Evolutionary algorithm#Generic definition

The following is an example of a generic evolutionary algorithm:{{cite book |last1=Jansen |first1=Thomas |last2=Weyland |first2=Dennis |chapter=Analysis of evolutionary algorithms for the longest common subsequence problem |title=Proceedings of the 9th annual conference on Genetic and evolutionary computation |date=7 July 2007 |pages=939–946 |doi=10.1145/1276958.1277148 |chapter-url=https://dl.acm.org/doi/abs/10.1145/1276958.1277148 |publisher=Association for Computing Machinery|isbn=978-1-59593-697-4 }}{{cite book |last1=Jin |first1=Yaochu |chapter=Evolutionary Algorithms |title=Advanced Fuzzy Systems Design and Applications |series=Studies in Fuzziness and Soft Computing |date=2003 |volume=112 |pages=49–71 |doi=10.1007/978-3-7908-1771-3_2 |chapter-url=https://link.springer.com/chapter/10.1007/978-3-7908-1771-3_2 |publisher=Physica-Verlag HD |isbn=978-3-7908-2520-6 |language=en}}{{cite book |last1=Tavares |first1=Jorge |last2=Machado |first2=Penousal |last3=Cardoso |first3=Amílcar |last4=Pereira |first4=Francisco B. |last5=Costa |first5=Ernesto |chapter=On the Evolution of Evolutionary Algorithms |title=Genetic Programming |series=Lecture Notes in Computer Science |date=2004 |volume=3003 |pages=389–398 |doi=10.1007/978-3-540-24650-3_37 |chapter-url=https://link.springer.com/chapter/10.1007/978-3-540-24650-3_37 |publisher=Springer |isbn=978-3-540-21346-8 |language=en}}

1. Randomly generate the initial population of individuals, the first generation.
2. Evaluate the fitness of each individual in the population.
3. Check, if the goal is reached and the algorithm can be terminated.
4. Select individuals as parents, preferably of higher fitness.
5. Produce offspring with optional crossover (mimicking reproduction).
6. Apply mutation operations on the offspring.
7. Select individuals preferably of lower fitness for replacement with new individuals (mimicking natural selection).
8. Return to 2

Similar techniques differ in genetic representation and other implementation details, and the nature of the particular applied problem.

• Genetic algorithm – This is the most popular type of EA. One seeks the solution of a problem in the form of strings of numbers (traditionally binary, although the best representations are usually those that reflect something about the problem being solved), by applying operators such as recombination and mutation (sometimes one, sometimes both). This type of EA is often used in optimization problems.
• Genetic programming – Here the solutions are in the form of computer programs, and their fitness is determined by their ability to solve a computational problem. There are many variants of Genetic Programming:
• Cartesian genetic programming
• Gene expression programming
• Grammatical evolution
• Linear genetic programming
• Multi expression programming
• Evolutionary programming – Similar to evolution strategy, but with a deterministic selection of all parents.
• Evolution strategy (ES) – Works with vectors of real numbers as representations of solutions, and typically uses self-adaptive mutation rates. The method is mainly used for numerical optimization, although there are also variants for combinatorial tasks.{{Citation |last1=Nissen |first1=Volker |last2=Krause |first2=Matthias |title=Fuzzy Logik |chapter=Constrained Combinatorial Optimization with an Evolution Strategy |series=Informatik aktuell |date=1994 |editor-last=Reusch |editor-first=Bernd |url=https://link.springer.com/chapter/10.1007/978-3-642-79386-8_5 |language=en |location=Berlin, Heidelberg |publisher=Springer |pages=33–40 |doi=10.1007/978-3-642-79386-8_5 |isbn=978-3-642-79386-8|url-access=subscription }}{{Cite journal |last1=Coelho |first1=V. N. |last2=Coelho |first2=I. M. |last3=Souza |first3=M. J. F. |last4=Oliveira |first4=T. A. |last5=Cota |first5=L. P. |last6=Haddad |first6=M. N. |last7=Mladenovic |first7=N. |last8=Silva |first8=R. C. P. |last9=Guimarães |first9=F. G. |year=2016 |title=Hybrid Self-Adaptive Evolution Strategies Guided by Neighborhood Structures for Combinatorial Optimization Problems. |journal=Evol Comput |volume=24 |issue=4 |pages=637–666 |doi=10.1162/EVCO_a_00187|pmid=27258842 |s2cid=13582781 }}{{cite journal |last1=Slowik |first1=Adam |last2=Kwasnicka |first2=Halina |title=Evolutionary algorithms and their applications to engineering problems |journal=Neural Computing and Applications |date=1 August 2020 |volume=32 |issue=16 |pages=12363–12379 |doi=10.1007/s00521-020-04832-8 |language=en |issn=1433-3058|doi-access=free }}
• CMA-ES
• Natural evolution strategy
• Differential evolution – Based on vector differences and is therefore primarily suited for numerical optimization problems.
• Coevolutionary algorithm – Similar to genetic algorithms and evolution strategies, but the created solutions are compared on the basis of their outcomes from interactions with other solutions. Solutions can either compete or cooperate during the search process. Coevolutionary algorithms are often used in scenarios where the fitness landscape is dynamic, complex, or involves competitive interactions.{{Citation|last1=Ma |first1=Xiaoliang |last2=Li |first2=Xiaodong |last3=Zhang |first3=Qingfu |last4=Tang |first4=Ke |last5=Liang |first5=Zhengping |last6=Xie |first6=Weixin |last7=Zhu |first7=Zexuan |title=A Survey on Cooperative Co-Evolutionary Algorithms. |date=2019 |url=https://ieeexplore.ieee.org/document/8454482|journal=IEEE Transactions on Evolutionary Computation|volume=23 |number=3|pages=421–441|doi=10.1109/TEVC.2018.2868770|s2cid=125149900 |access-date=2023-05-22|url-access=subscription }}{{Cite book |chapter-url=https://link.springer.com/referenceworkentry/10.1007/978-3-540-92910-9_31 |title=Handbook of Natural Computing |date=2012 |publisher=Springer Berlin Heidelberg |pages=987–1033

|chapter=Coevolutionary Principles|isbn=978-3-540-92910-9 |editor-last1=Rozenberg |editor-first1=Grzegorz |editor-last2=Bäck |editor-first2=Thomas |editor-last3=Kok |editor-first3=Joost N.|author-first1=Elena |author-last1=Popovici |author-first2=Anthony|author-last2=Bucci |author-first3=R. Paul|author-last3=Wiegand|author-first4=Edwin D.|author-last4=De Jong |location=Berlin, Heidelberg |language=en |doi=10.1007/978-3-540-92910-9_31}}

• Neuroevolution – Similar to genetic programming but the genomes represent artificial neural networks by describing structure and connection weights. The genome encoding can be direct or indirect.
• Learning classifier system – Here the solution is a set of classifiers (rules or conditions). A Michigan-LCS evolves at the level of individual classifiers whereas a Pittsburgh-LCS uses populations of classifier-sets. Initially, classifiers were only binary, but now include real, neural net, or S-expression types. Fitness is typically determined with either a strength or accuracy based reinforcement learning or supervised learning approach.
• Quality–Diversity algorithms – QD algorithms simultaneously aim for high-quality and diverse solutions. Unlike traditional optimization algorithms that solely focus on finding the best solution to a problem, QD algorithms explore a wide variety of solutions across a problem space and keep those that are not just high performing, but also diverse and unique.{{Cite journal |last1=Pugh |first1=Justin K. |last2=Soros |first2=Lisa B. |last3=Stanley |first3=Kenneth O. |date=2016-07-12 |title=Quality Diversity: A New Frontier for Evolutionary Computation |journal=Frontiers in Robotics and AI |volume=3 |doi=10.3389/frobt.2016.00040 |issn=2296-9144 |doi-access=free }}{{Cite book |last1=Lehman |first1=Joel |last2=Stanley |first2=Kenneth O. |title=Proceedings of the 13th annual conference on Genetic and evolutionary computation |chapter=Evolving a diversity of virtual creatures through novelty search and local competition |date=2011-07-12 |pages=211–218 |chapter-url=http://dx.doi.org/10.1145/2001576.2001606 |location=New York, NY, USA |publisher=ACM |doi=10.1145/2001576.2001606|isbn=9781450305570 |s2cid=17338175 }}{{Cite journal |last1=Cully |first1=Antoine |last2=Clune |first2=Jeff |last3=Tarapore |first3=Danesh |last4=Mouret |first4=Jean-Baptiste |date=2015-05-27 |title=Robots that can adapt like animals |url=http://dx.doi.org/10.1038/nature14422 |journal=Nature |volume=521 |issue=7553 |pages=503–507 |doi=10.1038/nature14422 |pmid=26017452 |arxiv=1407.3501 |bibcode=2015Natur.521..503C |s2cid=3467239 |issn=0028-0836}}

The following theoretical principles apply to all or almost all EAs.

The no free lunch theorem of optimization states that all optimization strategies are equally effective when the set of all optimization problems is considered. Under the same condition, no evolutionary algorithm is fundamentally better than another. This can only be the case if the set of all problems is restricted. This is exactly what is inevitably done in practice. Therefore, to improve an EA, it must exploit problem knowledge in some form (e.g. by choosing a certain mutation strength or a problem-adapted coding). Thus, if two EAs are compared, this constraint is implied. In addition, an EA can use problem specific knowledge by, for example, not randomly generating the entire start population, but creating some individuals through heuristics or other procedures.{{Cite book |last=Davis |first=Lawrence |url=https://www.worldcat.org/oclc/23081440 |title=Handbook of genetic algorithms |date=1991 |publisher=Van Nostrand Reinhold |isbn=0-442-00173-8 |location=New York |oclc=23081440}}{{Citation |last1=Lienig |first1=Jens |title=An evolutionary algorithm for the routing of multi-chip modules |date=1994 |url=http://link.springer.com/10.1007/3-540-58484-6_301 |work=Parallel Problem Solving from Nature — PPSN III |volume=866 |pages=588–597 |editor-last=Davidor |editor-first=Yuval |place=Berlin, Heidelberg |publisher=Springer |doi=10.1007/3-540-58484-6_301 |isbn=978-3-540-58484-1 |access-date=2022-10-18 |last2=Brandt |first2=Holger |editor2-last=Schwefel |editor2-first=Hans-Paul |editor3-last=Männer |editor3-first=Reinhard|url-access=subscription }} Another possibility to tailor an EA to a given problem domain is to involve suitable heuristics, local search procedures or other problem-related procedures in the process of generating the offspring. This form of extension of an EA is also known as a memetic algorithm. Both extensions play a major role in practical applications, as they can speed up the search process and make it more robust.{{Cite book |url=http://link.springer.com/10.1007/978-3-642-23247-3 |title=Handbook of Memetic Algorithms |date=2012 |publisher=Springer Berlin Heidelberg |isbn=978-3-642-23246-6 |editor-last=Neri |editor-first=Ferrante |series=Studies in Computational Intelligence |volume=379 |location=Berlin, Heidelberg |language=en |doi=10.1007/978-3-642-23247-3 |editor-last2=Cotta |editor-first2=Carlos |editor-last3=Moscato |editor-first3=Pablo}}

For EAs in which, in addition to the offspring, at least the best individual of the parent generation is used to form the subsequent generation (so-called elitist EAs), there is a general proof of convergence under the condition that an optimum exists. Without loss of generality, a maximum search is assumed for the proof:

From the property of elitist offspring acceptance and the existence of the optimum it follows that per generation $k$ an improvement of the fitness $F$ of the respective best individual $x\text{'}$ will occur with a probability $P\; >\; 0$. Thus:

:$F(x\text{'}\_1)\; \backslash leq\; F(x\text{'}\_2)\; \backslash leq\; F(x\text{'}\_3)\; \backslash leq\; \backslash cdots\; \backslash leq\; F(x\text{'}\_k)\; \backslash leq\; \backslash cdots$

I.e., the fitness values represent a monotonically non-decreasing sequence, which is bounded due to the existence of the optimum. From this follows the convergence of the sequence against the optimum.

Since the proof makes no statement about the speed of convergence, it is of little help in practical applications of EAs. But it does justify the recommendation to use elitist EAs. However, when using the usual panmictic population model, elitist EAs tend to converge prematurely more than non-elitist ones.{{Cite journal |last1=Leung |first1=Yee |last2=Gao |first2=Yong |last3=Xu |first3=Zong-Ben |date=1997 |title=Degree of population diversity - a perspective on premature convergence in genetic algorithms and its Markov chain analysis |url=https://ieeexplore.ieee.org/document/623217 |journal=IEEE Transactions on Neural Networks |volume=8 |issue=5 |pages=1165–1176 |doi=10.1109/72.623217 |pmid=18255718 |issn=1045-9227|url-access=subscription }} In a panmictic population model, mate selection (see step 4 of the generic definition) is such that every individual in the entire population is eligible as a mate. In non-panmictic populations, selection is suitably restricted, so that the dispersal speed of better individuals is reduced compared to panmictic ones. Thus, the general risk of premature convergence of elitist EAs can be significantly reduced by suitable population models that restrict mate selection.{{Citation |last=Gorges-Schleuter |first=Martina |title=A comparative study of global and local selection in evolution strategies |date=1998 |url=http://link.springer.com/10.1007/BFb0056879 |work=Parallel Problem Solving from Nature — PPSN V |series=Lecture Notes in Computer Science |volume=1498 |pages=367–377 |editor-last=Eiben |editor-first=Agoston E. |place=Berlin, Heidelberg |publisher=Springer Berlin Heidelberg |doi=10.1007/bfb0056879 |isbn=978-3-540-65078-2 |access-date=2022-10-21 |editor2-last=Bäck |editor2-first=Thomas |editor3-last=Schoenauer |editor3-first=Marc |editor4-last=Schwefel |editor4-first=Hans-Paul|url-access=subscription }}{{Cite book |last1=Dorronsoro |first1=Bernabe |url=http://link.springer.com/10.1007/978-0-387-77610-1 |title=Cellular Genetic Algorithms |last2=Alba |first2=Enrique |date=2008 |publisher=Springer US |isbn=978-0-387-77609-5 |series=Operations Research/Computer Science Interfaces Series |volume=42 |location=Boston, MA |doi=10.1007/978-0-387-77610-1}}

With the theory of virtual alphabets, David E. Goldberg showed in 1990 that by using a representation with real numbers, an EA that uses classical recombination operators (e.g. uniform or n-point crossover) cannot reach certain areas of the search space, in contrast to a coding with binary numbers.{{Citation |last=Goldberg |first=David E. |title=The theory of virtual alphabets |date=1990 |url=http://link.springer.com/10.1007/BFb0029726 |work=Parallel Problem Solving from Nature |series=Lecture Notes in Computer Science |volume=496 |pages=13–22 |publication-date=1991 |editor-last=Schwefel |editor-first=Hans-Paul |place=Berlin/Heidelberg |publisher=Springer-Verlag |language=en |doi=10.1007/bfb0029726 |isbn=978-3-540-54148-6 |access-date=2022-10-22 |editor2-last=Männer |editor2-first=Reinhard|url-access=subscription }} This results in the recommendation for EAs with real representation to use arithmetic operators for recombination (e.g. arithmetic mean or intermediate recombination). With suitable operators, real-valued representations are more effective than binary ones, contrary to earlier opinion.{{Cite book |last1=Stender |first1=J. |url=https://www.worldcat.org/oclc/47216370 |title=Genetic algorithms in optimisation, simulation, and modelling |last2=Hillebrand |first2=E. |last3=Kingdon |first3=J. |date=1994 |publisher=IOS Press |isbn=90-5199-180-0 |location=Amsterdam |oclc=47216370}}{{Cite book |last=Michalewicz |first=Zbigniew |url=https://www.worldcat.org/oclc/851375253 |title=Genetic Algorithms + Data Structures = Evolution Programs |date=1996 |publisher=Springer |isbn=978-3-662-03315-9 |edition=3rd |publication-place=Berlin Heidelberg |oclc=851375253}}

A possible limitation{{According to whom|date=May 2013}} of many evolutionary algorithms is their lack of a clear genotype–phenotype distinction. In nature, the fertilized egg cell undergoes a complex process known as embryogenesis to become a mature phenotype. This indirect encoding is believed to make the genetic search more robust (i.e. reduce the probability of fatal mutations), and also may improve the evolvability of the organism.G.S. Hornby and J.B. Pollack. "Creating high-level components with a generative representation for body-brain evolution". Artificial Life, 8(3):223–246, 2002.Jeff Clune, Benjamin Beckmann, Charles Ofria, and Robert Pennock. [http://www.ofria.com/pubs/2009CluneEtAl.pdf "Evolving Coordinated Quadruped Gaits with the HyperNEAT Generative Encoding"] {{Webarchive|url=https://web.archive.org/web/20160603205252/http://www.ofria.com/pubs/2009CluneEtAl.pdf |date=2016-06-03 }}. Proceedings of the IEEE Congress on Evolutionary Computing Special Section on Evolutionary Robotics, 2009. Trondheim, Norway. Such indirect (also known as generative or developmental) encodings also enable evolution to exploit the regularity in the environment.J. Clune, C. Ofria, and R. T. Pennock, [http://jeffclune.com/publications/Clune-HyperNEATandRegularity.pdf "How a generative encoding fares as problem-regularity decreases"], in PPSN (G. Rudolph, T. Jansen, S. M. Lucas, C. Poloni, and N. Beume, eds.), vol. 5199 of Lecture Notes in Computer Science, pp. 358–367, Springer, 2008. Recent work in the field of artificial embryogeny, or artificial developmental systems, seeks to address these concerns. And gene expression programming successfully explores a genotype–phenotype system, where the genotype consists of linear multigenic chromosomes of fixed length and the phenotype consists of multiple expression trees or computer programs of different sizes and shapes.Ferreira, C., 2001. [http://www.gene-expression-programming.com/webpapers/GEP.pdf "Gene Expression Programming: A New Adaptive Algorithm for Solving Problems"]. Complex Systems, Vol. 13, issue 2: 87–129.{{Synthesis inline|date=May 2013}}

Both method classes have in common that their individual search steps are determined by chance. The main difference, however, is that EAs, like many other metaheuristics, learn from past search steps and incorporate this experience into the execution of the next search steps in a method-specific form. With EAs, this is done firstly through the fitness-based selection operators for partner choice and the formation of the next generation. And secondly, in the type of search steps: In EA, they start from a current solution and change it or they mix the information of two solutions. In contrast, when dicing out new solutions in Monte-Carlo methods, there is usually no connection to existing solutions.{{Cite book |last=Schwefel |first=Hans-Paul |url=https://www.researchgate.net/publication/220690578 |title=Evolution and Optimum Seeking |date=1995 |publisher=Wiley |isbn=978-0-471-57148-3 |series=Sixth-generation computer technology series |location=New York |pages=109}}{{Cite book |url=https://www.worldcat.org/title/ocm44807816 |title=Evolutionary Computation 1 |date=2000 |publisher=Institute of Physics Publishing |isbn=978-0-7503-0664-5 |editor-last=Fogel |editor-first=David B. |location=Bristol ; Philadelphia |pages=xxx and xxxvii (Glossary) |oclc=ocm44807816 |editor-last2=Bäck |editor-first2=Thomas |editor-last3=Michalewicz |editor-first3=Zbigniew}}

If, on the other hand, the search space of a task is such that there is nothing to learn, Monte-Carlo methods are an appropriate tool, as they do not contain any algorithmic overhead that attempts to draw suitable conclusions from the previous search. An example of such tasks is the proverbial search for a needle in a haystack, e.g. in the form of a flat (hyper)plane with a single narrow peak.

The areas in which evolutionary algorithms are practically used are almost unlimited and range from industry,{{Cite book |last1=Sanchez |first1=Ernesto |url=http://link.springer.com/10.1007/978-3-642-27467-1 |title=Industrial Applications of Evolutionary Algorithms |last2=Squillero |first2=Giovanni |last3=Tonda |first3=Alberto |date=2012 |publisher=Springer Berlin Heidelberg |isbn=978-3-642-27466-4 |series=Intelligent Systems Reference Library |volume=34 |location=Berlin, Heidelberg |doi=10.1007/978-3-642-27467-1}}{{Cite book |url=https://www.wiley.com/en-us/Evolutionary+Algorithms+in+Engineering+and+Computer+Science%3A+Recent+Advances+in+Genetic+Algorithms%2C+Evolution+Strategies%2C+Evolutionary+Programming%2C+Genetic+Programming+and+Industrial+Applications-p-9780471999027 |title=Evolutionary algorithms in engineering and computer science : recent advances in genetic algorithms, evolution strategies, evolutionary programming, genetic programming, and industrial applications |date=1999 |publisher=Wiley and Sons |isbn=0-585-29445-3 |editor-last=Miettinen |editor-first=Kaisa |location=Chichester |language=en |oclc=45728460 |editor-last2=Neittaanmäki |editor-first2=Pekka |editor-last3=Mäkelä |editor-first3=M. M. |editor-last4=Périaux |editor-first4=Jacques}} engineering,{{Cite book |last1=Gen |first1=Mitsuo |url=http://doi.wiley.com/10.1002/9780470172261 |title=Genetic Algorithms and Engineering Optimization |last2=Cheng |first2=Runwei |date=1999-12-17 |publisher=John Wiley & Sons, Inc. |isbn=978-0-470-17226-1 |series=Wiley Series in Engineering Design and Automation |location=Hoboken, NJ, USA |language=en |doi=10.1002/9780470172261}} complex scheduling,{{Cite book |last1=Dahal |first1=Keshav P. |url=https://www.worldcat.org/oclc/184984689 |title=Evolutionary scheduling |last2=Tan |first2=Kay Chen |last3=Cowling |first3=Peter I. |date=2007 |publisher=Springer |isbn=978-3-540-48584-1 |location=Berlin |language=en |doi=10.1007/978-3-540-48584-1 |oclc=184984689}}{{Cite journal |last1=Jakob |first1=Wilfried |last2=Strack |first2=Sylvia |last3=Quinte |first3=Alexander |last4=Bengel |first4=Günther |last5=Stucky |first5=Karl-Uwe |last6=Süß |first6=Wolfgang |date=2013-04-22 |title=Fast Rescheduling of Multiple Workflows to Constrained Heterogeneous Resources Using Multi-Criteria Memetic Computing |journal=Algorithms |language=en |volume=6 |issue=2 |pages=245–277 |doi=10.3390/a6020245 |issn=1999-4893|doi-access=free }} agriculture,{{Cite book |last=Mayer |first=David G. |url=http://link.springer.com/10.1007/978-1-4615-1717-7 |title=Evolutionary Algorithms and Agricultural Systems |date=2002 |publisher=Springer US |isbn=978-1-4613-5693-6 |location=Boston, MA |doi=10.1007/978-1-4615-1717-7}} robot movement planning{{Citation |last=Blume |first=Christian |title=Optimized Collision Free Robot Move Statement Generation by the Evolutionary Software GLEAM |date=2000 |url=http://link.springer.com/10.1007/3-540-45561-2_32 |work=Real-World Applications of Evolutionary Computing |volume= 1803|pages=330–341 |editor-last=Cagnoni |editor-first=Stefano |series=LNCS 1803 |place=Berlin, Heidelberg |publisher=Springer |language=en |doi=10.1007/3-540-45561-2_32 |isbn=978-3-540-67353-8 |access-date=2022-12-28|url-access=subscription }} and finance{{Citation |last1=Aranha |first1=Claus |title=Application of a Memetic Algorithm to the Portfolio Optimization Problem |date=2008 |url=http://link.springer.com/10.1007/978-3-540-89378-3_52 |work=AI 2008: Advances in Artificial Intelligence |volume=5360 |pages=512–521 |editor-last=Wobcke |editor-first=Wayne |place=Berlin, Heidelberg |publisher=Springer Berlin Heidelberg |doi=10.1007/978-3-540-89378-3_52 |isbn=978-3-540-89377-6 |access-date=2022-12-23 |last2=Iba |first2=Hitoshi |series=Lecture Notes in Computer Science |editor2-last=Zhang |editor2-first=Mengjie|url-access=subscription }}{{Cite book |url=http://link.springer.com/10.1007/978-3-7908-1784-3 |title=Evolutionary Computation in Economics and Finance |date=2002 |publisher=Physica-Verlag HD |isbn=978-3-7908-2512-1 |editor-last=Chen |editor-first=Shu-Heng |series=Studies in Fuzziness and Soft Computing |volume=100 |location=Heidelberg |doi=10.1007/978-3-7908-1784-3}} to research{{Cite book |last1=Lohn |first1=J.D. |last2=Linden |first2=D.S. |last3=Hornby |first3=G.S. |last4=Kraus |first4=W.F. |title=IEEE Antennas and Propagation Society Symposium, 2004 |chapter=Evolutionary design of an X-band antenna for NASA's Space Technology 5 mission |date=June 2004 |chapter-url=https://ieeexplore.ieee.org/document/1331834 |volume=3 |pages=2313–2316 Vol.3 |doi=10.1109/APS.2004.1331834|hdl=2060/20030067398 |isbn=0-7803-8302-8 |hdl-access=free }}{{Cite book |last1=Fogel |first1=Gary |url=https://linkinghub.elsevier.com/retrieve/pii/B9781558607972X50008 |title=Evolutionary Computation in Bioinformatics |last2=Corne |first2=David |date=2003 |publisher=Elsevier |isbn=978-1-55860-797-2 |language=en |doi=10.1016/b978-1-55860-797-2.x5000-8}} and art. The application of an evolutionary algorithm requires some rethinking from the inexperienced user, as the approach to a task using an EA is different from conventional exact methods and this is usually not part of the curriculum of engineers or other disciplines. For example, the fitness calculation must not only formulate the goal but also support the evolutionary search process towards it, e.g. by rewarding improvements that do not yet lead to a better evaluation of the original quality criteria. For example, if peak utilisation of resources such as personnel deployment or energy consumption is to be avoided in a scheduling task, it is not sufficient to assess the maximum utilisation. Rather, the number and duration of exceedances of a still acceptable level should also be recorded in order to reward reductions below the actual maximum peak value.{{Citation |last=Jakob |first=Wilfried |title=Applying Evolutionary Algorithms Successfully - A Guide Gained from Realworld Applications |date=2021 |url=https://publikationen.bibliothek.kit.edu/1000135763/121278298 |series=KIT Scientific Working Papers |volume=170 |place=Karlsruhe, FRG |publisher=KIT Scientific Publishing |doi=10.5445/IR/1000135763 |arxiv=2107.11300 |s2cid=236318422 |access-date=2022-12-23 }} There are therefore some publications that are aimed at the beginner and want to help avoiding beginner's mistakes as well as leading an application project to success.{{Cite journal |last=Whitley |first=Darrell |date=2001 |title=An overview of evolutionary algorithms: practical issues and common pitfalls |url=https://linkinghub.elsevier.com/retrieve/pii/S0950584901001884 |journal=Information and Software Technology |language=en |volume=43 |issue=14 |pages=817–831 |doi=10.1016/S0950-5849(01)00188-4|s2cid=18637958 |url-access=subscription }}{{Cite book |last1=Eiben |first1=A.E. |url=http://link.springer.com/10.1007/978-3-662-44874-8 |title=Introduction to Evolutionary Computing |last2=Smith |first2=J.E. |date=2015 |publisher=Springer Berlin Heidelberg |isbn=978-3-662-44873-1 |edition=2nd |series=Natural Computing Series |location=Berlin, Heidelberg |pages=147–163 |language=en |chapter=Working with Evolutionary Algorithms |doi=10.1007/978-3-662-44874-8|s2cid=20912932 }} This includes clarifying the fundamental question of when an EA should be used to solve a problem and when it is better not to.

There are some other proven and widely used methods of nature inspired global search techniques such as

• Memetic algorithm – A hybrid method, inspired by Richard Dawkins's notion of a meme. It commonly takes the form of a population-based algorithm (frequently an EA) coupled with individual learning procedures capable of performing local refinements. Emphasizes the exploitation of problem-specific knowledge and tries to orchestrate local and global search in a synergistic way.
• A cellular evolutionary or memetic algorithm uses a topological neighbouhood relation between the individuals of a population for restricting the mate selection and by that reducing the propagation speed of above-average individuals. The idea is to maintain genotypic diversity in the poulation over a longer period of time to reduce the risk of premature convergence.
• Ant colony optimization is based on the ideas of ant foraging by pheromone communication to form paths. Primarily suited for combinatorial optimization and graph problems.
• Particle swarm optimization is based on the ideas of animal flocking behaviour. Also primarily suited for numerical optimization problems.
• Gaussian adaptation – Based on information theory. Used for maximization of manufacturing yield, mean fitness or average information. See for instance Entropy in thermodynamics and information theory.

In addition, many new nature-inspired or methaphor-guided algorithms have been proposed since the beginning of this century. For criticism of most publications on these, see the remarks at the end of the introduction to the article on metaheuristics.

In 2020, Google stated that their AutoML-Zero can successfully rediscover classic algorithms such as the concept of neural networks.{{cite news |last1=Gent |first1=Edd |title=Artificial intelligence is evolving all by itself |url=https://www.science.org/content/article/artificial-intelligence-evolving-all-itself |access-date=16 April 2020 |work=Science {{!}} AAAS |date=13 April 2020 |language=en |archive-url=https://web.archive.org/web/20200416222954/https://www.sciencemag.org/news/2020/04/artificial-intelligence-evolving-all-itself |archive-date=16 April 2020 |url-status=live }}

The computer simulations Tierra and Avida attempt to model macroevolutionary dynamics.

{{Cite book |last1=Simionescu |first1=P.A. |title=2006 IEEE International Conference on Evolutionary Computation |last2=Dozier |first2=G.V. |last3=Wainwright |first3=R.L. |chapter=A Two-Population Evolutionary Algorithm for Constrained Optimization Problems |series=Proc 2006 IEEE International Conference on Evolutionary Computation|place=Vancouver, Canada |pages=1647–1653 |year=2006 |doi=10.1109/CEC.2006.1688506 |chapter-url=http://faculty.tamucc.edu/psimionescu/PDFs/WCCI2006-Paper7204(1).pdf |access-date=7 January 2017|isbn=0-7803-9487-9 |s2cid=1717817 }}{{cite book|last=Simionescu|first=P.A.|title=Computer Aided Graphing and Simulation Tools for AutoCAD Users|year=2014|publisher=CRC Press|location=Boca Raton, FL|isbn=978-1-4822-5290-3|edition=1st}}

File:Two-population EA search (2).gif|A two-population EA search over a constrained Rosenbrock function with bounded global optimum

File:Two-population EA search (3).gif|A two-population EA search over a constrained Rosenbrock function. Global optimum is not bounded.

File:Estimation of Distribution Algorithm animation.gif|Estimation of distribution algorithm over Keane's bump function

File:Two population EA animation.gif|A two-population EA search of a bounded optima of Simionescu's function

{{Reflist}}

• Ashlock, D. (2006), Evolutionary Computation for Modeling and Optimization, Springer, New York, doi:10.1007/0-387-31909-3 {{ISBN|0-387-22196-4}}.
• Bäck, T. (1996), [https://books.google.com/books?id=htJHI1UrL7IC Evolutionary Algorithms in Theory and Practice: Evolution Strategies, Evolutionary Programming, Genetic Algorithms], Oxford Univ. Press, New York, {{ISBN|978-0-19-509971-3}}.
• Bäck, T., Fogel, D., Michalewicz, Z. (1999), Evolutionary Computation 1: Basic Algorithms and Operators, CRC Press, Boca Raton, USA, {{ISBN|978-0-7503-0664-5}}.
• Bäck, T., Fogel, D., Michalewicz, Z. (2000), Evolutionary Computation 2: Advanced Algorithms and Operators, CRC Press, Boca Raton, USA, doi:10.1201/9781420034349 {{ISBN|978-0-3678-0637-8}}.
• Banzhaf, W., Nordin, P., Keller, R., Francone, F. (1998), Genetic Programming - An Introduction, Morgan Kaufmann, San Francisco, {{ISBN|978-1-55860-510-7}}.
• Eiben, A.E., Smith, J.E. (2003), Introduction to Evolutionary Computing, Springer, Heidelberg, New York, doi:10.1007/978-3-662-44874-8 {{ISBN|978-3-662-44873-1}}.
• Holland, J. H. (1992), [https://books.google.com/books?id=5EgGaBkwvWcC Adaptation in Natural and Artificial Systems], MIT Press, Cambridge, MA, {{ISBN|978-0-262-08213-6}}.
• Michalewicz, Z.; Fogel, D.B. (2004), How To Solve It: Modern Heuristics. Springer, Berlin, Heidelberg, {{ISBN|978-3-642-06134-9}}, doi:10.1007/978-3-662-07807-5.
• {{cite book |doi=10.1109/BICTA.2010.5645312 |chapter=Bin Packing/Covering with Delivery, solved with the evolution of algorithms |title=2010 IEEE Fifth International Conference on Bio-Inspired Computing: Theories and Applications (BIC-TA) |pages=298–302 |year=2010 |last1=Benko |first1=Attila |last2=Dosa |first2=Gyorgy |last3=Tuza |first3=Zsolt |isbn=978-1-4244-6437-1 |s2cid=16875144 }}
• {{cite book |author1=Poli, R. |author2=Langdon, W. B. |author3=McPhee, N. F. |year=2008 |title=A Field Guide to Genetic Programming |publisher=Lulu.com, freely available from the internet |url=http://cswww.essex.ac.uk/staff/rpoli/gp-field-guide/ |isbn=978-1-4092-0073-4 |access-date=2011-03-05 |archive-url=https://web.archive.org/web/20160527142933/http://cswww.essex.ac.uk/staff/rpoli/gp-field-guide/ |archive-date=2016-05-27 |url-status=dead }}{{self-published source|date=February 2020}}
• Price, K., Storn, R.M., Lampinen, J.A., (2005). [https://books.google.com/books?id=hakXI-dEhTkC Differential Evolution: A Practical Approach to Global Optimization], Springer, Berlin, Heidelberg, {{ISBN|978-3-642-42416-8}}, doi:10.1007/3-540-31306-0.
• Ingo Rechenberg (1971), Evolutionsstrategie - Optimierung technischer Systeme nach Prinzipien der biologischen Evolution (PhD thesis). Reprinted by Fromman-Holzboog (1973). {{ISBN|3-7728-1642-8}}
• Hans-Paul Schwefel (1974), Numerische Optimierung von Computer-Modellen (PhD thesis). Reprinted by Birkhäuser (1977).
• Hans-Paul Schwefel (1995), [https://www.researchgate.net/publication/220690578_Evolution_and_Optimum_Seeking Evolution and Optimum Seeking]. Wiley & Sons, New York. {{ISBN|0-471-57148-2}}
• Simon, D. (2013), [http://academic.csuohio.edu/simond/EvolutionaryOptimization Evolutionary Optimization Algorithms] {{Webarchive|url=https://web.archive.org/web/20140310010900/http://academic.csuohio.edu/simond/EvolutionaryOptimization/ |date=2014-03-10 }}, Wiley & Sons, {{ISBN|978-0-470-93741-9}}
• Kruse, Rudolf; Borgelt, Christian; Klawonn, Frank; Moewes, Christian; Steinbrecher, Matthias; Held, Pascal (2013), [https://books.google.com/books?id=yQVGAAAAQBAJ Computational Intelligence: A Methodological Introduction]. Springer, London. {{ISBN|978-1-4471-5012-1}}, doi:10.1007/978-1-4471-5013-8.
• {{cite journal |last1=Rahman |first1=Rosshairy Abd. |last2=Kendall |first2=Graham |last3=Ramli |first3=Razamin |last4=Jamari |first4=Zainoddin |last5=Ku-Mahamud |first5=Ku Ruhana |title=Shrimp Feed Formulation via Evolutionary Algorithm with Power Heuristics for Handling Constraints |journal=Complexity |date=2017 |volume=2017 |pages=1–12 |doi=10.1155/2017/7053710 |doi-access=free }}

• [https://www.staracle.com/general/evolutionaryAlgorithms.php An Overview of the History and Flavors of Evolutionary Algorithms]

{{Evolutionary computation}}

{{DEFAULTSORT:Evolutionary Algorithm}}

Category:Cybernetics

Category:Evolution

Category:Optimization algorithms and methods