Exploring genetic programming systems with MAP-Elites

MAP-Elites is an evolutionary computation technique that has proven valuable for exploring and illuminating the genotype-phenotype space of a computational problem. In MAP-Elites, a population is structured based on phenotypic traits of prospective solutions; each cell represents a distinct combination of traits and maintains only the most fit organism found with those traits. The resulting map of trait combinations allows the user to develop a better understanding of how each trait relates to fitness and how traits interact. While MAP-Elites has not been demonstrated to be competitive for identifying the optimal Pareto front, the insights it provides do allow users to better understand the underlying problem. In particular, MAP-Elites has provided insight into the underlying structure of problem representations, such as the value of connection cost or modularity to evolving neural networks. Here, we extend the use of MAP-Elites to examine genetic programming representations, using aspects of program architecture as traits to explore. We demonstrate that MAP-Elites can generate programs with a much wider range of architectures than other evolutionary algorithms do (even those that are highly successful at maintaining diversity), which is not surprising as this is the purpose of MAP-Elites. Ultimately, we propose that MAP-Elites is a useful tool for understanding why genetic programming representations succeed or fail and we suggest that it should be used to choose selection techniques and tune parameters. Emily Dolson BEACON Center for the Study of Evolution in Action and Department of Computer Science and Ecology, Evolutionary Biology, and Behavior Program, Michigan State University, East Lansing, MI, USA e-mail: dolsonem@msu.edu Alexander Lalejini BEACON Center for the Study of Evolution in Action and Department of Computer Science and Ecology, Evolutionary Biology, and Behavior Program, Michigan State University, East Lansing, MI, USA e-mail: lalejini@msu.edu Charles Ofria BEACON Center for the Study of Evolution in Action and Department of Computer Science and Ecology, Evolutionary Biology, and Behavior Program, Michigan State University, East Lansing, MI, USA e-mail: ofria@msu.edu

[1]  Kenneth O. Stanley,et al.  Confronting the Challenge of Quality Diversity , 2015, GECCO.

[2]  C. Ofria,et al.  Sexual reproduction reshapes the genetic architecture of digital organisms , 2006, Proceedings of the Royal Society B: Biological Sciences.

[3]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[4]  Charles Ofria,et al.  Exploring Genetic Programming Systems with MAP-Elites , 2018, GPTP.

[5]  Lee Spector,et al.  Expressive genetic programming: concepts and applications , 2018, GECCO.

[6]  Lee Spector,et al.  Simultaneous evolution of programs and their control structures , 1996 .

[7]  Lee Spector,et al.  Autoconstructive Evolution: Push, PushGP, and Pushpop , 2001 .

[8]  J. Pollack,et al.  The Evolutionary Induction of Subroutines , 1997 .

[9]  Lee Spector,et al.  General Program Synthesis Benchmark Suite , 2015, GECCO.

[10]  W. Banzhaf,et al.  1 Linear Genetic Programming , 2007 .

[11]  John R. Koza,et al.  Genetic programming 2 - automatic discovery of reusable programs , 1994, Complex Adaptive Systems.

[12]  Cedric E. Ginestet.  ggplot2: Elegant Graphics for Data Analysis , 2011 .

[13]  Charles Ofria,et al.  What Else Is in an Evolved Name? Exploring Evolvable Specificity with SignalGP , 2018, GPTP.

[14]  John R. Koza,et al.  Evolving Modules in Genetic Programming by Subtree Encapsulation , 2001, EuroGP.

[15]  Leslie G. Valiant,et al.  Evolvability , 2009, JACM.

[16]  Antoine Cully,et al.  Robots that can adapt like animals , 2014, Nature.

[17]  Jean-Baptiste Mouret,et al.  Illuminating search spaces by mapping elites , 2015, ArXiv.

[18]  Kalyanmoy Deb,et al.  Approximating a multi-dimensional Pareto front for a land use management problem: A modified MOEA with an epigenetic silencing metaphor , 2012, 2012 IEEE Congress on Evolutionary Computation.

[19]  Lee Spector,et al.  Tag-based modules in genetic programming , 2011, GECCO '11.

[20]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[21]  Julian Francis Miller,et al.  The Automatic Acquisition, Evolution and Reuse of Modules in Cartesian Genetic Programming , 2008, IEEE Transactions on Evolutionary Computation.

[22]  Yiannis Demiris,et al.  Quality and Diversity Optimization: A Unifying Modular Framework , 2017, IEEE Transactions on Evolutionary Computation.

[23]  John W. Emerson,et al.  Nonparametric Goodness-of-Fit Tests for Discrete Null Distributions , 2011, R J..

[24]  Leonardo Vanneschi,et al.  Open issues in genetic programming , 2010, Genetic Programming and Evolvable Machines.

[25]  Lee Spector,et al.  Assessment of problem modality by differential performance of lexicase selection in genetic programming: a preliminary report , 2012, GECCO '12.