Evolving the Behavior of Machines: From Micro to Macroevolution

Overview

Journal iScience

Publisher Cell Press

Date 2020 Nov 23

PMID 33225243

Citations 2

Authors

Jean-Baptiste Mouret

Affiliations

Soon will be listed here.

Abstract

Evolution gave rise to creatures that are arguably more sophisticated than the greatest human-designed systems. This feat has inspired computer scientists since the advent of computing and led to optimization tools that can evolve complex neural networks for machines-an approach known as "neuroevolution." After a few successes in designing evolvable representations for high-dimensional artifacts, the field has been recently revitalized by going beyond optimization: to many, the wonder of evolution is less in the perfect optimization of each species than in the creativity of such a simple iterative process, that is, in the diversity of species. This modern view of artificial evolution is moving the field away from microevolution, following a fitness gradient in a niche, to macroevolution, filling many niches with highly different species. It already opened promising applications, like evolving gait repertoires, video game levels for different tastes, and diverse designs for aerodynamic bikes.

Citing Articles

Open-endedness in synthetic biology: A route to continual innovation for biological design.

Stock M, Gorochowski T Sci Adv. 2024; 10(3):eadi3621.

PMID: 38241375 PMC: 11809665. DOI: 10.1126/sciadv.adi3621.

Automated exploration of DNA-based structure self-assembly networks.

Cazenille L, Baccouche A, Aubert-Kato N R Soc Open Sci. 2021; 8(10):210848.

PMID: 34754499 PMC: 8493194. DOI: 10.1098/rsos.210848.

MAP-Elites Enables Powerful Stepping Stones and Diversity for Modular Robotics.

Nordmoen J, Veenstra F, Ellefsen K, Glette K Front Robot AI. 2021; 8:639173.

PMID: 33996926 PMC: 8115726. DOI: 10.3389/frobt.2021.639173.

References

Jelisavcic M, De Carlo M, Hupkes E, Eustratiadis P, Orlowski J, Haasdijk E . Real-World Evolution of Robot Morphologies: A Proof of Concept. Artif Life. 2017; 23(2):206-235. DOI: 10.1162/ARTL_a_00231. View

Ahnert S . Structural properties of genotype-phenotype maps. J R Soc Interface. 2017; 14(132). PMC: 5550974. DOI: 10.1098/rsif.2017.0275. View

Erwin D . Macroevolution is more than repeated rounds of microevolution. Evol Dev. 2001; 2(2):78-84. DOI: 10.1046/j.1525-142x.2000.00045.x. View

Cully A, Clune J, Tarapore D, Mouret J . Robots that can adapt like animals. Nature. 2015; 521(7553):503-7. DOI: 10.1038/nature14422. View

Reznick D, Ricklefs R . Darwin's bridge between microevolution and macroevolution. Nature. 2009; 457(7231):837-42. DOI: 10.1038/nature07894. View

Cussat-Blanc S, Harrington K, Banzhaf W . Artificial Gene Regulatory Networks-A Review. Artif Life. 2019; 24(4):296-328. DOI: 10.1162/artl_a_00267. View

Wagner G, Pavlicev M, Cheverud J . The road to modularity. Nat Rev Genet. 2007; 8(12):921-31. DOI: 10.1038/nrg2267. View

Kashtan N, Alon U . Spontaneous evolution of modularity and network motifs. Proc Natl Acad Sci U S A. 2005; 102(39):13773-8. PMC: 1236541. DOI: 10.1073/pnas.0503610102. View

Kriegman S, Blackiston D, Levin M, Bongard J . A scalable pipeline for designing reconfigurable organisms. Proc Natl Acad Sci U S A. 2020; 117(4):1853-1859. PMC: 6994979. DOI: 10.1073/pnas.1910837117. View

10.

Floreano D, Mondada F . Evolutionary neurocontrollers for autonomous mobile robots. Neural Netw. 2003; 11(7-8):1461-1478. DOI: 10.1016/s0893-6080(98)00082-3. View

11.

Adams M, Celniker S, Holt R, Evans C, Gocayne J, Amanatides P . The genome sequence of Drosophila melanogaster. Science. 2000; 287(5461):2185-95. DOI: 10.1126/science.287.5461.2185. View

12.

Lindenmayer A . Mathematical models for cellular interactions in development. II. Simple and branching filaments with two-sided inputs. J Theor Biol. 1968; 18(3):300-15. DOI: 10.1016/0022-5193(68)90080-5. View

13.

Stanley K, DAmbrosio D, Gauci J . A hypercube-based encoding for evolving large-scale neural networks. Artif Life. 2009; 15(2):185-212. DOI: 10.1162/artl.2009.15.2.15202. View

14.

Lehman J, Stanley K . Evolvability is inevitable: increasing evolvability without the pressure to adapt. PLoS One. 2013; 8(4):e62186. PMC: 3634764. DOI: 10.1371/journal.pone.0062186. View

15.

Deb K, Beyer H . Self-adaptive genetic algorithms with simulated binary crossover. Evol Comput. 2001; 9(2):197-221. DOI: 10.1162/106365601750190406. View

16.

Southan C . Has the yo-yo stopped? An assessment of human protein-coding gene number. Proteomics. 2004; 4(6):1712-26. DOI: 10.1002/pmic.200300700. View

17.

Cully A, Mouret J . Evolving a Behavioral Repertoire for a Walking Robot. Evol Comput. 2015; 24(1):59-88. DOI: 10.1162/EVCO_a_00143. View

18.

Clune J, Mouret J, Lipson H . The evolutionary origins of modularity. Proc Biol Sci. 2013; 280(1755):20122863. PMC: 3574393. DOI: 10.1098/rspb.2012.2863. View

19.

Pigliucci M . Is evolvability evolvable?. Nat Rev Genet. 2007; 9(1):75-82. DOI: 10.1038/nrg2278. View

20.

Gaier A, Asteroth A, Mouret J . Data-Efficient Design Exploration through Surrogate-Assisted Illumination. Evol Comput. 2018; 26(3):381-410. DOI: 10.1162/evco_a_00231. View