DocumentCode :
2324618
Title :
Neuro-evolution versus Particle Swarm Optimization for competitive co-evolution of pursuit-evasion behaviors
Author :
Langenhoven, Leo H. ; Nitschke, Geoff S.
Author_Institution :
Dept. of Comput. Sci., Univ. of Pretoria, Pretoria, South Africa
fYear :
2010
fDate :
18-23 July 2010
Firstpage :
1
Lastpage :
8
Abstract :
This paper presents a study that compares the efficacy of Neuro-Evolution (NE) versus Particle Swarm Optimization (PSO) for evolving Artificial Neural Network (ANN) controllers in an unsupervised adaptation process. The research objective is to ascertain which adaptive method is most appropriate for deriving agent behaviors in a competitive co-evolution pursuit-evasion task. This task requires one predator agent to capture one prey agent in a simulation where behavior adaptation is guided by an arms race of competitive co-evolution. Results indicate that NE was overall more effective at deriving pursuit and evasion behaviors according to the task performance measures defined for this study.
Keywords :
artificial intelligence; evolutionary computation; neural nets; neurocontrollers; particle swarm optimisation; predator-prey systems; unsupervised learning; agent behavior; artificial neural network; competitive coevolution; neuroevolution; particle swarm optimization; pursuit evasion behavior; unsupervised adaptation process; Adaptation model; Artificial neural networks; Computational modeling; Games; Neurons; Robots; Sensors;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Evolutionary Computation (CEC), 2010 IEEE Congress on
Conference_Location :
Barcelona
Print_ISBN :
978-1-4244-6909-3
Type :
conf
DOI :
10.1109/CEC.2010.5585971
Filename :
5585971
Link To Document :
بازگشت