ABSTRACT
In this work, we analyse the performance of Novelty Search (NS) in a set of generalization experiments in a navigation task with Grammatical Evolution. Agents are trained on a single, simple environment, and tested on a selection of related, increasingly more difficult environments. We show that agents discovered with NS, although using a tiny number (six) of training samples, successfully generalise to these more difficult environments.
- Loukas Georgiou. [n.d.]. jGE NetLogo v2.0. https://web.archive.org/web/20101129085227/http://www.bangor.ac.uk/~eep201/jge/ Last Modified: 22 May 2010.Google Scholar
- Loukas Georgiou and William J. Teahan. 2006. jGE - A Java implementation of Grammatical Evolution. In 10th WSEAS International Conference on Systems. Athens, Greece, 534--869.Google Scholar
- Loukas Georgiou and William J. Teahan. 2010. Grammatical Evolution and the Santa Fe Trail Problem. In International Conference on Evolutionary Computation (ICEC). SciTePress, Valencia, Spain, 10--19.Google Scholar
- Joel Lehman and Kenneth O. Stanley. 2010. Efficiently evolving programs through the search for novelty.. In GECCO, Martin Pelikan and Jürgen Branke (Eds.). ACM, 837--844.Google Scholar
- E. Naredo, P. Urbano, and L. Trujillo. 2017. The training set and generalization in grammatical evolution for autonomous agent navigation. Soft Comput 21, 15 (2017), 4399--4416.Google ScholarCross Ref
- Conor Ryan, J. J. Collins, and Michael O'Neill. 1998. Grammatical Evolution: Evolving Programs for an Arbitrary Language.. In EuroGP (Lecture Notes in Computer Science), Wolfgang Banzhaf, Riccardo Poli, Marc Schoenauer, and Terence C. Fogarty (Eds.), Vol. 1391. Springer, 83--96.Google Scholar
- U. Wilensky. 1999. NetLogo 4.1. https://ccl.northwestern.edu/netlogo/references.shtml/ Accessed: Jan 01, 2019.Google Scholar
Index Terms
- General controllers evolved through grammatical evolution with a divergent search
Recommendations
The training set and generalization in grammatical evolution for autonomous agent navigation
Over recent years, evolutionary computation research has begun to emphasize the issue of generalization. Instead of evolving solutions that are optimized for a particular problem instance, the goal is to evolve solutions that can generalize to various ...
An exploration of learning and grammars in grammatical evolution
GECCO '09: Proceedings of the 11th Annual Conference Companion on Genetic and Evolutionary Computation Conference: Late Breaking PapersThis paper is concerned with the challenge of learning solutions to problems. The method employed here is a grammar based heuristic, where domain knowledge is encoded in a generative grammar, while evolution drives the update of the population of ...
Evolution of shared grammars for describing simulated spatial scenes with grammatical evolution
We propose a model based on an evolutionary process combined with an adapted planning process to develop a limited spatial language with a syntactical structure in a team of artificial agents. Syntax is induced by means of a grammar and the grammar ...
Comments