getALife - An Artificial Life Environment for the Evaluation of Agent-Based Systems and Evolutionary Algorithms for Reinforcement Learning

Daniel Machado, Miguel Rocha

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearch

Abstract

An Artificial Life environment - getALife - is proposed, whose major aim is to provide a framework to evaluate single and multi-agent systems and evolutionary approaches to the development of reinforcement learning algorithms. The environment is based on a predator-prey scenario, with multiple species and where individuals are mainly characterized by their decision modules and genetic information. The platform is quite powerful, flexible, modular, visually attractive, easy to program and to use, making an interesting tool both to research and teaching. Two applications based on getALife are provided: the evaluation of a Neural Network based decision module with evolutionary learning and the development of a children's game.
Original languageEnglish
Title of host publicationNew challenges in applied intelligence technologies
PublisherSpringer Publishing Company
Publication date2008
Pages35-44
ISBN (Print)978-3-540-79354-0
ISBN (Electronic)978-3-540-79355-7
DOIs
Publication statusPublished - 2008
Externally publishedYes
Event21st International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems - Wroclaw, Poland
Duration: 18 Jun 200820 Jun 2008
Conference number: 21

Conference

Conference21st International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems
Number21
CountryPoland
CityWroclaw
Period18/06/200820/06/2008
SeriesStudies in Computational Intelligence
Volume134
ISSN1860-949X

Fingerprint Dive into the research topics of 'getALife - An Artificial Life Environment for the Evaluation of Agent-Based Systems and Evolutionary Algorithms for Reinforcement Learning'. Together they form a unique fingerprint.

Cite this