength or accuracy: credit assignment in learning classifier systems. Springer, Heidelberg (2003)"},{"key":"10_CR76","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4615-1539-5","volume-title":"Estimation of distribution algorithms: A new tool for evolutionary computation","author":"P. Larranaga","year":"2002","unstructured":"Larranaga, P., Lozano, J.: Estimation of distribution algorithms: A new tool for evolutionary computation. Springer, Netherlands (2002)"},{"issue":"3","key":"10_CR77","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1016\/0022-5193(68)90080-5","volume":"18","author":"A. Lindenmayer","year":"1968","unstructured":"Lindenmayer, A.: Mathematical models for cellular interactions in development II. Simple and branching filaments with two-sided inputs. Journal of Theoretical Biology\u00a018(3), 300\u2013315 (1968)","journal-title":"Journal of Theoretical Biology"},{"key":"10_CR78","unstructured":"Littman, M.L., Dean, T.L., Kaelbling, L.P.: On the complexity of solving Markov decision processes. In: Proceedings of the Eleventh International Conference on Uncertainty in Artificial Intelligence, pp. 394\u2013402 (1995)"},{"key":"10_CR79","doi-asserted-by":"crossref","unstructured":"Lucas, S.M., Runarsson, T.P.: Temporal difference learning versus co-evolution for acquiring othello position evaluation. In: IEEE Symposium on Computational Intelligence and Games (2006)","DOI":"10.1109\/CIG.2006.311681"},{"key":"10_CR80","doi-asserted-by":"crossref","unstructured":"Lucas, S.M., Togelius, J.: Point-to-point car racing: an initial study of evolution versus temporal difference learning. In: Symposium, I.E.E.E. (ed.) on Computational Intelligence and Games, pp. 260\u2013267 (2007)","DOI":"10.1109\/CIG.2007.368107"},{"key":"10_CR81","first-page":"2169","volume":"8","author":"S. Mahadevan","year":"2007","unstructured":"Mahadevan, S., Maggioni, M.: Proto-value functions: A Laplacian framework for learning representation and control in Markov decision processes. Journal of Machine Learning Research\u00a08, 2169\u20132231 (2007)","journal-title":"Journal of Machine Learning Research"},{"key":"10_CR82","unstructured":"Mahfoud, S.: A comparison of parallel and sequential niching methods. In: Conference on Genetic Algorithms, vol.\u00a0136, p. 143 (1995)"},{"key":"10_CR83","unstructured":"McQuesten, P., Miikkulainen, R.: Culling and teaching in neuro-evolution. In: Proceedings of the Seventh International Conference on Genetic Algorithms, pp. 760\u2013767 (1997)"},{"key":"10_CR84","first-page":"1","volume-title":"Evolutionary Robotics","author":"J. Meyer","year":"1998","unstructured":"Meyer, J., Husbands, P., Harvey, I.: Evolutionary robotics: A survey of applications and problems. In: Evolutionary Robotics, pp. 1\u201321. Springer, Heidelberg (1998)"},{"issue":"2","key":"10_CR85","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1023\/A:1017988514716","volume":"49","author":"J. Mill\u00e1n","year":"2002","unstructured":"Mill\u00e1n, J., Posenato, D., Dedieu, E.: Continuous-action Q-learning. Machine Learning\u00a049(2), 247\u2013265 (2002)","journal-title":"Machine Learning"},{"key":"10_CR86","doi-asserted-by":"crossref","unstructured":"Monroy, G., Stanley, K., Miikkulainen, R.: Coevolution of neural networks using a layered Pareto archive. In: Proceedings of the 8th Annual Conference on Genetic and Evolutionary Computation, p. 336 (2006)","DOI":"10.1145\/1143997.1144058"},{"issue":"4","key":"10_CR87","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1162\/evco.1997.5.4.373","volume":"5","author":"D. Moriarty","year":"1997","unstructured":"Moriarty, D., Miikkulainen, R.: Forming neural networks through efficient and adaptive coevolution. Evolutionary Computation\u00a05(4), 373\u2013399 (1997)","journal-title":"Evolutionary Computation"},{"issue":"11","key":"10_CR88","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(11), 11\u201333 (1996)","journal-title":"Machine Learning"},{"key":"10_CR89","doi-asserted-by":"crossref","first-page":"199","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, 199\u2013229 (1999)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"10_CR90","unstructured":"Ng, A.Y., Coates, A., Diel, M., Ganapathi, V., Schulte, J., Tse, B., Berger, E., Liang, E.: Inverted autonomous helicopter flight via reinforcement learning. In: Proceedings of the International Symposium on Experimental Robotics (2004)"},{"issue":"1","key":"10_CR91","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1177\/105971239600500104","volume":"5","author":"S. Nolfi","year":"1997","unstructured":"Nolfi, S., Parisi, D.: Learning to adapt to changing environments in evolving neural networks. Adaptive Behavior\u00a05(1), 75\u201398 (1997)","journal-title":"Adaptive Behavior"},{"key":"10_CR92","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1177\/105971239400300102","volume":"2","author":"S. Nolfi","year":"1994","unstructured":"Nolfi, S., Elman, J.L., Parisi, D.: Learning and evolution in neural networks. Adaptive Behavior\u00a02, 5\u201328 (1994)","journal-title":"Adaptive Behavior"},{"issue":"2","key":"10_CR93","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1177\/105971239700500201","volume":"5","author":"P. Nordin","year":"1997","unstructured":"Nordin, P., Banzhaf, W.: An on-line method to evolve behavior and to control a miniature robot in real time with genetic programming. Adaptive Behavior\u00a05(2), 107 (1997)","journal-title":"Adaptive Behavior"},{"issue":"3","key":"10_CR94","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1007\/s10458-005-2631-2","volume":"11","author":"L. Panait","year":"2005","unstructured":"Panait, L., Luke, S.: Cooperative multi-agent learning: The state of the art. Autonomous Agents and Multi-Agent Systems\u00a011(3), 387\u2013434 (2005)","journal-title":"Autonomous Agents and Multi-Agent Systems"},{"key":"10_CR95","doi-asserted-by":"crossref","unstructured":"Panait, L., Luke, S., Harrison, J.F.: Archive-based cooperative coevolutionary algorithms. In: GECCO 2006: Proceedings of the 8th Annual Conference on Genetic and Evolutionary Computation, pp. 345\u2013352 (2006)","DOI":"10.1145\/1143997.1144060"},{"key":"10_CR96","doi-asserted-by":"crossref","unstructured":"Parr, R., Painter-Wakefield, C., Li, L., Littman, M.: Analyzing feature generation for value-function approximation. In: Proceedings of the 24th International Conference on Machine Learning, p. 744 (2007)","DOI":"10.1145\/1273496.1273589"},{"key":"10_CR97","unstructured":"Pereira, F.B., Costa, E.: Understanding the role of learning in the evolution of busy beaver: A comparison between the Baldwin Effect and a Lamarckian strategy. In: Proceedings of the Genetic and Evolutionary Computation Conference, GECCO 2001 (2001)"},{"issue":"7-9","key":"10_CR98","doi-asserted-by":"crossref","first-page":"1180","DOI":"10.1016\/j.neucom.2007.11.026","volume":"71","author":"J. Peters","year":"2008","unstructured":"Peters, J., Schaal, S.: Natural actor-critic. Neurocomputing\u00a071(7-9), 1180\u20131190 (2008)","journal-title":"Neurocomputing"},{"issue":"3","key":"10_CR99","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1023\/A:1007417214905","volume":"32","author":"J. Pollack","year":"1998","unstructured":"Pollack, J., Blair, A.: Co-evolution in the successful learning of backgammon strategy. Machine Learning\u00a032(3), 225\u2013240 (1998)","journal-title":"Machine Learning"},{"key":"10_CR100","volume-title":"Handbook of Natural Computing","author":"E. Popovici","year":"2010","unstructured":"Popovici, E., Bucci, A., Wiegand, P., De Jong, E.: Coevolutionary principles. In: Rozenberg, G., Baeck, T., Kok, J. (eds.) Handbook of Natural Computing. Springer, Berlin (2010)"},{"key":"10_CR101","unstructured":"Potter, M.A., De Jong, K.A.: Evolving neural networks with collaborative species. In: Summer Computer Simulation Conference, pp. 340\u2013345 (1995)"},{"key":"10_CR102","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1162\/106365600568086","volume":"8","author":"M.A. Potter","year":"2000","unstructured":"Potter, M.A., De Jong, K.A.: Cooperative coevolution: An architecture for evolving coadapted subcomponents. Evolutionary Computation\u00a08, 1\u201329 (2000)","journal-title":"Evolutionary Computation"},{"issue":"6","key":"10_CR103","doi-asserted-by":"crossref","first-page":"999","DOI":"10.1007\/BF02703810","volume":"28","author":"D. Pratihar","year":"2003","unstructured":"Pratihar, D.: Evolutionary robotics: A review. Sadhana\u00a028(6), 999\u20131009 (2003)","journal-title":"Sadhana"},{"key":"10_CR104","doi-asserted-by":"crossref","unstructured":"Priesterjahn, S., Weimer, A., Eberling, M.: Real-time imitation-based adaptation of gaming behaviour in modern computer games. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 1431\u20131432 (2008)","DOI":"10.1145\/1389095.1389374"},{"issue":"1","key":"10_CR105","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1007\/BF01411376","volume":"1","author":"N. Radcliffe","year":"1993","unstructured":"Radcliffe, N.: Genetic set recombination and its application to neural network topology optimisation. Neural Computing & Applications\u00a01(1), 67\u201390 (1993)","journal-title":"Neural Computing & Applications"},{"issue":"1","key":"10_CR106","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1162\/evco.1997.5.1.1","volume":"5","author":"C.D. Rosin","year":"1997","unstructured":"Rosin, C.D., Belew, R.K.: New methods for competitive coevolution. Evolutionary Computation\u00a05(1), 1\u201329 (1997)","journal-title":"Evolutionary Computation"},{"key":"10_CR107","volume-title":"Monte-Carlo Simulation, and Machine Learning","author":"R. Rubinstein","year":"2004","unstructured":"Rubinstein, R., Kroese, D.: The cross-entropy method: a unified approach to combinatorial optimization. In: Monte-Carlo Simulation, and Machine Learning. Springer, Heidelberg (2004)"},{"key":"10_CR108","doi-asserted-by":"crossref","first-page":"628","DOI":"10.1109\/TEVC.2005.856212","volume":"9","author":"T.P. Runarsson","year":"2005","unstructured":"Runarsson, T.P., Lucas, S.M.: Co-evolution versus self-play temporal difference learning for acquiring position evaluation in small-board go. IEEE Transactions on Evolutionary Computation\u00a09, 628\u2013640 (2005)","journal-title":"IEEE Transactions on Evolutionary Computation"},{"key":"10_CR109","unstructured":"Schmidhuber, J., Wierstra, D., Gomez, F.J.: Evolino: Hybrid neuroevolution \/ optimal linear search for sequence learning. In: Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, pp. 853\u2013858 (2005)"},{"issue":"3","key":"10_CR110","doi-asserted-by":"crossref","first-page":"757","DOI":"10.1162\/neco.2007.19.3.757","volume":"19","author":"J. Schmidhuber","year":"2007","unstructured":"Schmidhuber, J., Wierstra, D., Gagliolo, M., Gomez, F.: Training recurrent networks by evolino. Neural Computation\u00a019(3), 757\u2013779 (2007)","journal-title":"Neural Computation"},{"issue":"1","key":"10_CR111","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/S0967-0661(00)00087-3","volume":"9","author":"P. Schroder","year":"2001","unstructured":"Schroder, P., Green, B., Grum, N., Fleming, P.: On-line evolution of robust control systems: an industrial active magnetic bearing application. Control Engineering Practice\u00a09(1), 37\u201349 (2001)","journal-title":"Control Engineering Practice"},{"key":"10_CR112","doi-asserted-by":"crossref","unstructured":"Sigaud, O., Butz, M., Kozlova, O., Meyer, C.: Anticipatory Learning Classifier Systems and Factored Reinforcement Learning. Anticipatory Behavior in Adaptive Learning Systems, 321\u2013333 (2009)","DOI":"10.1007\/978-3-642-02565-5_18"},{"issue":"2","key":"10_CR113","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1162\/106454603322221487","volume":"9","author":"K. Stanley","year":"2003","unstructured":"Stanley, K., Miikkulainen, R.: A taxonomy for artificial embryogeny. Artificial Life\u00a09(2), 93\u2013130 (2003)","journal-title":"Artificial Life"},{"issue":"2","key":"10_CR114","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1162\/106365602320169811","volume":"10","author":"K.O. Stanley","year":"2002","unstructured":"Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evolutionary Computation\u00a010(2), 99\u2013127 (2002)","journal-title":"Evolutionary Computation"},{"key":"10_CR115","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1613\/jair.1338","volume":"21","author":"K.O. Stanley","year":"2004","unstructured":"Stanley, K.O., Miikkulainen, R.: Competitive coevolution through evolutionary complexification. Journal of Artificial Intelligence Research\u00a021, 63\u2013100 (2004a)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"10_CR116","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"1226","DOI":"10.1007\/978-3-540-24855-2_130","volume-title":"Genetic and Evolutionary Computation \u2013 GECCO 2004","author":"K.O. Stanley","year":"2004","unstructured":"Stanley, K.O., Miikkulainen, R.: Evolving a Roving Eye for Go. In: Deb, K., et al. (eds.) GECCO 2004. LNCS, vol.\u00a03103, pp. 1226\u20131238. Springer, Heidelberg (2004b)"},{"key":"10_CR117","doi-asserted-by":"crossref","unstructured":"Stanley, K.O., Bryant, B.D., Miikkulainen, R.: Evolving adaptive neural networks with and without adaptive synapses. In: Proceeedings of the 2003 Congress on Evolutionary Computation (CEC 2003), vol.\u00a04, pp. 2557\u20132564 (2003)","DOI":"10.1109\/CEC.2003.1299410"},{"issue":"2","key":"10_CR118","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1162\/artl.2009.15.2.15202","volume":"15","author":"K.O. Stanley","year":"2009","unstructured":"Stanley, K.O., D\u2019Ambrosio, D.B., Gauci, J.: A hypercube-based indirect encoding for evolving large-scale neural networks. Artificial Life\u00a015(2), 185\u2013212 (2009)","journal-title":"Artificial Life"},{"key":"10_CR119","doi-asserted-by":"crossref","unstructured":"Steels, L.: Emergent functionality in robotic agents through on-line evolution. In: Artificial Life IV: Proceedings of the Fourth International Workshop on the Synthesis and Simulation of Living Systems, pp. 8\u201316 (1994)","DOI":"10.7551\/mitpress\/1428.003.0004"},{"key":"10_CR120","doi-asserted-by":"crossref","unstructured":"Sutton, R.S.: Integrated architectures for learning, planning, and reacting based on approximating dynamic programming. In: Proceedings of the Seventh International Conference on Machine Learning, pp. 216\u2013224 (1990)","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"10_CR121","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press (1998)","DOI":"10.1109\/TNN.1998.712192"},{"key":"10_CR122","unstructured":"Sywerda, G.: Uniform crossover in genetic algorithms. In: Proceedings of the Third International Conference on Genetic Algorithms, pp. 2\u20139 (1989)"},{"key":"10_CR123","doi-asserted-by":"crossref","unstructured":"Tan, C., Ang, J., Tan, K., Tay, A.: Online adaptive controller for simulated car racing. In: Congress on Evolutionary Computation (CEC), pp. 2239\u20132245 (2008)","DOI":"10.1109\/CEC.2008.4631096"},{"key":"10_CR124","doi-asserted-by":"crossref","unstructured":"Taylor, M.E., Whiteson, S., Stone, P.: Comparing evolutionary and temporal difference methods in a reinforcement learning domain. In: GECCO 2006: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 1321\u20131328 (2006)","DOI":"10.1145\/1143997.1144202"},{"key":"10_CR125","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1162\/neco.1994.6.2.215","volume":"6","author":"G. Tesauro","year":"1994","unstructured":"Tesauro, G.: TD-gammon, a self-teaching backgammon program achieves master-level play. Neural Computation\u00a06, 215\u2013219 (1994)","journal-title":"Neural Computation"},{"issue":"3","key":"10_CR126","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1023\/A:1007469231743","volume":"32","author":"G. Tesauro","year":"1998","unstructured":"Tesauro, G.: Comments on co-evolution in the successful learning of backgammon strategy. Machine Learning\u00a032(3), 241\u2013243 (1998)","journal-title":"Machine Learning"},{"key":"10_CR127","first-page":"1737","volume":"11","author":"P. Verbancsics","year":"2010","unstructured":"Verbancsics, P., Stanley, K.: Evolving Static Representations for Task Transfer. Journal of Machine Learning Research\u00a011, 1737\u20131769 (2010)","journal-title":"Journal of Machine Learning Research"},{"key":"10_CR128","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1007\/BF01448847","volume":"100","author":"J. Neumann Von","year":"1928","unstructured":"Von Neumann, J.: Zur Theorie der Gesellschaftsspiele Math. Annalen\u00a0100, 295\u2013320 (1928)","journal-title":"Annalen"},{"key":"10_CR129","first-page":"877","volume":"7","author":"S. Whiteson","year":"2006","unstructured":"Whiteson, S., Stone, P.: Evolutionary function approximation for reinforcement learning. Journal of Machine Learning Research\u00a07, 877\u2013917 (2006a)","journal-title":"Journal of Machine Learning Research"},{"key":"10_CR130","doi-asserted-by":"crossref","unstructured":"Whiteson, S., Stone, P.: On-line evolutionary computation for reinforcement learning in stochastic domains. In: GECCO 2006: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 1577\u20131584 (2006b)","DOI":"10.1145\/1143997.1144252"},{"issue":"1","key":"10_CR131","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1007\/s10994-005-0460-9","volume":"59","author":"S. Whiteson","year":"2005","unstructured":"Whiteson, S., Kohl, N., Miikkulainen, R., Stone, P.: Evolving keepaway soccer players through task decomposition. Machine Learning\u00a059(1), 5\u201330 (2005)","journal-title":"Machine Learning"},{"issue":"2","key":"10_CR132","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1609\/aimag.v31i2.2227","volume":"31","author":"S. Whiteson","year":"2010","unstructured":"Whiteson, S., Tanner, B., White, A.: The reinforcement learning competitions. AI Magazine\u00a031(2), 81\u201394 (2010a)","journal-title":"AI Magazine"},{"issue":"1","key":"10_CR133","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10458-009-9100-2","volume":"21","author":"S. Whiteson","year":"2010","unstructured":"Whiteson, S., Taylor, M.E., Stone, P.: Critical factors in the empirical performance of temporal difference and evolutionary methods for reinforcement learning. Autonomous Agents and Multi-Agent Systems\u00a021(1), 1\u201327 (2010b)","journal-title":"Autonomous Agents and Multi-Agent Systems"},{"key":"10_CR134","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1023\/A:1022674030396","volume":"13","author":"D. Whitley","year":"1993","unstructured":"Whitley, D., Dominic, S., Das, R., Anderson, C.W.: Genetic reinforcement learning for neurocontrol problems. Machine Learning\u00a013, 259\u2013284 (1993)","journal-title":"Machine Learning"},{"key":"10_CR135","doi-asserted-by":"crossref","unstructured":"Whitley, D., Gordon, S., Mathias, K.: Lamarckian evolution, the Baldwin effect and function optimization. In: Parallel Problem Solving from Nature - PPSN III, pp. 6\u201315 (1994)","DOI":"10.1007\/3-540-58484-6_245"},{"key":"10_CR136","unstructured":"Wiegand, R., Liles, W., De Jong, K.: An empirical analysis of collaboration methods in cooperative coevolutionary algorithms. In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO), pp. 1235\u20131242 (2001)"},{"key":"10_CR137","doi-asserted-by":"crossref","unstructured":"Wieland, A.: Evolving neural network controllers for unstable systems. In: International Joint Conference on Neural Networks, vol\u00a02, pp. 667\u2013673 (1991)","DOI":"10.1109\/IJCNN.1991.155416"},{"issue":"2","key":"10_CR138","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1162\/evco.1995.3.2.149","volume":"3","author":"S. Wilson","year":"1995","unstructured":"Wilson, S.: Classifier fitness based on accuracy. Evolutionary Computation\u00a03(2), 149\u2013175 (1995)","journal-title":"Evolutionary Computation"},{"key":"10_CR139","unstructured":"Wilson, S.: Function approximation with a classifier system. In: GECCO 2001: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 974\u2013982 (2001)"},{"key":"10_CR140","doi-asserted-by":"crossref","unstructured":"Wolpert, D., Tumer, K.: Optimal payoff functions for members of collectives. Modeling Complexity in Economic and Social Systems, 355 (2002)","DOI":"10.1142\/9789812777263_0020"},{"key":"10_CR141","unstructured":"Yamasaki, K., Sekiguchi, M.: Clear explanation of different adaptive behaviors between Darwinian population and Lamarckian population in changing environment. In: Proceedings of the Fifth International Symposium on Artificial Life and Robotics, vol.\u00a01, pp. 120\u2013123 (2000)"},{"issue":"9","key":"10_CR142","doi-asserted-by":"crossref","first-page":"1423","DOI":"10.1109\/5.784219","volume":"87","author":"X. Yao","year":"1999","unstructured":"Yao, X.: Evolving artificial neural networks. Proceedings of the IEEE\u00a087(9), 1423\u20131447 (1999)","journal-title":"Proceedings of the IEEE"},{"key":"10_CR143","unstructured":"Yong, C.H., Miikkulainen, R.: Coevolution of role-based cooperation in multi-agent systems. Tech. Rep. AI07-338, Department of Computer Sciences, The University of Texas at Austin (2007)"},{"issue":"3","key":"10_CR144","first-page":"199","volume":"7","author":"B. Zhang","year":"1993","unstructured":"Zhang, B., Muhlenbein, H.: Evolving optimal neural networks using genetic algorithms with Occam\u2019s razor. Complex Systems\u00a07(3), 199\u2013220 (1993)","journal-title":"Complex Systems"},{"key":"10_CR145","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"592","DOI":"10.1007\/3-540-36181-2_59","volume-title":"Biologically Motivated Computer Vision","author":"J.-C. Zufferey","year":"2002","unstructured":"Zufferey, J.-C., Floreano, D., van Leeuwen, M., Merenda, T.: Evolving vision-based flying robots. In: B\u00fclthoff, H.H., Lee, S.-W., Poggio, T.A., Wallraven, C. (eds.) BMCV 2002. LNCS, vol.\u00a02525, pp. 592\u2013600. Springer, Heidelberg (2002)"}],"container-title":["Adaptation, Learning, and Optimization","Reinforcement Learning"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-27645-3_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T13:03:16Z","timestamp":1742648596000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-27645-3_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642276446","9783642276453"],"references-count":145,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-27645-3_10","relation":{},"ISSN":["1867-4534","1867-4542"],"issn-type":[{"value":"1867-4534","type":"print"},{"value":"1867-4542","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012]]}}}