1) the complete title of one (or more) paper(s) published in the open literature describing the work that the author claims describes a human-competitive result;

Medvet E., Bartoli A. (2018)
On the Automatic Design of a Representation for Grammar-Based Genetic Programming.
European Conference on Genetic Programming EuroGP 2018.
Lecture Notes in Computer Science, vol 10781. Springer
BEST PAPER AWARD


2) the name, complete physical mailing address, e-mail address, and phone number of EACH author of EACH paper(s);

Eric Medvet, emedvet@units.it, +393283314160
Alberto Bartoli, bartoli.alberto@units.it, +393291899955

The physical mailing address of each author is: "Dipartimento di Ingegneria e Architettura, Università di Trieste - Via Valerio 6/1 - 34125, Trieste - Italy"


3) the name of the corresponding author (i.e., the author to whom notices will be sent concerning the competition);

Eric Medvet


4) the abstract of the paper(s);

A long-standing problem in Evolutionary Computation consists in how to choose an appropriate representation for the solutions. In this work we investigate the feasibility of synthesizing a representation automatically, for the large class of problems whose solution spaces can be defined by a context-free grammar. We propose a framework based on a form of meta-evolution in which individuals are candidate representations expressed with an ad hoc language that we have developed to this purpose. Individuals compete and evolve according to an evolutionary search aimed at optimizing such representation properties as redundancy, locality, uniformity of redundancy.

We assessed experimentally three variants of our framework on established benchmark problems and compared the resulting representations to human-designed representations commonly used (e.g., classical Grammatical Evolution). The results are promising in the sense that the evolved representations indeed exhibit better properties than the human-designed ones. Furthermore, while those improved properties do not result in a systematic improvement of search effectiveness, some of the evolved representations do improve search effectiveness over the human-designed baseline.


5) a list containing one or more of the eight letters (A, B, C, D, E, F, G, or H) that correspond to the criteria (see above) that the author claims that the work satisfies;

G


6) a statement stating why the result satisfies the criteria that the contestant claims (see examples of statements of human-competitiveness as a guide to aid in constructing this part of the submission);

Our result consists of a method for synthesizing a representation of candidate solutions in Grammatical Evolution automatically. More in detail, the method addresses the large class of problems whose solution spaces can be defined by a context-free grammar.

(G) The result solves a problem of indisputable difficulty in its field.

A difficult and long-standing problem in Evolutionary Computation consists in how to choose an appropriate representation for the solutions.

This claim is strongly supported by the literature, e.g., “perhaps the most difficult and least understood area of EA design is that of adapting its internal representation” (from “Parameter Setting in EAs: a 30 Year Perspective”, Kenneth De Jong, Parameter Setting in Evolutionary Algorithms, 2007). And, “How should the representations that are used in evolutionary algorithms, on which variation and selection act, be chosen and justified?”, (from Lee Spector, Introduction to the peer commentary special section on “On the Mapping of Genotype to Phenotype in Evolutionary Algorithms, Genetic Programming and Evolvable Machines, 2017”).

We assessed our method on established benchmark problems, by comparing the automatically-constructed representations to human-designed representations used for Grammatical Evolution and published in the scientific literature. The automatically-constructed representations indeed exhibit better properties than the human-designed ones, in terms of redundancy (the tendency of mapping many genotypes on the same phenotype), locality (the tendency of mapping genotypic neighbors to phenotypic neighbors), uniformity of redundancy (the tendency of exhibiting similar degrees of redundancy across different regions of the search space). Furthermore, several evolved representations do improve search effectiveness over the human-designed ones.


7) a full citation of the paper (that is, author names; publication date; name of journal, conference, technical report, thesis, book, or book chapter; name of editors, if applicable, of the journal or edited book; publisher name; publisher city; page numbers, if applicable);

Medvet E., Bartoli A.
“On the Automatic Design of a Representation for Grammar-Based Genetic Programming” 21st European Conference on Genetic Programming (EuroGP), 2018,
Editors: Castelli M., Sekanina L., Zhang M., Cagnoni S., García-Sánchez P.
Lecture Notes in Computer Science, vol 10781. Springer, Cham
DOI 10.1007/978-3-319-77553-1_7


8) a statement either that "any prize money, if any, is to be divided equally among the co-authors" OR a specific percentage breakdown as to how the prize money, if any, is to be divided among the co-authors;
Any prize money, if any, is to be divided equally among the co-authors.


9) a statement stating why the judges should consider the entry as "best" in comparison to other entries that may also be "human-competitive;"
We have faced a fundamental problem (how to represent candidate solutions in grammatical evolution so as to ensure certain representation properties), rather than a specific application. As such, our contribution demonstrates that evolutionary techniques may be human-competitive not only for solving a specific problem but also for designing the overall solution framework, that is, for partially automating the modelling phase. Indeed, an implementation of our contribution is publicly available (https://github.com/ericmedvet/evolved-ge) and can be hence used for further research.

Capabilities of this kind are more and more relevant in several different frameworks, for example the so-called neuro-evolutionary techniques often succeed in synthesizing the architecture of a neural network that is competitive with a human-designed one automatically. Our contribution is a significant step in this direction for grammatical evolution, one of the most important frameworks for evolutionary computation.


10) An indication of the general type of genetic or evolutionary computation used, such as GA (genetic algorithms), GP (genetic programming), ES (evolution strategies), EP (evolutionary programming), LCS (learning classifier systems), GE (grammatical evolution), GEP (gene expression programming), DE (differential evolution), etc.

GP (context-free grammar genetic programming CFG-GP), GE (grammatical evolution)