DocumentCode
2781178
Title
Symbiosis: Using Predator-Prey Games as a Test Bed for Studying Competitive Co-evolution
Author
Tzima, Fani A. ; Symeonidis, Andreas L. ; Mitkas, Pericles A.
Author_Institution
Dept. of Electr. & Comput. Eng., Aristotle Univ. of Thessaloniki
fYear
2007
fDate
April 30 2007-May 3 2007
Firstpage
115
Lastpage
120
Abstract
The animal approach constitutes an intriguing attempt to study and comprehend the behavior of adaptive, learning entities in complex environments. Further inspired by the notions of co-evolution and evolutionary \´\´arms races", we have developed Symbiosis, a virtual ecosystem that hosts two self-organizing, combating species - preys and predators. All animats live and evolve in this shared environment, they are self-maintaining and engage in a series of vital activities - nutrition, growth, communication - with the ultimate goals of survival and reproduction. The main objective of Symbiosis is to study the behavior of ecosystem members, especially in terms of the emergent learning mechanisms and the effect of co-evolution on the evolved behavioral strategies. In this direction, several indicators are used to assess individual behavior, with the overall effectiveness metric depending strongly on the animats net energy gain and reproduction rate. Several experiments have been conducted with the developed simulator under various environmental conditions. Overall experimental results support our original hypothesis that co-evolution is a driving factor in the animat learning procedure
Keywords
artificial life; game theory; learning (artificial intelligence); predator-prey systems; Symbiosis virtual ecosystem; adaptive entities; animats; combating species; competitive co-evolution; emergent learning; evolutionary arms races; learning entities; predator-prey games; self-organizing; Animals; Animation; Arm; Biological system modeling; Ecosystems; Evolution (biology); Learning systems; Multiagent systems; Symbiosis; Testing;
fLanguage
English
Publisher
ieee
Conference_Titel
Integration of Knowledge Intensive Multi-Agent Systems, 2007. KIMAS 2007. International Conference on
Conference_Location
Waltham, MA
Print_ISBN
1-4244-0944-6
Electronic_ISBN
1-4244-0945-4
Type
conf
DOI
10.1109/KIMAS.2007.369795
Filename
4227534
Link To Document