臺灣博碩士論文加值系統

在本篇論文中，提出了改良安全性增強式學習為基礎的自我適應進化演算法應用於TSK型式模糊類神經控制器的設計上。本論文所提出的方法可以改善增強式學習的訊號設計以及傳統的進化演算法。本論文的方法可以分為兩部份來探討。首先，在第一部份中本論文提出了自我適應進化演算法來解決傳統進化演算法所遭遇到的問題，如: 1)將所有模糊規則編碼至一條染色體中；2)模糊法則需要在學習前指定；3)無法局部考量單一模糊法則。在第二部份中，本論文提出了改良安全性增強式學習。在改良安全性增強式學習中透過兩個不同的策略-判斷以及衡量策略來決定增強式訊號。此外，Lyapunov 穩定性分析也被考量在本論文所提出的改良安全性增強式學習。在本文中提出了單桿以及雙桿倒單擺控制系統來驗證本論文所提出方法的效能，從實驗結果中可以發現，相較於其他進化演算法，本論文所提出的方法有較佳的效能。

In this dissertation, improved safe reinforcement learning based self adaptive evolutionary algorithms (ISRL-SAEAs) are proposed for TSK-type neuro-fuzzy controller design. The ISRL-SAEAs can improve not only the reinforcement signal designed but also traditional evolutionary algorithms. There are two parts in the proposed ISRL-SAEAs. In the first part, the SAEAs are proposed to solve the following problems: 1) all the fuzzy rules are encoded into one chromosome; 2) the number of fuzzy rules has to be assigned in advance; and 3) the population cannot evaluate each fuzzy rule locally. The second part of the ISRL-SAEAs is the ISRL. In the ISRL, two different strategies (judgment and evaluation) are used to design the reinforcement signal. Moreover the Lyapunov stability is considered in ISRL. To demonstrate the performance of the proposed method, the inverted pendulum control system and tandem pendulum control system are presented. As shown in simulation, the ISRL-SAEAs perform better than other reinforcement evolution methods.

Chinese Abstract i
English Abstract ii
Chinese Acknowledgements iii
Contents v
List of Figures vii
List of Tables ix

Chapter 1 Introduction 1
1.1 Motivation 1
1.2 Review of previous works 3
1.3 Research Purpose 7
1.4 Approach 12
1.5 Overview of Dissertation 12

Chapter 2 Foundations 14
2.1 Neuro-Fuzzy Controller 14
2.2 Reinforcement Learning 18
2.3 Lyapunov Stability 21
2.4 Evolution Learning 23
2.4.1 Genetic algorithm 23
2.4.2 Cooperative Coevolution 26
2.4.3 Symbiotic Evolution 27


Chapter 3 Self Adaptive Evolutionary Algorithms 31
3.1 Self Adaptive Hybrid Evolutionary Algorithm 31
3.2 Self Adaptive Groups Cooperation Based Symbiotic Evolution 40
3.3 Self adaptive Groups Based Symbiotic Evolution using FP-growth Algorithm 53
Chapter 4 Improved Safe Reinforcement Learning 69
4.1 Safe Reinforcement Learning 70
4.2 Structure of the ISRL 72
4.3 Two Strategies in the ISRL 75

Chapter 5 Control Illustration 79
5.1 Inverted Pendulum Control System 80
5.1.1 Evaluating performance of the HEA 83
5.1.2 Evaluating performance of the SACG-SE 95
5.1.3 Evaluating performance of the SAG-SEFA 102
5.2 Tandem Pendulum Control System 109
5.2.1 Evaluating performance of the HEA 113
5.2.2 Evaluating performance of the SACG-SE 121
5.2.3 Evaluating performance of the SAG-SEFA 125

Chapter 6 Conclusion 130
6. 1 Contributions 130
6. 2 Future Research 133

Bibliography 134
Vita 145
Publication List 146

[1] C. T. Lin and C. S. G. Lee, Neuro-fuzzy Systems: A Neuro-Fuzzy Synergism to Intelligent System, NJ:Prentice-Hall, 1996.
[2] G. G. Towell and J. W. Shavlik, “Extracting refined rules from knowledge-based neural networks,” Mach. Learn., vol. 13, pp. 71-101, 1993.
[3] C. J. Lin and C. T. Lin, “An ART-based fuzzy adaptive learning control network,” IEEE Trans. Fuzzy systs., vol. 5, no. 4, pp. 477-496, 1997.
[4] L. X. Wang and J. M. Mendel, “Generating fuzzy rules by learning from examples,” IEEE Trans. Syst., Man, Cybern., vol. 22, no. 6, pp. 1414-1427, 1992.
[5] T. Takagi and M. Sugeno, “Fuzzy identification of systems and its applications to modeling and control,” IEEE Trans. Syst., Man, Cybern., vol. 15, no. 1, pp. 116-132, 1985.
[6] C. F. Juang and C. T. Lin, “An on-line self-constructing neuro-fuzzy inference network and its applications,” IEEE Trans. Fuzzy Systs., vol. 6, no.1, pp. 12-31, 1998.
[7] J. S. R. Jang, “ANFIS: Adaptive-network-based fuzzy inference system,” IEEE Trans. Syst., Man, and Cybern., vol. 23, no. 3, pp. 665-685, 1993.
[8] F. J. Lin, C. H. Lin, and P. H. Shen, “Self-constructing fuzzy neural network speed controller for permanent-magnet synchronous motor drive,” IEEE Trans. Fuzzy Systs., vol. 9, no. 5, pp. 751-759, 2001.
[9] H. Takagi, N. Suzuki, T. Koda, and Y. Kojima, “Neural networks designed on approximate reasoning architecture and their application,” IEEE Trans. Neural Networks, vol. 3, no. 5, pp. 752-759, 1992.
[10] E. Mizutani and J. S. R. Jang, “Coactive neuro-fuzzy modeling,” in Proc. IEEE Int. Conf. Neural Networks, Perth, WA , USA, vol. 2, pp. 760-765, November 27-December 1, 1995.
[11] C. J. Lin and C. C. Chin, “Prediction and identification using wavelet-based recurrent fuzzy neural networks,” IEEE Trans. Syst., Man, Cybern., Part B, vol. 34, no. 5, pp. 2144-2154, 2004.
[12] K. S. Narendra and K. Parthasarathy, “Identification and control of dynamical systems using neural networks,” IEEE Trans. Neural Networks, vol. 1, no. 1, pp. 4-27, 1990.
[13] C. F. Juang and C. T. Lin, “A recurrent self-organizing neuro-fuzzy inference network,” IEEE Trans. Neural Networks, vol. 10, no. 4, pp.828-845, 1999.
[14] P. A. Mastorocostas and J. B. Theocharis, “A recurrent fuzzy-neural model for dynamic system identification,” IEEE Trans. Syst., Man, Cybern., Part B, vol. 32, no. 2, pp. 176-190, 2002.
[15] X. Xu and H. G. He, “Residual-gradient-based neural reinforcement learning for the optimal control of an acrobat,” in Proc. IEEE Int. Symposium on Intelligent Control, Vancouver, Canada, pp. 758-763, October 27-30, 2002.
[16] O. G.rigore, “Reinforcement learning neural network used in control of nonlinear systems,” in Proc. IEEE Int. Conf. Industrial Technology, vol. 1, Goa, India, pp. 662-665, January 19-22, 2000.
[17] A. G. Barto, R. S. Sutton, and C. W. Anderson, “Neuron like adaptive elements that can solve difficult learning control problem,” IEEE Trans. Syst., Man, Cybern., vol. 13, no 5, pp. 834-847, 1983.
[18] C. J. Lin, “A GA-based neural network with supervised and reinforcement learning,” Journal of the Chinese Institute of Electrical Engineering, vol. 9, no. 1, pp. 11-25, 2002.
[19] X. W. Yan, Z.D. Deng, and Z.Q. Sun, “Competitive Takagi-Sugeno fuzzy reinforcement learning,” in Proc. IEEE Int. Conf. Control Applications, Mexico City, Mexico, pp. 878-883, September 5-7, 2001.
[20] C. J. Lin and Y. C. Hsu, “Reinforcement hybrid evolutionary learning for recurrent wavelet-based neuro-fuzzy systems,” IEEE Trans. on Fuzzy Systems, vol. 15, no. 4, pp. 729-745, 2007.
[21] H. R. Berenji and P. Khedkar, “Learning and tuning fuzzy logic controllers through reinforcements,” IEEE Trans. Neural Networks, vol. 3, no. 5, pp. 724-740, 1992.
[22] D. E. Goldberg, Genetic Algorithms in Search Optimization and Machine Learning, Reading, MA: Addison-Wesley, 1989.
[23] J. K. Koza, Genetic Programming: On the Programming of Computers by Means of Natural Selection, Cambridge, MA: MIT Press, 1992.
[24] L. J. Fogel, “Evolutionary programming in perspective: The top-down view,” in Computational Intelligence: Imitating Life, J. M. Zurada, R. J. Marks II, and C. Goldberg, Eds. Piscataway, NJ: IEEE Press, 1994.
[25] I. Rechenberg, “Evolution strategy,” in Computational Intelligence: Imitating Life, J. M. Zurada, R. J. Marks II, and C. Goldberg, Eds. Piscataway, NJ: IEEE Press, 1994.
[26] C. L. Karr, “Design of an adaptive fuzzy logic controller using a genetic algorithm,” in Proc. Int. Conf. Genetic Algorithms, San Diego, CA, USA, pp. 450-457, July 1991.
[27] B. Carse, T. C. Fogarty, and A. Munro, “Evolving fuzzy rule based controllers using genetic algorithms,” Fuzzy Sets and Systems, vol. 80, no. 3, pp. 273-293, 1996.
[28] C. T. Lin and C. P. Jou, “GA-based fuzzy reinforcement learning for control of a magnetic bearing system,” IEEE Trans. Syst., Man, Cybern., Part B, vol. 30, no. 2, pp. 276-289, 2000.
[29] C. F. Juang, J. Y. Lin and C. T. Lin, “Genetic reinforcement learning through symbiotic evolution for fuzzy controller design,” IEEE Trans. Syst., Man, Cybern., Part B, vol. 30, no. 2, pp. 290-302, 2000.
[30] S. Bandyopadhyay, C. A. Murthy, and S. K. Pal, “VGA-classifier: design and applications,” IEEE Trans. Syst., Man, and Cybern., Part B, vol. 30, no. 6, pp. 890-895, 2000.
[31] D. Y. Wang, H. C. Chuang, Y. J. Xu, and C. J. Lin, “A novel evolution learning for recurrent wavelet-based neuro-fuzzy networks,” in Proc. IEEE Int. Conf. Fuzzy Systems, Reno, NV, USA, pp. 1092-1097, May 25-25, 2005.
[32] T. J. Perkins, and A. G. Barto, “Lyapunov design for safe reinforcement learning,” Journal of Machine Learning Research, vol. 3, no. 4-5, pp. 803-832, 2003.
[33] C. K. Ting, C. N. Lee, H. C. Chang, and J. S. Wu, “Wireless heterogeneous transmitter placement using multiobjective variable-length genetic algorithm,” IEEE Trans. Syst., Man, Cybern., Part B, vol. 39, no. 4, pp. 945-958, 2009.
[34] E. Saeidpour, V. S. Parizy, M. Abedi, and H. Rastegar, “Complete, integrated and simultaneously design for STATCOM fuzzy controller with variable length genetic algorithm for voltage profile improvement,” in Proc. Int. Conf. Harmonics and Quality of Power, Wollongong, NSW, Australia, pp. 1-7, September 28-October 1, 2008.
[35] Y. C. Hsu and S. F. Lin, “Reinforcement self-adaptive evolutionary algorithm for fuzzy systems design,” in Proc. IEEE Int. Conf. Industrial Technology, Chengdu, China, pp. 1-6, April 21-24, 2008.
[36] I. Saha, U. Maulik, and S. Bandyopadhyay, “A new differential evolution based fuzzy clustering for automatic cluster evolution,” in Proc. IEEE Int. Conf. Advance Computing, Patiala, India, pp. 706-711, March 6-7, 2009.
[37] K. S. Tang, “Genetic algorithms in modeling and optimization,” Ph. D. Dissertation, Dep. Electronic Engineering, City Univ. Hong Kong, Hong Kong, 1996.
[38] M. Ma and L. B. Zhang, “Optimizing a fuzzy neural network with a hierarchical genetic algorithm,” in Proc. IEEE Int. Conf. Machine Learning and Cybernetics, Hong Kong, China, vol. 5, pp. 2812-2815, August 19-22, 2007.
[39] R. Kumar, K. Izui, Y. Masataka, and S. Nishiwaki, “Multilevel redundancy allocation optimization using hierarchical genetic algorithm,” IEEE Trans. Reliability, vol. 57, no. 4, pp. 650-661, 2008.
[40] F. J. Gomez, “Robust non-linear control through neuroevolution,” Ph. D. Disseration, Dep. Computer Sciences, Univ. Texas of Austin, USA, 2003.
[41] F. Gomez and J. Schmidhuber, “Co-evolving recurrent neurons learn deep memory POMDPs,” in Proc. Conf. Genetic and Evolutionary Computation, Washington, DC, USA, pp. 491-498, June 25-29, 2005.
[42] J. Li and Z. J. Miao, “Entertainment oriented intelligent virtual environment with agent and neural networks,” in Proc. IEEE Int. Workshop on Haptic, Audio and Visual Environments and Games, Ottawa, Canada, pp. 90-95, October12-14, 2007.
[43] C. F. Juang, “Combination of online clustering and Q-value based GA for reinforcement fuzzy system design,” IEEE Trans. Fuzzy Systs., vol. 13, no. 3, pp. 289-302, 2005.
[44] C. J. Lin and Y. J. Xu, “Efficient reinforcement learning through dynamical symbiotic evolution for TSK-type fuzzy controller design,” International Journal of General Systems, vol. 34, no.5, pp. 559-578, 2005.
[45] D. T. Larose, Discovering Knowledge in Data: An Introduction to Data Mining, Wiley Publishers, 2004.
[46] U. Fayyad, “Data mining and knowledge discovery in databases: implications for scientific database,” in Proc. Int. Conf. Scientific and Statistical Database Management, Olympia, Greece, pp. 2-11, August 11-13, 1997.
[47] M. Chen and Z. W. Yao, “Classification techniques of neural networks using improved genetic algorithms,” in Proc. Int. Conf. Genetic and Evolutionary Computing, Hubei, China, pp. 115-119, September 25-26, 2008.
[48] Q. L. Guo and M. Zhang, “A novel approach for fault diagnosis of steam turbine based on neural network and genetic algorithm,” in Proc. IEEE Int. Conf. Neural Networks, Hong Kong, China, pp. 25-29, June 1-8, 2008.
[49] R. Agrawal and R. Srikant, “Fast algorithm for mining association rules,” in Proc. Int .Conf. Very Large Data Bases, Santiago, Chile, pp. 487-499, September 12-15, 1994.
[50] J. Han, J. Pei, and Y. Yin, “Mining frequent patterns without candidate generation,” in Proc. Int. Conf. Management of Data, Dallas, Texas, USA, pp.1-12, May 16-18, 2000.
[51] T. P. Hong, C. S. Kuo, and S. C. Chi, “A data mining algorithm for transaction data with quantitative values,” Intelligent Data Analysis, vol. 3, no. 5, pp. 363-376, 1999.
[52] Y. T. Wu, Y. J. An, J. Geller, and Y. T. Wu, “A data mining based genetic algorithm,” in Proc. IEEE Int. Workshop on Software Technologies for Future Embedded and Ubiquitous Systems and Collaborative Computing, Integration, and Assurance, Gyeongju, Korea, pp. 6, April 27-28, 2006.
[53] K. G. Srinivasa, M. Jagadish, K. R. Venugopal, and L. M. Patnaik, “Data mining based query processing using rough sets and genetic algorithms,” in Proc. IEEE Symposium on Computational Intelligence and Data Mining, Honolulu, USA, pp. 275-282, March 1-April 5 , 2007.
[54] S. P. Dai and P. Zhang, “A data mining algorithm in distance learning,” in Proc. IEEE Int. Conf. Computer Supported Cooperative Work in Design, Xi'an, China, pp.1014-1017, April 16-18, 2008.
[55] C. J. Lin and Y. J. Xu, “The design of TSK-type fuzzy controllers using a new hybrid learning approach,” International Journal of Adaptive Control and Signal Processing, vol. 20, no. 1, pp. 1-25, 2006.
[56] K. C. Cheok and N. K. Loh, “A ball-balancing demonstration of optimal and disturbance-accommodating control,” IEEE Contr. Syst. Mag., vol. 7, no. 1, pp. 54-57, 1987.
[57] D. Whitley, S. Dominic, R. Das, and C. W. Anderson, “Genetic reinforcement learning for neuro control problems,” Mach. Learn., vol. 13, pp. 259-284, 1993.
[58] A. Wieland, “Evolving neural network controllers for unstable systems,” in Proc. IEEE Int. Conf. Neural Networks, Seattle, WA , USA, vol. 2, pp. 667-673, July 8-14, 1991.
[59] X. Xin and M. Kaneda, “Analysis of the energy-based control for swinging up two pendulums,” IEEE Trans. Automatic Control, vol. 50, no. 5, pp. 679-684, 2005.
[60] X. Xin and M. Kaneda, “Analysis of the energy based control for swinging up two pendulums,” in Proc. IEEE Int. Conf. Decision and Control, Maui, Hawaii, USA, vol. 5, pp. 4688-4693, December 9-12, 2003.
[61] R. A. Howard, Dynamic Programming and Markov Processes, Cambridge, MA: MIT Press, 1960.
[62] R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, Cambridge, MA: MIT Press, 1998.
[63] C. J. C. H. Watkins, “Learning from delayed rewards,” Ph. D. Dissertation, Univ. Cambridge, England, 1989.
[64] C. J. C. H. Watkins and P. Dayan, “Q-learning,” Mach. Learn., vol. 8, no. 3, pp. 279-292, 1992.
[65] G. A. Rummery and M. Niranjan, On-line Q-learning using connectionist systems, Technical Report CUED/F-INFENG/TR-166, Dep. Eng., Univ. Cambridge, 1994.
[66] L. J. Lin, “Reinforcement learning for robots using neural networks,” Ph. D. Dissertation, Dep. Computer Sciences, Univ. Carnegie Mellon, Pittsburg, 1993.
[67] R. H. Crites and A. G. Barto, “Improving elevator performance using reinforcement learning,” Advances in Neural Information Processing System, vol. 8, pp. 1017-1023, 1996.
[68] R. S. Sutton, “Generalization in reinforcement learning: successful examples using sparse coarse coding,” Advances in Neural Information Processing System, vol. 8, pp. 1038-1044, 1996.
[69] H. K. Khalil, Nonlinear systems, NJ: Prentice-Hall, 2002.
[70] N. Chaiyaratana and A. M. S. Zalzala, “Recent developments in evolutionary and genetic algorithms: theory and applications,” in Proc. IEEE Int. Conf. Genetic Algorithms in Engineering Systems: Innovations and Applications, Glasgow, United Kingdom, pp. 270-277, September 2-4, 1997.
[71] D. Wicker, M. M. Rizki, and L. A. Tamburino, “The multi-tiered tournament selection for evolutionary neural network synthesis,” in Proc. IEEE Int. Symposium on Combinations of Evolutionary Computation and Neural Networks, San Antonio, USA, pp. 207-215, May 11-13, 2000.
[72] Y. P. Zou, Z. K. Mi, and M. H. Xu, “Dynamic load balancing based on roulette wheel selection,” in Proc. IEEE Int. Conf. Communications, Circuits and Systems, Guilin, China, vol. 3, pp.1732-1734, June 25-28, 2006.
[73] P. M. Godley, D. E. Cairns, J. Cowie, and J. McCall, “Fitness directed intervention crossover approaches applied to bio-scheduling problems,” in Proc. IEEE Int. Symposium on Computational Intelligence in Bioinformatics and Computational Biology, Sun Valley, USA, pp. 120-127, September 15-17, 2008.
[74] S. Su and D. H. Zhan, “New genetic algorithm for the fixed charge transportation problem,” in Proc. IEEE Int. World Congress on Intelligent Control and Automation, Dalian, China, vol. 2, pp. 7039-7043, June 21-23, 2002.
[75] W. Y. Wang, T. T. Lee, C. C. Hsu, and Y. H. Li, “GA-based learning of BMF fuzzy-neural network,” in Proc. IEEE Int. Conf. Fuzzy Systems, Honolulu, USA, pp. 1234-1239, May 12-17, 2002.
[76] G. Lin and X. Yao, “Analysing crossover operators by search step size,” in Proc. IEEE Int. Conf. Evolutionary Computation, Indianapolis, USA, pp. 107-110, April 13-16, 1997.
[77] C. P. Chen, S. P. Koh, I. B. Aris, F. Y. C. Albert, and S. K. Tiong, “Path optimization using genetic algorithm in laser scanning system,” in Proc. IEEE Int. Symposium on Information Technology, Kuala Lumpur, Malaysia, vol. 3, pp. 1-5, August 26-28, 2008.
[78] C. J. Hsu, C. Y. Huang, and T. Y. Chen, “A modified genetic algorithm for parameter estimation of software reliability growth models,” in Proc. IEEE Int. Symposium on Software Reliability Engineering, Seattle, WA, USA, pp. 281-282, November 10-14, 2008.
[79] P. Luo, J. F. Teng, J. H. Guo, and Q. Li, “An improved genetic algorithm and its performance analysis,” in Proc. IEEE Int. Conf. Info-tech and Info-net, Beijing, China, vol. 4, pp. 329-333, October 29-November 1, 2001.
[80] G. W. Greenwood, “Adapting mutations in genetic algorithms using gene flow principles,” in Proc. IEEE Congress on Evolutionary Computation, Canberra, Australia vol. 2, pp.1392-1397, December 8-12, 2003.
[81] H. J. Lee, Y. S. Ma, and Y. R. Kwon, “Empirical evaluation of orthogonality of class mutation operators,” in Proc. IEEE Int. Conf. Software Engineering, Busan, Korea, pp. 512-518, November 30-Decmber 3, 2004.
[82] N. S. Chaudhari, A. Purohit, and A. Tiwari, “A multiclass classifier using Genetic Programming,” in Proc. IEEE Int. Conf. Control, Automation, Robotics and Vision, Hanoi, Vietnam, pp. 1884-1887, December 17-20, 2008.
[83] N. Gomez Bias, L. F. Mingo, and J. Castellanos, “Networks of evolutionary processors with a self-organizing learning,” in Proc. IEEE Int. Conf. Computer Systems and Applications, Doha, Qatar, pp. 917-918, March 31-April 4, 2008.
[84] S. Abedi and R. Tafazolli, “Genetically modified multiuser detection for code division multiple access systems,” IEEE Journal on Selected Areas, pp. 1884-1887, 2008.
[85] P. J. Darwen, “Co-evolutionary learning by automatic modularization with speciation,” Ph. D. Dissertation, Univ. South Wales, 1996.
[86] J. B. Pollack, A. D. Blair, and M. Land, “Coevolution of a backgammon player,” in Proc. Int. Conf. Artificial Life: Synthesis and Simulation of Living Systems, Nara, Japan, pp. 92-98, May 1996.
[87] G. Miller and D. Cliff, Co-evolution of pursuit and evasion i: Biological and game-theoretic foundations, Technical Report CSRP311, Dep. Cognitive and Computing Sciences, Univ. Sussex, Brighton, UK, 1994.
[88] D. Grady, “The vision thing: mainly in the brain,” Discover, vol. 14, pp.57-66, 1993.
[89] J. H. Holland, and J. S. Reitman, Cognitive systems based on adaptive algorithms, In Waterman, D. A., and Hayes-Roth, F., editors, Pattern-Directed Inference Systems. New York: Academic Press, 1978.
[90] R. Eriksson and B. Olsson, “Cooperative coevolution in inventory control optimization,” in Proc. Int. Conf. Artificial Neural Networks and Genetic Algorithms, Norwich, UK, pp. 583-587, April 1997.
[91] J. Horn, D. E. Goldberg, and K. Deb, “Implicit niching in a learning classifier system: nature’s way,” Evolutionary Computation, vol. 2, no. 1, pp. 37-66, 1994.
[92] J. Paredis, “Coevolutionary computation,” Artificial Life, vol. 2, no. 4, pp. 355-375, 1995.
[93] B. A. Whitehead and T. D. Choate, “Cooperative-competitive genetic evolution of radial basis function centers and widths for time series prediction,” IEEE Trans. Neural Networks, vol. 7, no. 4, pp. 869-880, 1996.
[94] M. A. Potter and K. A. De Jong, “Evolving neural networks with collaborative species,” in Proc. Conf. Summer Computer Simulation, Ottawa, Ontario, Canada , pp. 1-7, July 24-26, 1995.
[95] D. E. Moriarty, “Symbiotic evolution of neural networks in sequential decision tasks,” Ph. D. Dissertation, Dep. of Computer Sciences, Univ. Texas at Austin, USA, Technical Report UT-AI97-257, 1997.
[96] D. E. Moriarty and R. Miikkulainen, “Efficient reinforcement learning through symbiotic evolution,” Mach. Learn., vol. 22, pp. 11-32, 1996.
[97] R. E. Smith, S. Forrest, and A. S. Perelson, “Searching for diverse, cooperative populations with genetic algorithms,” Evol. Comput., vol. 1, no. 2, pp. 127-149, 1993.
[98] Z. Michalewicz, Genetic Algorithms+Data Structures=Evolution Programs, New York: Springer-Verlag, 1999.
[99] R. Tanese, “Distributed genetic algorithm,” in Proc. Int. Conf. Genetic Algorithms, San Mateo, USA, pp. 434-439, December 1989.
[100] J. Arabas, Z. Michalewicz, and J. Mulawka, “GAVaPS—A genetic algorithm with varying population size,” in Proc. IEEE Int. Conf. Evolutionary Computation, Orlando, USA, pp. 73-78, June 27-29, 1994.
[101] G. R. Harik, F. G. Lobo and D. E. Goldberg, “The compact genetic algorithm,” IEEE Trans. Evolutionary Computation, vol. 3, no. 4, pp. 287-297, 1999.
[102] K. Y. Lee, X. M. Bai, and Y. M. Park, “Optimization method for reactive power planning by using a modified simple genetic algorithm,” IEEE Trans. Power Systems, vol. 10, no. 4, pp. 1843-1850, 1995.
[103] K. A. De Jong, “Analysis of the behavior of a class of genetic adaptive systems,” Ph. D. Dissertation, Dep. Computer and Communication Sciences, Univ. Michigan, Ann Arbor, MI, 1975.
[104] J. J. Grefenstette, “Optimization of control parameters for genetic algorithms,” IEEE Trans. Syst., Man, Cybern., vo1. 6, no. 1, pp. 122-128, 1986.