Abstract
Evolution strategies (ESs) are a special class of probabilistic, direct, global optimization methods. They are similar to genetic algorithms but work in continuous spaces and have the additional capability of self-adapting their major strategy parameters. This paper presents the most important features of ESs, namely their self-adaptation, as well as their robustness and potential for parallelization which they share with other evolutionary algorithms.
Besides the early (1 + 1)-ES and its underlying theoretical results, the modern (μ + λ)-ES and (μ, λ)-ES are presented with special emphasis on the self-adaptation of strategy parameters, a mechanism which enables the algorithm to evolve not only the object variables but also the characteristics of the probability distributions of normally distributed mutations. The self-adaptation property of the algorithm is also illustrated by an experimental example.
The robustness of ESs is demonstrated for noisy fitness evaluations and by its application to discrete optimization problems, namely the travelling salesman problem (TSP).
Finally, the paper concludes by summarizing existing work and general possibilities regarding the parallelization of evolution strategies and evolutionary algorithms in general.
Similar content being viewed by others
References
Amdahl, G. (1967). Validity of the single processor approach to achieving large scale computing capabilities. In AFIPS Conference Proceedings, Volume 30, Washington, D.C., pp. 483–485. Thompson Books.
Bäck, T. (1992). Self-adaptation in genetic algorithms. In Proceedings of the First European Conference on Artificial Life, ed. F. J. Varela and P. Bourgine, pp. 263–271. MIT Press, Cambridge, MA.
Bäck, T., Hoffmeister, F. and Schwefel, H.-P. (1992). Applications of evolutionary algorithms. Report of the Systems Analysis Research Group SYS-2/92, Universität Dortmund, Fachbereich Informatik.
Bäck, T., Rudolph, G. and Schwefel, H.-P. (1993). Evolutionary programming and evolution strategies: Similarities and differences. In Proceedings of the 2nd Annual Conference on Evolutionary Programming, ed. D. B. Fogel and W. Atmar, pp. 11–22. Evolutionary Programming Society, San Diego, CA.
Bäck, T. and Schwefel, H.-P. (1993). An overview of evolutionary algorithms for parameter optimization. Evolutionary Computation, 1, 1–23.
Belew, R. K. and Booker, L. B. (eds) (1991). Proceedings of the 4th International Conference on Genetic Algorithms. Morgan Kaufmann, San Mateo, CA.
Bernutat-Buchmann, U. and Krieger, J. (1984). Evolution strategies in numerical optimization on vector computers. In Parallel Computing 83, ed. Feilmeier, Joubert, and Schendel, pp. 99–105. Elsevier, Amsterdam.
Bethke, A. D. (1981). Genetic Algorithms as Function Optimizers. Ph. D. thesis, University of Michigan. Diss. Abstr. Int. 41(9), 3503B, University Microfilms No. 8106101.
Bormann, A. (1989). Parallelisierungsmöglichkeiten für direkte Optimierungsverfahren auf Transputersystemen. Diplomarbeit, Universität Dortmund, Germany.
Born, J. (1978). Evolutionsstrategien zur numerischen Lösung von Adaptationsaufgaben. Dissertation A, Humboldt-Universität, Berlin.
Cohoon, J. P., Hedge, S. U., Martin, W. N. and Richards, D. S. (1987). Punctuated equilibria: a parallel genetic algorithm. See Grefenstette (1987)Proceedings of the 2nd International Conference on Genetic Algorithms and Their Applications. Lawrence Erlbaum Associates, Hillsdale, NJ}, pp. 148–154.
Collins, R. J. and Jefferson, D. R. (1991). Selection in massively parallel genetic algorithms. See Belew and Booker (1991)Proceedings of the 4th International Conference on Genetic Algorithms. Morgan Kaufmann, San Mateo, CA}, pp. 249–256.
Davidor, Y. (1991). A naturally occuring niche and species phenomenon: The model and first results. See Belew and Booker (1991)Proceedings of the 4th International Conference on Genetic Algorithms. Morgan Kaufmann, San Mateo, CA}, pp. 257–263.
DeJong, K. A. D. (1975). An Analysis of the Behaviour of a Class of Genetic Adaptive Systems. Ph. D. thesis, University of Michigan. Diss. Abstr. Int. 36(10), 5140B, University Micro-films No. 76-9381.
Fogel, D. B. (1991). System Identification through Simulated Evolution: A Machine Learning Approach to Modeling. Ginn Press, Needham Heights.
Fogel, D. B. (1992). Evolving Artificial Intelligence. Ph. D. thesis, University of California, San Diego, CA.
Fogel, L. J., Owens, A. J. and Walsh, M. J. (1966). Artificial Intelligence through Simulated Evolution. Wiley, New York.
Goldberg, D. E. (1989). Genetic Algorithms in Search, Optimization and Machine Learning. Addison Wesley, Reading, MA.
Gorges-Schleuter, M. (1989). ASPARAGOS: an asynchronous parallel genetic optimization strategy. See Schaffer (1989), pp. 422–427.
Grefenstette, J. J. (1986). Optimization of control parameters for genetic algorithms. IEEE Transactions on Systems, Man and Cybernetics 16, 122–128.
Grefenstette, J. J. (ed.) (1987). Proceedings of the 2nd International Conference on Genetic Algorithms and Their Applications. Lawrence Erlbaum Associates, Hillsdale, NJ.
Guliaev, Y. V., Bukatova, I. L., Golubeva, L. N. and Krapivin, V. F. (1989). Evolutionary informatics and ‘intelligent’ special processors. Academy of Sciences of the USSR, Institute of Radio Engineering and Electronics. Preprint.
Heckler, R. and Schwefel, H.-P. (1978). Superimposing direct search methods for parameter optimization onto dynamic simulation models. In Proceedings of the Winter Simulation Conference, ed. H. Highland, N. Nielsen, and L. Hull. Miami Beach FL, Volume 1, pp. 173–181.
Herdy, M. (1992). Reproductive isolation as strategy parameter in hierarchically organized evolution strategies. See Männer and Manderick (1992)}Parallel Problem Solving from Nature 2. Elsevier, Amsterdam}, pp. 207–217.
Hoffmeister, F. (1991). Scalable parallelism by evolutionary algorithms. In Parallel Computing and Mathematical Optimization, ed. M. Grauer and D. B. Pressmar, Lecture Notes in Economics and Mathematical Systems 367, pp. 177–198. Springer-Verlag, Berlin.
Hoffmeister, F. and Bäck, T. (1991). Genetic algorithms and evolution strategies: Similarities and differences. See Schwefel and Männer (1991)Parallel Problem Solving from Nature—Proceedings 1st Workshop PPSN I. Lecture Notes in Computer Science, 496. Springer-Verlag, Berlin}, pp. 447–461.
Hoffmeister, F. and Bäck, T. (1992). Genetic self-learning. In Proceedings of the First European Conference on Artificial Life, Ed. F. J. Varela and P. Bourgine, pp. 227–235. MIT Press, Cambridge, MA.
Holland, J. H. (1975). Adaptation in Natural and Artificial Systems. University of Michigan Press, Ann Arbor, MI.
Kottkamp, R. (1989). Nichtlineare Optimierung unter Verwendung verteilter, paralleler Prozesse in einem Local Area Network (LAN). Diplomarbeit, Universität Dortmund, Germany.
Kursawe, F. (1991). A variant of evolution strategies for vector optimization. See Schwefel and Männer (1991)Parallel Problem Solving from Nature—Proceedings 1st Workshop PPSN I. Lecture Notes in Computer Science, 496. Springer-Verlag, Berlin}, pp. 193–197.
Lichtfuss, H. J. (1965). Evolution eines Rohrkrümmers. Diplomarbeit, Technische Universität Berlin.
Lohmann, R. (1991). Application of evolution strategy in parallel populations. See Schwefel and Männer (1991)Parallel Problem Solving from Nature—Proceedings 1st Workshop PPSN I}. Lecture Notes in Computer Science, 496. Springer-Verlag, Berlin}, pp. 198–208.
Männer, R. and Manderick, B. (eds.) (1992). Parallel Problem Solving from Nature 2. Elsevier, Amsterdam.
Michalski, R. S. (1986). Understanding the nature of learning: Issues and research directions. In Machine Learning Vol. II, eds. R. S. Michalski, J. G. Carbonell, and T. M. Mitchell, Chapter 1, pp. 3–25. Morgan Kaufmann, San Mateo, CA.
Mühlenbein, H. (1992). How genetic algorithms really work: I. mutation and hillclimbing. See Männer and Manderick (1992)Parallel Problem Solving from Nature 2. Elsevier, Amsterdam}, pp. 15–25.
Mühlenbein, H., Schomisch, M. and Born, J. (1991). The parallel genetic algorithm as function optimizer. See Belew and Booker (1991)Proceedings of the 4th International Conference on Genetic Algorithms. Morgan Kaufmann, San Mateo, CA}, pp. 271–278.
Oliver, I. M., Smith, D. J. and Holland, J. R. C. (1987). A study of permutation crossover operators on the traveling salesman problem. See Grefenstette (1987)Proceedings of the 2nd International Conference on Genetic Algorithms and Their Applications. Lawrence Erlbaum Associates, Hillsdale, NJ}, pp. 224–230.
Pintér, J. (1984). Convergence properties of stochastic optimization procedures. Mathematik der Operationsforschung and Statistik, Serie optimization 15, 405–427.
Rechenberg, I. (1965). Cybernetic solution path of an experimental problem. Royal Aircraft Establishment, Library translation No. 1122, Farnborough, Hants., UK.
Rechenberg, I. (1973). Evolutionsstrategie: Optimierung technischer Systeme nach Prinzipien der biologischen Evolution Frommann-Holzboog, Stuttgart.
Rudolph, G. (1991). Global optimization by means of distributed evolution strategies. See Schwefel and Männer (1991)Parallel Problem Solving from Nature—Proceedings 1st Workshop PPSN I. Lecture Notes in Computer Science, 496. Springer-Verlag, Berlin}, pp. 209–213.
Rudolph, G. (1992a). On correlated mutations in evolution strategies. See Männer and Manderick (1992)Parallel Problem Solving from Nature 2. Elsevier, Amsterdam}, pp. 105–114.
Rudolph, G. (1992b). Parallel approaches to stochastic global optimization. In Parallel computing: From Theory to Sound Practice, Proceedings of the European Workshop on Parallel Computing, eds. W. Joosen and E. Milgrom, pp. 256–267. IOS Press, Amsterdam.
Schaffer, J. D. (d.) (1989). Proceedings of the 3rd International Conference on Genetic Algorithms and Their Applications. Morgan Kaufmann, San Mateo, CA.
Schaffer, J. D. and Morishima, A. (1987). An adaptive crossover distribution mechanism for genetic algorithms. See Grefenstette (1987)}Proceedings of the 2nd International Conference on Genetic Algorithms and Their Applications. Lawrence Erlbaum Associates, Hillsdale, NJ}, pp. 36–40.
Schwefel, H.-P. (1965). Kybernetische Evolution als Strategie der experimentellen Forschung in der Strömungstechnik. Diplomarbeit, Technische Universität Berlin.
Schwefel, H.-P. (1968). Projekt MHD-Staustrahlrohr: Experimentelle Optimierung einer Zweiphasendüse, Teil I. Technischer Bericht 11.034/68, 35, AEG Forschungsinstitut, Berlin.
Schwefel, H.-P. (1975). Evolutionsstrategie und numerische Optimierung. Dissertation, Technische Universität Berlin.
Schwefel, H.-P. (1977). Numerische Optimierung von Computer-Modellen mittels der Evolutionsstrategie. Interdisciplinary Systems Research, Volume 26. Birkhäuser, Basel.
Schwefel, H.-P. (1981). Numerical Optimization of Computer Models. Wiley, Chichester.
Schwefel, H.-P. (1987). Collective phenomena in evolutionary systems. In Preprints of the 31st Annual Meeting of the International Society for General System Research, Budapest, Volume 2, pp. 1025–1033.
Schwefel, H.-P. (1988). Evolutionary learning optimum-seeking on parallel computer architectures. In Proceedings of the International Symposium on Systems Analysis and Simulation 1988, I: Theory and Foundations, eds. A. Sydow, S. G. Tzafestas, and R. Vichnevetsky, pp. 217–225. Akademie-Verlag, Berlin.
Schwefel, H.-P. and Männer, R. (1991). (Eds.) Parallel Problem Solving from Nature—Proceedings 1st Workshop PPSN I. Lecture Notes in Computer Science, 496. Springer-Verlag, Berlin.
Spiessens, P. and Manderick, B. (1989). Fine-grained parallel genetic algorithms. See Schaffer (1989)Proceedings of the 3rd International Conference on Genetic Algorithms and Their Applications. Morgan Kaufmann, San Mateo, CA}, pp. 428–433.
Starkweather, T., Whitley, D. and Mathias, K. (1991). Optimization using distributed genetic algorithms. See Schwefel and Männer (1991)Parallel Problem Solving from Nature—Proceedings 1st Workshop PPSN I. Lecture Notes in Computer Science, 496. Springer-Verlag, Berlin}, pp. 176–186.
Tanese, R. (1989). Distributed genetic algorithms. See Schaffer (1989)Proceedings of the 3rd International Conference on enetic Algorithms and Their Applications. Morgan Kaufmann, San Mateo, CA}, pp. 434–439.
Whitley, D. (1989). The GENITOR algorithm and selection pressure: why rank-based allocation of reproductive trials is best. See Schaffe (1989)Proceedings of the 3rd International Conference on enetic Algorithms and Their Applications. Morgan Kaufmann, San Mateo, CA}, pp. 116–121.
Zhigljavsky, A. A. (1992). Theory of Global Random Search. Mathematics and Its Applications. Kluwer, Dordrecht.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Bäck, T., Hoffmeister, F. Basic aspects of evolution strategies. Stat Comput 4, 51–63 (1994). https://doi.org/10.1007/BF00175353
Issue Date:
DOI: https://doi.org/10.1007/BF00175353