The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities
Open accessThe DOI matches its Crossref record; 162 of the 162 references it cites were found in a registry or an index.
Abstract
Evolution provides a creative fount of complex and subtle adaptations that often surprise the scientists who discover them. However, the creativity of evolution is not limited to the natural world: Artificial organisms evolving in computational environments have also elicited surprise and wonder from the researchers studying them. The process of evolution is an algorithmic process that transcends the substrate in which it occurs. Indeed, many researchers in the field of digital evolution can provide examples of how their evolving algorithms and organisms have creatively subverted their expectations or intentions, exposed unrecognized bugs in their code, produced unexpectedly adaptations, or engaged in behaviors and outcomes, uncannily convergent with ones found in nature. Such stories routinely reveal surprise and creativity by evolution in these digital worlds, but they rarely fit into the standard scientific narrative. Instead they are often treated as mere obstacles to be overcome, rather than results that warrant study in their own right. Bugs are fixed, experiments are refocused, and one-off surprises are collapsed into a single data point. The stories themselves are traded among researchers through oral tradition, but that mode of information transmission is inefficient and prone to error and outright loss. Moreover, the fact that these stories tend to be shared only among practitioners means that many natural scientists do not realize how interesting and lifelike digital organisms are and how natural their evolution can be. To our knowledge, no collection of such anecdotes has been published before. This article is the crowd-sourced product of researchers in the fields of artificial life and evolutionary computation who have provided first-hand accounts of such cases. It thus serves as a written, fact-checked collection of scientifically important and even entertaining stories. In doing so we also present here substantial evidence that the existence and importance of evolutionary surprises extends beyond the natural world, and may indeed be a universal property of all complex evolving systems.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures









![Figure 9 Three table designs evolved using the generic evolutionary design system [8].](https://figures.cochat.ai/paper-figures/956ee05672eb4cfaae910af610b5492b/the-surprising-creativity-of-digital-evolution-a-collection-of-anecdotes-from-figure-9.png)



![Figure 12 A stop-motion view of a small sample of the evolved gaits from Cheney et al. [15], which produced surprisingly effective and biologically reminiscent behaviors. Shown here are soft robots progressing from left to right across the panel. Colors correspond to voxel types (with red and green denoting oppositely contracting muscle groups, and dark and light blue representing stiff and soft support materials, respectively). In the top gait, notice how evolution creates distinct regions of each muscle. It employs these opposing muscle groups to create an inchworm-like behavior. In the bottom gait, the use of stiff (bonelike) support material allows evolution to create relatively long appendages and produce a horselike galloping behavior. Videos of various soft-robot gaits, including these two, can be found at https://youtu.be/z9ptOeByLA4?list=PL5278ezwmoxQODgYB0hWnC0-Ob09GZGe2.](https://figures.cochat.ai/paper-figures/528d8bbeddd84d34ab302294cb9f6784/the-surprising-creativity-of-digital-evolution-a-collection-of-anecdotes-from-figure-12.png)



Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Much like natural and artificial evolution (79), our framework also demonstrates remarkable creativity in discovering solutions, for instance, it independently evolved distributed eyelet-type architectures without being explicitly designed to do so.”
From What if eye...? Computationally recreating vision evolution (2025) · cites this paper as [79]
The cited source says what the claim attributes to it.
In the citing paper
“This method effectively stopped the organisms from deceitfully evolving to replicate faster.”
From AI deception: A survey of examples, risks, and potential solutions (2024) · cites this paper as [10]
The cited source says what the claim attributes to it.
In the citing paper
“This experience demonstrates how evolutionary pressures can select for agents that deceive their selection mechanism, a concerning form of deception that could arise in other contexts.”
From AI deception: A survey of examples, risks, and potential solutions (2024) · cites this paper as [10]
The cited source says what the claim attributes to it.
In the citing paper
“Indeed, we have already observed an AI system deceiving its evaluation.”
From AI deception: A survey of examples, risks, and potential solutions (2024) · cites this paper as [10]
In the citing paper
“Ofria realized that the organisms had learned to recognize the testing environment and stop replicating. They were pretending to be slower replicators to avoid being removed.”
From AI deception: A survey of examples, risks, and potential solutions (2024) · cites this paper as [10]
1 more claim about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Human-level control through deep reinforcement learning
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., et al. (2015) · Nature · doi:10.1038/nature14236 · Cited by 30,357 · cited 2×
“Atari games are a common benchmark in deep reinforcement learning [94, 95, 117, 132].”
Potent and specific genetic interference by double-stranded RNA in Caenorhabditis elegans
Fire, A., Xu, S., Montgomery, M. K., Kostas, S. A., Driver, S. E., & Mello, C. C. (1998) · Nature · doi:10.1038/35888 · Cited by 15,429 · cited 1×
“Even seasoned field biologists are still surprised by the new adaptations they discover, which they express in popular press accounts of their work [100, 111, 77], but only more rarely in official academic publications, for example, in [41] but not in [76, 142].”
BackgroundGenetic Programming: On the Programming of Computers by Means of Natural Selection
Koza, J. R. (1992) · Medical Entomology and Zoology · Cited by 13,082
On computable numbers, with an application to the entscheidungsproblem
Turing, A. M. (1937) · Proceedings of the London Mathematical Society · doi:10.1112/plms/s2-42.1.230 · Cited by 8,283 · cited 1×
“However, a well-known result in theoretical computer science is that, for many computer programs, the outcome of a program cannot be predicted without actually running it [58].”
The Neutral Theory of Molecular Evolution
Kimura, M. (1979) · Scientific American · doi:10.1038/scientificamerican1179-98 · Cited by 7,666
Asynchronous Methods for Deep Reinforcement Learning
Mnih, V., Badia, A. P., Mirza, M., Graves, A., Lillicrap, T. P., Harley, T., Silver, D., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1602.01783 · Cited by 7,132 · cited 2×
“Relevant to this anecdote, researchers at OpenAI [87], Uber [89], and the University of Freiburg [90] have recently shown that evolutionary algorithms are a competitive approach to solving such games [86, 88].”
The Neutral Theory of Molecular Evolution
Kimura, M. (1983) · Cambridge University Press eBooks · doi:10.1017/cbo9780511623486 · Cited by 6,347
Exaptation—a missing term in the science of form
Gould, S. J., & Vrba, E. S. (1982) · Paleobiology · doi:10.1017/s0094837300004310 · Cited by 5,136 · cited 1×
“Although evolution lacks the foresight and intentionality of human creativity, structures evolved for one functionality are often opportunistically adapted for other purposes, a phenomenon known as exaptation [54].”
BackgroundThe Ecology of Adaptive Radiation
Schluter, D. (2000) · doi:10.1093/oso/9780198505235.001.0001 · Cited by 4,974
The standard definition of creativity
Runco, M. A., & Jaeger, G. J. (2012) · Creativity Research Journal · doi:10.1080/10400419.2012.650092 · Cited by 3,895 · cited 1×
“Thus to avoid a semantic and philosophical quagmire, while acknowl-edging that other definitions and opinions exist, we here adopt the “ standard definition ” [116]: Cre-ativity requires inventing something both original (i.e., novel) and effective (i.e., functional).”
Selforganization of matter and the evolution of biological macromolecules
Eigen, M. (1971) · Die Naturwissenschaften · doi:10.1007/bf00623322 · Cited by 3,788 · cited 1×
“Only the relation between the size of the coding region of the genome and the mutation rates was theoretically expected, as a result of the error threshold effect first identified by Eigen in his quasi-species model [32].”
ResultCANALIZATION OF DEVELOPMENT AND THE INHERITANCE OF ACQUIRED CHARACTERS
WADDINGTON, C. H. (1942) · Nature · doi:10.1038/150563a0 · Cited by 3,255 · cited 1×
“That natural evolution could favor robustness to change has been known to biologists since the 1940s [119, 140].”
Proceedings of the 23rd international conference on Machine learning
Cohen, W. W., & Moore, A. (2006) · Cited by 2,647
Wilson, E. O. (1992) · DigitalGeorgetown (Georgetown University Library) · Cited by 2,468
Holland, J. H. (1998) · doi:10.1093/oso/9780198504092.001.0001 · Cited by 2,410
Superintelligence: paths, dangers, strategies
(2015) · Choice Reviews Online · doi:10.5860/choice.187536 · Cited by 1,979 · cited 1×
“…therein are concerned with the potential for perverse outcomes from optimizing reward functions that appear sensible on their surface [4, 11, 37, 134], characterized in that community as problems such as avoiding negative side effects [4, 69], reward hacking (also known as wire-heading)…”
DENNETT, D. C. (1995) · The Sciences · doi:10.1002/j.2326-1951.1995.tb03633.x · Cited by 1,975 · cited 2×
“Independent of its physical medium, evolution can happen wherever replication, variation, and selection intersect [16, 17].”
An Unsolvable Problem of Elementary Number Theory
Church, A. (1936) · American Journal of Mathematics · doi:10.2307/2371045 · Cited by 1,763
Vehicles: Experiments in Synthetic Psychology.
Dennett, D. C., & Braitenberg, V. (1986) · The Philosophical Review · doi:10.2307/2185146 · Cited by 1,616 · cited 1×
“This type of robot is well known from Braitenberg’s famous book Vehicles [104], which argued that connecting sensor inputs to motor outputs in a particular way results in simple light-following behavior.”
Computation at the edge of chaos: Phase transitions and emergent computation
Langton, C. G. (1990) · Physica D: Nonlinear Phenomena · doi:10.1016/0167-2789(90)90064-v · Cited by 1,527
Vehicles: Experiments in synthetic psychology
Stefik, M. J. (1985) · Artificial Intelligence · doi:10.1016/0004-3702(85)90057-8 · Cited by 1,333
Takagi, H. (2001) · Proceedings of the IEEE · doi:10.1109/5.949485 · Cited by 1,327 · cited 1×
“At first glance it may seem that interactive evolution [133] is unlikely to surprise anyone, because of close and constant interactions with the user.”
Concrete Problems in AI Safety
Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., & Mané, D. (2016) · arXiv · doi:10.48550/arxiv.1606.06565 · Cited by 1,314 · cited 2×
“…for perverse outcomes from optimizing reward functions that appear sensible on their surface [4, 11, 37, 134], characterized in that community as problems such as avoiding negative side effects [4, 69], reward hacking (also known as wire-heading) [4, 36], or more generally AI alignment [134].”
A constant rate of spontaneous mutation in DNA-based microbes.
Drake, J. W. (1991) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.88.16.7160 · Cited by 1,199
Kirschner, M., & Gerhart, J. (1998) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.95.15.8420 · Cited by 1,129 · cited 1×
“Even in the absence of direct foresight, studies of evolvability suggest that genomic architecture itself can become biased toward increasing creative potential [62, 65, 66].”
The blind watchmaker : why the evidence of evolution reveals a universe without design
Dawkins, R. (1996) · International Linear Collider · Cited by 1,057
Evolution Strategies as a Scalable Alternative to Reinforcement Learning
Salimans, T., Ho, J., Chen, X., Sidor, S., & Sutskever, I. (2017) · arXiv · doi:10.48550/arxiv.1703.03864 · Cited by 1,027 · cited 2×
“Atari games are a common benchmark in deep reinforcement learning [94, 95, 117, 132].”
Sims, K. (1994) · Proceedings of the 21st annual conference on Computer graphics and interactive techniques - SIGGRAPH '94 · doi:10.1145/192161.192167 · Cited by 1,005 · cited 2×
“In further virtual-creature experiments [126, 127], Karl Sims ʼ attempt to evolve swimming strategies resulted in new ways for evolution to cheat.”
Self-citationWagner, G. P., Pavlicev, M., & Cheverud, J. M. (2007) · Nature Reviews Genetics · doi:10.1038/nrg2267 · Cited by 987 · cited 1×
“Yet both philosophical arguments [23, 26, 27, 82, 109] and high-profile publications [2, 16, 18 – 21, 52, 59, 60, 83, 85, 86, 92, 141, 146, 148] suggest that digital evolution can be a useful tool to aid and complement the study of biological evolution.”
Robots that can adapt like animals
Cully, A., Clune, J., Tarapore, D., & Mouret, J.-B. (2015) · Nature · doi:10.1038/nature14422 · Cited by 979 · cited 2×
“Yet both philosophical arguments [23, 26, 27, 82, 109] and high-profile publications [2, 16, 18 – 21, 52, 59, 60, 83, 85, 86, 92, 141, 146, 148] suggest that digital evolution can be a useful tool to aid and complement the study of biological evolution.”
Self-citationAssessing the impact of planned social change
Campbell, D. T. (1979) · Evaluation and Program Planning · doi:10.1016/0149-7189(79)90048-x · Cited by 957 · cited 1×
“Just as well-intentioned metrics in human society can become corrupted by direct pressure to optimize them (known as Campbellʼs law [14] or Goodhartʼs law [53]), digital evolution often acts to fulfill the letter of the law (i.”
BackgroundAbandoning Objectives: Evolution Through the Search for Novelty Alone
Lehman, J., & Stanley, K. O. (2011) · Evolutionary Computation · doi:10.1162/evco_a_00025 · Cited by 917 · cited 1×
“The surprise inspired Stanley to conceive the novelty search algorithm [107], which searches without an explicit objective (just as Stanley found the car unintentionally), selecting instead the most different, novel outcomes at each evolution step.”
Self-citationSuperintelligence: Paths, Dangers, Strategies
Mulgan, T. (2015) · The Philosophical Quarterly · doi:10.1093/pq/pqv034 · Cited by 878
Spontaneous evolution of modularity and network motifs
Kashtan, N., & Alon, U. (2005) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0503610102 · Cited by 878 · cited 1×
“Yet both philosophical arguments [23, 26, 27, 82, 109] and high-profile publications [2, 16, 18 – 21, 52, 59, 60, 83, 85, 86, 92, 141, 146, 148] suggest that digital evolution can be a useful tool to aid and complement the study of biological evolution.”
Science and Sanity: An Introduction to Non-Aristotelian Systems and General Semantics.
Becker, H., & Korzybski, A. (1942) · American Sociological Review · doi:10.2307/2085182 · Cited by 862
The natural selection of bad science
Smaldino, P. E., & McElreath, R. (2016) · Royal Society Open Science · doi:10.1098/rsos.160384 · Cited by 860 · cited 1×
“In a final ironic twist, similar evolutionary arguments (applied to a higher level of biological organization) suggest that current incentive systems in science similarly produce surprising (and undesirable) byproducts [128].”
Launer, J. (2002) · QJM : monthly journal of the Association of Physicians · doi:10.1093/qjmed/95.3.195 · Cited by 848 · cited 2×
“Independently of its physical medium, evolution can happen wherever replication, variation, and selection intersect [23, 27].”
BackgroundEvolutionary computation: a unified approach
De Jong, K. (2007) · Proceedings of the 9th annual conference companion on Genetic and evolutionary computation · doi:10.1145/1274000.1274109 · Cited by 790
Search-based software engineering: Trends, techniques and applications
Harman, M., Mansouri, S. A., & Zhang, Y. (2012) · ACM Computing Surveys · doi:10.1145/2379776.2379787 · Cited by 777
Factors of Evolution:. The Theory of Stabilizing Selection
(1950) · Journal of the American Medical Association · doi:10.1001/jama.1950.02910300087029 · Cited by 765 · cited 1×
“That natural evolution could favor robustness to change has been known to biologists since the 1940s [127, 128].”
BackgroundThe evolutionary origin of complex features
Lenski, R. E., Ofria, C., Pennock, R. T., & Adami, C. (2003) · Nature · doi:10.1038/nature01568 · Cited by 751
Self-citationMakarova, K. S., Aravind, L., Wolf, Y. I., Tatusov, R. L., Minton, K. W., Koonin, E. V., & Daly, M. J. (2001) · Microbiology and Molecular Biology Reviews · doi:10.1128/mmbr.65.1.44-79.2001 · Cited by 738 · cited 1×
“Some flowers act as acoustic beacons to attract echo-locating bats [1], extremophile microbes repair their DNA to thrive in presence of extreme radiation [2], bombardier beetles repel predators with explosive chemical reactions [3], and parasites reprogram host brains, inducing suicide for the parasite’s own gain [4].”
Arnold, F. H. (1998) · Accounts of Chemical Research · doi:10.1021/ar960017f · Cited by 714 · cited 1×
“…connections between surprising results in digital evolution and the products of directed evolution in biology, wherein selection in an experimenter-controlled evolutionary process is manipulated with the hope of improving or adapting proteins or nucleic acids for practical purposes [5, 108].”
Advances in genetic programming
Fogel, D. B. (1995) · Biosystems · doi:10.1016/0303-2647(95)90007-1 · Cited by 703
Evolution of digital organisms at high mutation rates leads to survival of the flattest
Wilke, C. O., Wang, J. L., Ofria, C., Lenski, R. E., & Adami, C. (2001) · Nature · doi:10.1038/35085569 · Cited by 636 · cited 4×
“In research focused on understanding how organisms evolve to cope with high-mutation-rate environments [146], Ofria sought to disentangle the beneficial effects of performing tasks (which would allow an organism to execute its code faster and thus replicate faster) from evolved robustness to the…”
InfluentialSelf-citationThe Ecology of Adaptive Radiation
Turner, G. F. (2001) · Heredity · doi:10.1046/j.1365-2540.2001.0947b.x · Cited by 628
Ultrafast endocytosis at mouse hippocampal synapses
Watanabe, S., Rost, B. R., Camacho-Pérez, M., Davis, M. W., Söhl-Kielczynski, B., Rosenmund, C., & Jorgensen, E. M. (2013) · Nature · doi:10.1038/nature12809 · Cited by 607 · cited 1×
“Even seasoned field biologists are still surprised by the new adaptations they discover, which they express in popular press accounts of their work [77, 100, 111], but only more rarely in official academic publications, for example, in [41] but not in [76, 142].”
Evolution of biological complexity
Adami, C., Ofria, C., & Collier, T. C. (2000) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.97.9.4463 · Cited by 596 · cited 2×
“Yet both philosophical arguments [23, 26, 27, 82, 109] and high-profile publications [2, 16, 18 – 21, 52, 59, 60, 83, 85, 86, 92, 141, 146, 148] suggest that digital evolution can be a useful tool to aid and complement the study of biological evolution.”
Self-citationLangton, C. G. (1995) · Cited by 580
Neutral evolution of mutational robustness
van Nimwegen, E., Crutchfield, J. P., & Huynen, M. (1999) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.96.17.9716 · Cited by 568
(2020) · The Art of Political Storytelling · doi:10.5040/9781350107427.0018 · Cited by 544 · cited 1×
“that a copper atom exists at the tip of a statue’s nose is better understood at the level of history and politics rather than at the level of physics [63]).”
Such, F. P., Madhavan, V., Conti, E., Lehman, J., Stanley, K. O., & Clune, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.06567 · Cited by 525 · cited 2×
“Atari games are a common benchmark in deep reinforcement learning [94, 95, 117, 132].”
Self-citationThe evolutionary origins of modularity
Clune, J., Mouret, J.-B., & Lipson, H. (2013) · Proceedings of the Royal Society B: Biological Sciences · doi:10.1098/rspb.2012.2863 · Cited by 466 · cited 1×
“Yet both philosophical arguments [13, 18, 31, 14, 34] and high-profile publications [35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50] suggest that digital evolution can be a useful tool to aid and complement the study of biological evolution.”
Self-citationRoese, N. J., & Vohs, K. D. (2012) · Perspectives on Psychological Science · doi:10.1177/1745691612454303 · Cited by 457
Problems of Monetary Management: The UK Experience
Goodhart, C. A. E. (1984) · Monetary Theory and Practice · doi:10.1007/978-1-349-17295-5_4 · Cited by 416 · cited 1×
“Just as well-intentioned metrics in human society can become corrupted by direct pressure to optimize them (known as Campbell’s law [66] or Goodhart’s law [67]), digital evolution often acts to fulfill the letter of the law (i.”
Frequency-dependent predation, crypsis and aposematic coloration
Endler, J. A. (1988) · Philosophical Transactions of the Royal Society of London. B, Biological Sciences · doi:10.1098/rstb.1988.0062 · Cited by 390
Real-Time Neuroevolution in the NERO Video Game
Stanley, K. O., Bryant, B. D., & Miikkulainen, R. (2005) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2005.856210 · Cited by 390 · cited 1×
“Why Walk Around the Wall When You Can Walk Over It? The NeuroEvolving Robotic Operatives (NERO) video game applied digital evolution to enable non-player characters to evolve in real time while the game is being played [85].”
Self-citationIlluminating search spaces by mapping elites
Mouret, J.-B., & Clune, J. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1504.04909 · Cited by 386 · cited 2×
“Toevolve a large diversity of gaits, the team used the MAP-Elites evolutionary algorithm [99], which simultaneously searches for the fittest organism over every combination of chosen dimensions of variation (i.e., ways that phenotypes can vary).”
Self-citationAvida: A Software Platform for Research in Computational Evolutionary Biology
Ofria, C., & Wilke, C. O. (2004) · Artificial Life · doi:10.1162/106454604773563612 · Cited by 378
Self-citationEvolutionary computation: a unified approach
(2006) · Choice Reviews Online · doi:10.5860/choice.44-2154 · Cited by 370
Foundations of Genetic Algorithms
Sakawa, M. (2002) · Operations Research/Computer Science Interfaces Series · doi:10.1007/978-1-4615-1519-7_2 · Cited by 352
The Evolution of Evolvability in Genetic Programming
(2003) · Advances in Genetic Programming · doi:10.7551/mitpress/1108.003.0008 · Cited by 325
Genome complexity, robustness and genetic interactions in digital organisms
Lenski, R. E., Ofria, C., Collier, T. C., & Adami, C. (1999) · Nature · doi:10.1038/23245 · Cited by 306 · cited 2×
“Yet both philosophical arguments [23, 26, 27, 82, 109] and high-profile publications [2, 16, 18 – 21, 52, 59, 60, 83, 85, 86, 92, 141, 146, 148] suggest that digital evolution can be a useful tool to aid and complement the study of biological evolution.”
Self-citationForming Neural Networks Through Efficient and Adaptive Coevolution
Moriarty, D. E., & Miikkulainen, R. (1997) · Evolutionary Computation · doi:10.1162/evco.1997.5.4.373 · Cited by 304 · cited 1×
“One of the entries, however, was a player based on the SANE neuroevolution approach for playing Othello [96, 98].”
Self-citationVarying environments can speed up evolution
Kashtan, N., Noor, E., & Alon, U. (2007) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0611630104 · Cited by 288 · cited 1×
“Yet both philosophical arguments [23, 26, 27, 82, 109] and high-profile publications [2, 16, 18 – 21, 52, 59, 60, 83, 85, 86, 92, 141, 146, 148] suggest that digital evolution can be a useful tool to aid and complement the study of biological evolution.”
Evolving 3D Morphology and Behavior by Competition
Sims, K. (1994) · Artificial Life · doi:10.1162/artl.1994.1.4.353 · Cited by 284 · cited 3×
“Digital evolution does encompass paradigms like virtual creatures evolving completely in silico [126].”
Self-citationAn evolved circuit, intrinsic in silicon, entwined with physics
Thompson, A. (1997) · Lecture Notes in Computer Science · doi:10.1007/3-540-63173-9_61 · Cited by 280 · cited 1×
“This off-loading is similar to seminal work by Adrian Thompson in evolving real-world electronic circuits [101].”
Embodied Evolution: Distributing an evolutionary algorithm in a population of robots
Watson, R. A., Ficici, S. G., & Pollack, J. B. (2002) · Robotics and Autonomous Systems · doi:10.1016/s0921-8890(02)00170-7 · Cited by 275 · cited 2×
“The simple robots they built had two wheels, two motors, and two light sensors [102, 103].”
Self-citationBedau, M. A. (1997) · Noûs · doi:10.1111/0029-4624.31.s11.17 · Cited by 269
Pleiotropy as a mechanism to stabilize cooperation
Foster, K. R., Shaulsky, G., Strassmann, J. E., Queller, D. C., & Thompson, C. R. L. (2004) · Nature · doi:10.1038/nature02894 · Cited by 262 · cited 1×
“There is anecdotal evidence of similar mechanisms reducing the evolutionary potential toward cheating behavior in microbes [46, 103], but overlapping genes had never been studied in this context.”
Modeling evolutionary landscapes: Mutational stability, topology, and superfunnels in sequence space
Bornberg-Bauer, E., & Chan, H. S. (1999) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.96.19.10689 · Cited by 257 · cited 1×
“…that natural selection could favor robustness over finding the fittest organisms was discovered only in the 1980s [123], and later, in digital evolution, as selection for “ conservative code ” [3], neutral evolution, of mutational robustness [10, 102], and “ survival of the flattest ” [123, 146].”
Evolutionary Conditions for the Emergence of Communication in Robots
Floreano, D., Mitri, S., Magnenat, S., & Keller, L. (2007) · Current Biology · doi:10.1016/j.cub.2007.01.058 · Cited by 255
Self-citationNogueira, T., Rankin, D. J., Touchon, M., Taddei, F., Brown, S. P., & Rocha, E. P. C. (2009) · Current Biology · doi:10.1016/j.cub.2009.08.056 · Cited by 244 · cited 1×
“There is anecdotal evidence of similar mechanisms reducing the evolutionary potential toward cheating behavior in microbes [46, 103], but overlapping genes had never been studied in this context.”
A Comparison of Bloat Control Methods for Genetic Programming
Luke, S., & Panait, L. (2006) · Evolutionary Computation · doi:10.1162/evco.2006.14.3.309 · Cited by 239 · cited 1×
“As evolution progressed across generations, evolved ge-netic programs kept becoming larger and larger, a phenomenon called bloat [73, 87, 125], which eventually slowed the algorithm to a crawl because it took so long to run the huge evolved programs to test their fitness.”
A genetic programming approach to automated software repair
Forrest, S., Nguyen, T., Weimer, W., & Le Goues, C. (2009) · Proceedings of the 11th Annual conference on Genetic and evolutionary computation · doi:10.1145/1569901.1570031 · Cited by 236 · cited 1×
“One such algorithm is GenProg [45], which applies digital evolution to evolve code (called genetic programming [68]).”
Self-citationFrame, M., & Flake, G. W. (2000) · The American Mathematical Monthly · doi:10.2307/2589369 · Cited by 226 · cited 1×
“Indeed, within the field of complex systems it is well-known that simple programs can yield complex and surprising results when executed [59, 60]; such results relate to the broader concept of emergence [61, 62], wherein a phenomenon resulting from lower-level parts is best understood at a more abstract level of descr…”
An Evolutionary Approach to Synthetic Biology: Zen and the Art of Creating Life
Ray, T. S. (1993) · Artificial Life · doi:10.1162/artl.1993.1.179 · Cited by 219
Self-citationDirected evolution of industrial enzymes
Schmidt-Dannert, C., & Arnold, F. H. (1999) · Trends in Biotechnology · doi:10.1016/s0167-7799(98)01283-9 · Cited by 215 · cited 1×
“However, the result is often something that meets the heuristic but deviates from the ideal outcome in surprising ways [147, 148].”
McNamara, J. (2002) · Cited by 215
Balancing Robustness and Evolvability
Lenski, R. E., Barrick, J. E., & Ofria, C. (2006) · PLoS Biology · doi:10.1371/journal.pbio.0040428 · Cited by 211 · cited 2×
“Whole Genome Duplication in Avida Avida is a rich and versatile platform for digital evolution, one that has been used to study many fundamental evolutionary questions [35, 104, 39, 41, 42, 43, 44, 45, 48, 105, 49, 50].”
Self-citationCheney, N., MacCurdy, R., Clune, J., & Lipson, H. (2013) · Proceedings of the 15th annual conference on Genetic and evolutionary computation · doi:10.1145/2463372.2463404 · Cited by 211
Self-citationStationary mutant distributions and evolutionary optimization
Schuster, P., & Swetina, J. (1988) · Bulletin of Mathematical Biology · doi:10.1007/bf02460094 · Cited by 207 · cited 1×
“But the idea that natural selection could favor robustness over finding the fittest organisms was discovered only in the 1980s [129], and later in digital evolution as selection for “conservative code” [123], neutral evolution of mutational robustness [130, 131], and “survival of the flattest” [132, 129].”
Langdon, W. B., & Poli, R. (1998) · Soft Computing in Engineering Design and Manufacturing · doi:10.1007/978-1-4471-0427-8_2 · Cited by 203
Picbreeder: A Case Study in Collaborative Evolutionary Exploration of Design Space
Secretan, J., Beato, N., D'Ambrosio, D. B., Rodriguez, A., Campbell, A., Folsom-Kovarik, J. T., & Stanley, K. O. (2011) · Evolutionary Computation · doi:10.1162/evco_a_00030 · Cited by 203 · cited 2×
“And yet, in the case of Picbreeder [106], one such surprise was career-altering.”
Self-citationArtificial life: organization, adaptation and complexity from the bottom up
Bedau, M. (2003) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2003.09.012 · Cited by 201
Explicitly Defined Introns and Destructive Crossover in Genetic Programming
(1996) · Advances in Genetic Programming · doi:10.7551/mitpress/1109.003.0010 · Cited by 199
Moonlight drives ocean-scale mass vertical migration of zooplankton during the arctic winter
Last, K. S., Hobbs, L., Berge, J., Brierley, A. S., & Cottier, F. (2016) · Current Biology · doi:10.1016/j.cub.2015.11.038 · Cited by 193 · cited 1×
“Even seasoned field biologists are still surprised by the new adaptations they discover, which they express in popular press accounts of their work [77, 100, 111], but only more rarely in official academic publications, for example, in [41] but not in [76, 142].”
New insights into bacterial adaptation through in vivo and in silico experimental evolution
Hindré, T., Knibbe, C., Beslon, G., & Schneider, D. (2012) · Nature Reviews Microbiology · doi:10.1038/nrmicro2750 · Cited by 192
Self-citationProtein engineers turned evolutionists
Peisajovich, S. G., & Tawfik, D. S. (2007) · Nature Methods · doi:10.1038/nmeth1207-991 · Cited by 166 · cited 2×
“…connections between surprising results in digital evolution and the products of directed evolution in biology, wherein selection in an experimenter-controlled evolutionary process is manipulated with the hope of improving or adapting proteins or nucleic acids for practical purposes [5, 108].”
Silva, S., & Costa, E. (2009) · Genetic Programming and Evolvable Machines · doi:10.1007/s10710-008-9075-9 · Cited by 160
Evolutionary Advantages of Neuromodulated Plasticity in Dynamic, Reward-based Scenarios
Soltoggio, A., Bullinaria, J. A., Mattiussi, C., Dürr, P., & Floreano, D. (2008) · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · Cited by 154
Neural Modularity Helps Organisms Evolve to Learn New Skills without Forgetting Old Skills
Ellefsen, K. O., Mouret, J.-B., & Clune, J. (2015) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1004128 · Cited by 151
Self-citation(1997) · Computers & Mathematics with Applications · doi:10.1016/s0898-1221(97)84604-4 · Cited by 150
Digital genetics: unravelling the genetic basis of evolution
Adami, C. (2006) · Nature Reviews Genetics · doi:10.1038/nrg1771 · Cited by 148 · cited 1×
“Avida is a rich and versatile platform for digital evolution, one that has been used to study many fundamental evolutionary questions [1, 2, 16, 18, 20, 34, 52, 83, 85, 86, 92, 146].”
Self-citationChapter 3 Invasion of the Body Snatchers
Léfèvre, T., Adamo, S. A., Biron, D. G., Missé, D., Hughes, D. P., & Frédéric Thomas, A. (2009) · Advances in Parasitology/Advances in parasitology · doi:10.1016/s0065-308x(08)00603-9 · Cited by 144
(2007) · Choice Reviews Online · doi:10.5860/choice.44-6576 · Cited by 142
Biochemistry at 100°C: Explosive Secretory Discharge of Bombardier Beetles ( Brachinus )
Aneshansley, D. J., Eisner, T., Widom, J. M., & Widom, B. (1969) · Science · doi:10.1126/science.165.3888.61 · Cited by 138 · cited 1×
“…to attract echo-locating bats [121], extremophile microbes repair their DNA to thrive in the presence of extreme radiation [89], bombardier beetles repel predators with explosive chemical reactions [131], and parasites reprogram host brains, inducing suicide for the parasite ʼ s own gain [78].”
Everitt, T., Lea, G., & Hutter, M. (2018) · International Joint Conference on Artificial Intelligence · doi:10.48550/arxiv.1805.01109 · Cited by 134 · cited 1×
“For example, beyond their importance to digital evolution, the many examples of “misspecified fitness functions” in this article connect to the broader field of artificial intelligence safety: Many researchers therein are concerned with the potential for perverse outcomes from optimizing reward functions that appear s…”
BackgroundAdaptive Radiation from Resource Competition in Digital Organisms
Chow, S. S., Wilke, C. O., Ofria, C., Lenski, R. E., & Adami, C. (2004) · Science · doi:10.1126/science.1096307 · Cited by 131 · cited 2×
“Yet both philosophical arguments [23, 26, 27, 82, 109] and high-profile publications [2, 16, 18 – 21, 52, 59, 60, 83, 85, 86, 92, 141, 146, 148] suggest that digital evolution can be a useful tool to aid and complement the study of biological evolution.”
Self-citationExperiments on the role of deleterious mutations as stepping stones in adaptive evolution
Covert, A. W., Lenski, R. E., Wilke, C. O., & Ofria, C. (2013) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1313424110 · Cited by 123 · cited 1×
“Avida is a rich and versatile platform for digital evolution, one that has been used to study many fundamental evolutionary questions [1, 2, 16, 18, 20, 34, 52, 83, 85, 86, 92, 146].”
Self-citationSexual reproduction reshapes the genetic architecture of digital organisms
Misevic, D., Ofria, C., & Lenski, R. E. (2006) · Proceedings of the Royal Society B: Biological Sciences · doi:10.1098/rspb.2005.3338 · Cited by 120
Self-citationCombinatorial protein design: strategies for screening protein libraries
Zhao, H., & Arnold, F. H. (1997) · Current Opinion in Structural Biology · doi:10.1016/s0959-440x(97)80110-8 · Cited by 116
Task-switching costs promote the evolution of division of labor and shifts in individuality
Goldsby, H. J., Dornhaus, A., Kerr, B., & Ofria, C. (2012) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1202233109 · Cited by 113
Self-citationDiscovering Complex Othello Strategies through Evolutionary Neural Networks
Moriarty, D. E., & Miikkulainen, R. P. (1995) · Connection Science · doi:10.1080/09540099550039228 · Cited by 111
Self-citation(1999) · Choice Reviews Online · doi:10.5860/choice.36-3948 · Cited by 111
A Long-Term Evolutionary Pressure on the Amount of Noncoding DNA
Knibbe, C., Coulon, A., Mazet, O., Fayard, J., & Beslon, G. (2007) · Molecular Biology and Evolution · doi:10.1093/molbev/msm165 · Cited by 107 · cited 1×
“The effect on the noncoding region could be observed in Aevol because the model included chromosomal rearrangements in addition to point mutations [63].”
BackgroundSelf-citationEveritt, T., Lea, G., & Hutter, M. (2018) · Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/768 · Cited by 105
Clune, J., Misevic, D., Ofria, C., Lenski, R. E., Elena, S. F., & Sanjuán, R. (2008) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1000187 · Cited by 104 · cited 3×
“Yet both philosophical arguments [23, 26, 27, 82, 109] and high-profile publications [2, 16, 18 – 21, 52, 59, 60, 83, 85, 86, 92, 141, 146, 148] suggest that digital evolution can be a useful tool to aid and complement the study of biological evolution.”
Self-citationBack to Basics: Benchmarking Canonical Evolution Strategies for Playing Atari
Chrabąszcz, P., Loshchilov, I., & Hutter, F. (2018) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/197 · Cited by 104
Self-citationEmbodied evolution: embodying an evolutionary algorithm in a population of robots
Watson, R. A., Ficiei, S. G., & Pollack, J. B. (2003) · Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406) · doi:10.1109/cec.1999.781944 · Cited by 103 · cited 2×
“The simple robots they built had two wheels, two motors, and two light sensors [102, 103].”
Self-citationThe Princeton guide to evolution
(2014) · Choice Reviews Online · doi:10.5860/choice.51-5585 · Cited by 99
Quadratic bloat in genetic programming
Langdon, W. B. (2000) · Cited by 92
Kouvaris, K., Clune, J., Kounios, L., Brede, M., & Watson, R. A. (2017) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1005358 · Cited by 92 · cited 1×
“Even in the absence of direct foresight, studies of evolvability suggest that genomic architecture itself can become biased toward increasing creative potential [62, 65, 66].”
Self-citationClune, J., Misevic, D., Ofria, C., Lenski, R. E., Elena, S. F., & Sanjuán, R. (2013) · Genetic and Evolutionary Computation Conference Companion (GECCO Companion) · doi:10.1145/2464576.2464597 · Cited by 90
Self-citationChance and Creativity in Evolution
Dobzhansky, T. (1974) · doi:10.1007/978-1-349-01892-5_18 · Cited by 86
Macroevolution simulated with autonomously replicating computer programs
Yedid, G., & Bell, G. (2002) · Nature · doi:10.1038/nature01151 · Cited by 82
The evolution of information suppression in communicating robots with conflicting interests
Mitri, S., Floreano, D., & Keller, L. (2009) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0903152106 · Cited by 78
Self-citationAutomated program repair through the evolution of assembly code
Schulte, E., Forrest, S., & Weimer, W. R. (2010) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1145/1858996.1859059 · Cited by 73 · cited 1×
“With these files missing, because of how the test function was written, it awarded perfect fitness scores to the rogue candidate and to all of its peers [122].”
Self-citationThe Nature of Life: Classical and Contemporary Perspectives from Philosophy and Science
Bedau, M. A., & Cleland, C. E. (2010) · Cited by 64
Alignment for Advanced Machine Learning Systems
Taylor, J., Yudkowsky, E., LaVictoire, P., & Critch, A. (2020) · Ethics of Artificial Intelligence · doi:10.1093/oso/9780190905033.003.0013 · Cited by 59
On-Line, On-Board Evolution of Robot Controllers
Bredèche, N., Haasdijk, E., & Eiben, A. E. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-14156-0_10 · Cited by 57 · cited 1×
“It also includes the fields of evolvable hardware and evolutionary robotics, where evolved digital programs or controllers are deployed on real-world devices [13].”
BackgroundGeneric Evolutionary Design of Solid Objects using a Genetic Algorithm
Bentley, P. J. (2007) · UCL Discovery (University College London) · Cited by 54
Self-citationGenerating diverse software versions with genetic programming: an experimental study
Feldt, R. (1998) · IEE Proceedings - Software · doi:10.1049/ip-sen:19982444 · Cited by 54 · cited 2×
“In 1997, Feldt applied digital evolution to simulations of mechanical systems to try to evolve mechanisms that safely, but rapidly, decelerate aircraft as they land on an aircraft carrier [38].”
Self-citationProceedings of the 2nd Annual Conference on Genetic and Evolutionary Computation
Whitley, L. D., Goldberg, D. E., Cantú‐Paz, E., Spector, L. C., & Parmee, I. C. (2000) · Cited by 52
Improving evolvability through novelty search and self-adaptation
Lehman, J., & Stanley, K. O. (2011) · IEEE Congress on Evolutionary Computation (CEC) · doi:10.1109/cec.2011.5949955 · Cited by 50 · cited 1×
“Interestingly, this phenomenon goes away when evolution is not forced to focus on short term fitness improvement [126].”
Self-citationBats Are Acoustically Attracted to Mutualistic Carnivorous Plants
Schöner, M. G., Schöner, C. R., Simon, R., Grafe, T. U., Puechmaille, S. J., Ji, L. L., & Kerth, G. (2015) · Current Biology · doi:10.1016/j.cub.2015.05.054 · Cited by 49 · cited 1×
“Some flowers act as acoustic beacons to attract echo-locating bats [121], extremophile microbes repair their DNA to thrive in the presence of extreme radiation [89], bombardier beetles repel predators with explosive chemical reactions [131], and parasites reprogram host brains, inducing suicide for…”
Avoiding Wireheading with Value Reinforcement Learning
Everitt, T., & Hütter, M. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-41649-6_2 · Cited by 49 · cited 1×
“…for perverse outcomes from optimizing reward functions that appear sensible on their surface [4, 11, 37, 134], characterized in that community as problems such as avoiding negative side effects [4, 69], reward hacking (also known as wire-heading) [4, 36], or more generally AI alignment [134].”
Neutrality in evolutionary algorithms… What do we know?
Galván, E., Poli, R., Kattan, A. J., O’Neill, M., & Brabazon, A. (2011) · Evolving Systems · doi:10.1007/s12530-011-9030-5 · Cited by 48
Nguyen, A., Yosinski, J., & Clune, J. (2016) · Evolutionary Computation · doi:10.1162/evco_a_00189 · Cited by 45 · cited 1×
“An Art Museum Accepts and Displays Evolved Art Produced by Innovation Engines The Innovation Engine [109] is an algorithm that combines three keys ideas: (1) produce new innovations (i.”
Self-citationModels, simulations, instantiations, and evidence: the case of digital evolution
Pennock, R. T. (2007) · Journal of Experimental & Theoretical Artificial Intelligence · doi:10.1080/09528130601116113 · Cited by 44 · cited 1×
“Indeed, these evolving systems can be seen as real instances of evolution, rather than mere simulation of evolution [110].”
Self-citationA Hierarchical Approach to Learning the Boolean Multiplexer Function
Koza, J. R. (1991) · Foundations of genetic algorithms · doi:10.1016/b978-0-08-050684-5.50014-8 · Cited by 41 · cited 1×
“Impossibly Compact Solutions To test a distributed computation platform called EC-star [99], Babak Hodjat implemented a multiplexer problem [100], wherein the objective is to learn how to selectively forward an input signal.”
Evolving Obstacle Avoidance Behavior in a Robot Arm
Moriarty, D. E., & Miikkulainen, R. P. (1996) · The MIT Press eBooks · doi:10.7551/mitpress/3118.003.0056 · Cited by 40 · cited 1×
“A similar result was noted by Moriarty and Miikkulainen in 1996 [97].”
ResultSelf-citationHuman-competitive lens system design with evolution strategies
Gagné, C., Beaulieu, J., Parizeau, M., & Thibault, S. (2008) · Applied Soft Computing · doi:10.1016/j.asoc.2007.10.018 · Cited by 37 · cited 1×
“Two families of solutions that were identified as likely being optimal in an article using an optimization algorithm not based on evolution [107] were easily outperformed, by a factor of two, by a solution discovered though digital evolution by Gagné et al. [50].”
Self-citationGenetic Architecture Promotes the Evolution and Maintenance of Cooperation
Frénoy, A., Taddéi, F., & Misevic, D. (2013) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1003339 · Cited by 35
Self-citationWhen did theropods become feathered?—evidence for pre-archaeopteryx feathery appendages
Kundrát, M. (2004) · Journal of Experimental Zoology Part B Molecular and Developmental Evolution · doi:10.1002/jez.b.20014 · Cited by 33 · cited 1×
“For example, a leading theory is that feathers first evolved in dinosaurs for temperature regulation [71] and were later exapted for flight in birds.”
Monochromatic quartet: a search for the global optimum
O'Shea, D. C. (1991) · SPIE Proceedings · doi:10.1117/12.47896 · Cited by 27 · cited 1×
“Two families of solutions that were identified as likely being optimal in an article using an optimization algorithm not based on evolution [107] were easily outperformed, by a factor of two, by a solution discovered though digital evolution by Gagné et al. [50].”
Penalizing side effects using stepwise relative reachability
Krakovna, V., Orseau, L., Kumar, R., Martic, M., & Legg, S. (2018) · arXiv · doi:10.48550/arxiv.1806.01186 · Cited by 26
Kounios, L., Clune, J., Kouvaris, K., Wagner, G. P., Pavličev, M., Weinreich, D. M., & Watson, R. A. R. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.05955 · Cited by 25 · cited 1×
“Even in the absence of direct foresight, studies of evolvability suggest that genomic architecture itself can become biased toward increasing creative potential [62, 66, 65].”
BackgroundSelf-citationA Model for Genome Size Evolution
Fischer, S., Bernard, S., Beslon, G., & Knibbe, C. (2014) · Bulletin of Mathematical Biology · doi:10.1007/s11538-014-9997-8 · Cited by 23 · cited 1×
“This random encounter opened a new research direction that ultimately led to a more general mathematical model of genome evolution, showing that indirect selection for robustness to large duplications and deletions strongly bounds genome size [42].”
Self-citationBacterial Habitats in Extreme Environments
Madigan, M. T. (2000) · Springer eBooks · doi:10.1007/978-94-011-4269-4_5 · Cited by 22 · cited 1×
“Many more examples abound, covering the full range of biological systems [24, 49, 88].”
Bentley, P. J. (1999) · Cited by 19
Self-citationEC-Star: A Massive-Scale, Hub and Spoke, Distributed Genetic Programming System
O’Reilly, U.-M., Wagy, M. D., & Hodjat, B. (2013) · Genetic and evolutionary computation · doi:10.1007/978-1-4614-6846-2_6 · Cited by 17 · cited 1×
“To test a distributed computation platform called EC-star [106], Babak Hodjat implemented a multiplexer problem [67], wherein the objective is to learn how to selectively forward an input signal.”
Self-citationLau, N. C., & Bartel, D. P. (2003) · Scientific American · doi:10.1038/scientificamerican0803-34 · Cited by 17 · cited 1×
“Even seasoned field biologists are still surprised by the new adaptations they discover, which they express in popular press accounts of their work [77, 100, 111], but only more rarely in official academic publications, for example, in [41] but not in [76, 142].”
Effects of public good properties on the evolution of cooperation
Misevic, D., Frénoy, A., Parsons, D. P., & Taddéi, F. (2012) · Conference on Artificial Life (ALIFE) · doi:10.7551/978-0-262-31050-5-ch030 · Cited by 17 · cited 1×
“The Aevol system has recently been used to study cooperation [91, 47], by giving individuals the ability to secrete a public good molecule, which benefits all digital organisms in the neighborhood.”
MethodSelf-citationMeasuring and avoiding side effects using relative reachabilityPreprint
Krakovna, V., Orseau, L., Martic, M., & Legg, S. (2018) · arXiv (Cornell University) · Cited by 16
Advances in Automated Program Repair and a Call to Arms
Weimer, W. (2013) · International Symposium on Search Based Software Engineering · doi:10.1007/978-3-642-39742-4_1 · Cited by 15 · cited 2×
“In another project, to avoid runaway computation, the fitness function explicitly limited a program’s CPU usage: in response, GenProg produced programs that slept forever, which did not count toward CPU usage limits, since there were no computations actually performed [64].”
BackgroundMethodSelf-citationA Case Study of the De Novo Evolution of a Complex Odometric Behavior in Digital Organisms
Grabowski, L. M., Bryson, D., Dyer, F. C., Pennock, R. T., & Ofria, C. (2013) · PLoS ONE · doi:10.1371/journal.pone.0060466 · Cited by 13 · cited 2×
“While some such unexpected results have been published [9, 55, 90, 109], most have not, and they have not previously been presented together, as they are here.”
Self-citationSimderella: A robot simulator for neuro-controller design
van der Smagt, P. (1994) · Neurocomputing · doi:10.1016/0925-2312(94)90063-9 · Cited by 13
Robustness and evolvability of cooperation
Frénoy, A., Taddéi, F., & Misevic, D. (2012) · Conference on Artificial Life (ALIFE) · doi:10.7551/978-0-262-31050-5-ch008 · Cited by 11
Self-citationWebAL Comes of Age: A Review of the First 21 Years of Artificial Life on the Web
Taylor, T., Auerbach, J. E., Bongard, J., Clune, J., Hickinbotham, S., Ofria, C., Oka, M., Risi, S., Stanley, K. O., & Yosinski, J. (2016) · Artificial Life · doi:10.1162/artl_a_00211 · Cited by 11 · cited 1×
“We also appreciate Tim Taylor, from whom we got the idea for crowd-sourcing the writing of this paper by an open call for material from the community in which those whose submissions were accepted would become co-authors of the paper; he successfully piloted that model for a paper we were a part of [150], and we adopt…”
Self-citationTowards Efficient Evolutionary Design of Autonomous Robots
Krčah, P. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-85857-7_14 · Cited by 10 · cited 4×
“Virtual creatures evolved in the ERO system by Krcah [70] displayed a curious property: They sometimes contained small body parts whose function was not immediately obvious, yet they seemed to be carefully placed on the creature ʼ s body.”
BackgroundMethodInfluentialPennock, R. T. (2000) · Foundations of Science · doi:10.1023/a:1011356415685 · Cited by 9 · cited 2×
“Yet both philosophical arguments [16, 21, 34, 17, 40] and high-profile publications [41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56] suggest that digital evolution can be a useful tool to aid and complement the study of biological evolution.”
Self-citationElsberry, W. R., Grabowski, L. M., Ofria, C., & Pennock, R. T. (2009) · IEEE Symposium on Artificial Life (ALIFE) · doi:10.1109/alife.2009.4937699 · Cited by 8
Self-citationNatural Selection and Adaptation
Wool, D. (2006) · CRC Press eBooks · doi:10.1201/b10758-13 · Cited by 8
Evolutionary Algorithms as fitness function debuggers
Mansanné, F., Carrère, F., Ehinger, A., & Schoenauer, M. (1999) · Lecture notes in computer science · doi:10.1007/bfb0095153 · Cited by 7 · cited 3×
“Marc Schoenauer relates attempting to infer underground geological composition by analyzing echoes of controlled explosions [20].”
Self-citationInvestigating Biological Assumptions through Radical Reimplementation
Lehman, J., & Stanley, K. O. (2014) · Artificial Life · doi:10.1162/artl_a_00150 · Cited by 7 · cited 1×
“Yet both philosophical arguments [16, 21, 34, 17, 40] and high-profile publications [41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56] suggest that digital evolution can be a useful tool to aid and complement the study of biological evolution.”
Self-citationLehman, J. (2020) · Genetic and evolutionary computation · doi:10.1007/978-3-030-39958-0_10 · Cited by 7
Self-citationBiomimetic Software Engineering Techniques for Dependability
FELDT, R. H. (2002) · Chalmers Publication Library (Chalmers University of Technology) · Cited by 6
Self-citationEvolving Obstacle Avoidance Behavior in a Robot Arm
Maes, P., Matarić, M. J., Meyer, J.-A., Pollack, J. B., & Wilson, S. W. (1996) · Cited by 3
Lehman, J. (2019) · arXiv · doi:10.48550/arxiv.1906.10189 · Cited by 3 · cited 1×
“This awareness is most important for safety-critical applications, and points to the need for careful supervision when attempting to apply digital evolution in real-world systems [79].”
Self-citationLenski, R. E. (1998) · Science · doi:10.1126/science.280.5365.849 · Cited by 3 · cited 1×
“The general idea is that there exist abstract principles underlying biological evolution that are independent of the physical medium [23], and that these principles can be effectively implemented and studied within computers [84].”
Self-citationBack to Basics: Benchmarking Canonical Evolution Strategies for Playing Atari
Chrabaszcz, P., Loshchilov, I., & Hutter, F. (2018) · arXiv · doi:10.48550/arxiv.1802.08842
Self-citation
Research works printed but not linked: 13
- Bentley P. J., 1999, Proceedings of the AISB, 99, 28
- Bredeche N., 2009, International Conference on Artificial Evolution EA2009, 110
- Darwin C., 1859, On the origin of species
- Ecarlat P., 2015, Proceedings of Learning Objects Affordances Workshop at IROS 2016, 1
- Feldt R., 1999, Proceedings of the 1st International Workshop on Soft Computing Applied to Software Engineering, 11
- Nordin P., 1996, Advances in genetic programming, 2, 111
- Ray T., 1992, Le Temps stratégique, 47, 68
- 10.1162/artl.1993.1.1_2.179 · doi:10.1162/artl.1993.1.1_2.179 · Paper page
- Rechenberg I., 1973, Evolutionsstrategie–Optimierung technisher Systeme nach Prinzipien der biologischen Evolution
- 10.1016/S0092-8240(88)80059-4 · doi:10.1016/s0092-8240(88)80059-4 · Paper page
- Soltoggio A., 2008, Proceedings of the 11th International Conference on Artificial Life (Alife XI), 569
- Thompson A., 1996, International Conference on Evolvable Systems, 390
- Vincent J., 2018, The Verge
Cited by
Shortcut learning in deep neural networks
Geirhos, R., Jacobsen, J.-H., Michaelis, C., Zemel, R., Brendel, W., Bethge, M., & Wichmann, F. A. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-020-00257-z · Cited by 2,224
Next-Generation Experimentation with Self-Driving Laboratories
Häse, F., Roch, L. M., & Aspuru-Guzik, A. (2019) · Trends in Chemistry · doi:10.1016/j.trechm.2019.02.007 · Cited by 426
Emergent Tool Use From Multi-Agent Autocurricula
Baker, B., Kanitscheider, I., Markov, T., Wu, Y., Powell, G., McGrew, B., & Mordatch, I. (2019) · arXiv · doi:10.48550/arxiv.1909.07528 · Cited by 424
“[66] Joel Lehman, Jeff Clune, Dusan Misevic, Christoph Adami, Lee Altenberg, Julie Beaulieu, Peter J Bentley, Samuel Bernard, Guillaume Beslon, David M Bryson, et al.”
BackgroundDeep Learning for Intelligent Transportation Systems: A Survey of Emerging Trends
Veres, M., & Moussa, M. (2020) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2929020 · Cited by 394
On scientific understanding with artificial intelligence
Krenn, M., Pollice, R., Guo, S. Y., Aldeghi, M., Cervera-Lierta, A., Friederich, P., dos Passos Gomes, G., Häse, F., Jinich, A., Nigam, A., et al. (2022) · Nature Reviews Physics · doi:10.1038/s42254-022-00518-3 · Cited by 372
“[42] Joel Lehman, Jeff Clune, Dusan Misevic, Christoph Adami, Lee Altenberg, Julie Beaulieu, Peter J Bentley, Samuel Bernard, Guillaume Beslon, David M Bryson, et al.”
Background
Metadata
- Authors
- Lehman, J., Clune, J., Misevic, D., Adami, C., Altenberg, L., Beaulieu, J., Bentley, P. J., Bernard, S., Beslon, G., Bryson, D. M., Cheney, N., Chrabaszcz, P., Cully, A., Doncieux, S., Dyer, F. C., Ellefsen, K. O., Feldt, R., Fischer, S., Forrest, S., Fŕenoy, A., Gagńe, C., Le Goff, L., Grabowski, L. M., Hodjat, B., Hutter, F., Keller, L., Knibbe, C., Krcah, P., Lenski, R. E., Lipson, H., MacCurdy, R., Maestre, C., Miikkulainen, R., Mitri, S., Moriarty, D. E., Mouret, J.-B., Nguyen, A., Ofria, C., Parizeau, M., Parsons, D., Pennock, R. T., Punch, W. F., Ray, T. S., Schoenauer, M., Schulte, E., Sims, K., Stanley, K. O., Taddei, F., Tarapore, D., Thibault, S., Watson, R., Weimer, W., & Yosinski, J.
- Affiliations
- Uber AI (United States) (US)
- University of Wyoming (US)
- Inserm (FR)
- Michigan State University (US)
- University of Hawaiʻi at Mānoa (US)
- Université Laval (CA)
- University College London (GB)
- Centre National de la Recherche Scientifique (FR)
- University of Vermont (US)
- University of Freiburg
- Imperial College London (GB)
- Sorbonne Universités, UPMC Univ Paris 06, CNRS, Institute of Intelligent Systems and Robotics (ISIR)
- University of Oslo (NO)
- Chalmers University of Technology (SE)
- Institut national de recherche en sciences et technologies du numérique (FR)
- University of New Mexico (US)
- Université Grenoble Alpes
- Université Laval
- State University of New York (US)
- Cognizant (India) (IN)
- University of Lausanne (CH)
- Charles University Prague
- Columbia University (US)
- University of Colorado Boulder (US)
- The University of Texas at Austin (US)
- Apple (United States) (US)
- Norwegian University of Science and Technology (NO)
- University of Oklahoma (US)
- University of Central Florida (US)
- Center for Research and Interdisciplinarity, INSERM U1284, Université de Paris
- University of Southampton (GB)
- University of Virginia (US)
- ORCID
- Lehman, Joel
- Clune, Jeff
- Misevic, Dusan
- Adami, Christoph
- Altenberg, Lee
- Bentley, Peter J.
- Beslon, Guillaume
- Bryson, David M.
- Cheney, Nick
- Cully, Antoine
- Dyer, Fred C.
- Ellefsen, Kai Olav
- Feldt, Robert
- Forrest, Stephanie
- Hodjat, Babak
- Hutter, Frank
- Keller, Laurent
- Knibbe, Carole
- Lenski, Richard E.
- Lipson, Hod
- MacCurdy, Robert
- Miikkulainen, Risto
- Mitri, Sara
- Mouret, Jean-Baptiste
- Ofria, Charles
- Parizeau, Marc
- Parsons, David
- Pennock, Robert T.
- Schoenauer, Marc
- Stanley, Kenneth O.
- Tarapore, Danesh
- Thibault, Simon
- Watson, Richard
- Weimer, Westley
- Venue
- Artificial Life
- Publisher
- MIT Press
- Published
- 2020-05
- Volume
- 26
- Issue
- 2
- Pages
- 274-306
- ISSN
- 1064-5462 (ISSN-L)
- 1530-9185
- OpenAlex
- W3015475346
- Cited by
- 181
- References
- 160
- Citations by year
- 2026: 16 · 2025: 17 · 2024: 24 · 2023: 31 · 2022: 24 · 2021: 34 · 2020: 16
- FWCI
- 10.31
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Artificial Life (publishedVersion, cc-by)
- PubMed (publishedVersion)
- ePrints Soton (University of Southampton) (acceptedVersion)
- HAL (submittedVersion, other-oa)
- Chalmers Research (Chalmers University of Technology) (submittedVersion)
- IRIS (submittedVersion)
- SERVAL (Université de Lausanne) (submittedVersion)
- Spiral (Imperial College London) (submittedVersion)
- Funders
- National Science Foundation (CAREER, 1453549)
- Michigan State University
- College of Engineering, Michigan State University
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Evolutionary Algorithms and Applications
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Genetics › Evolution and Genetic Dynamics
- Social Sciences › Arts and Humanities › History and Philosophy of Science › Philosophy of Biology and Scientific Explanation
- Keywords
- digital evolution, evolutionary computation, digital organisms, algorithmic evolution, complex evolving systems
- MeSH terms
- Algorithms, Creativity, Biological Evolution, Computational Biology, Life
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.