DocumentCode :
3187230
Title :
Evaluation on the robustness of Genetic Network Programming with reinforcement learning
Author :
Mabu, Shingo ; Tjahjadi, Andre ; Sendari, Siti ; Hirasawa, Kotaro
Author_Institution :
Grad. Sch. of Inf., Production & Syst., Waseda Univ., Fukuoka, Japan
fYear :
2010
fDate :
10-13 Oct. 2010
Firstpage :
1659
Lastpage :
1664
Abstract :
Genetic Network Programming (GNP) has been proposed as one of the evolutionary algorithms and extended with reinforcement learning (GNP-RL). The combination of evolution and learning can efficiently evolve programs and the fitness improvement has been confirmed in the simulations of tileworld problems, elevator group supervisory control systems, stock trading models and wall following behavior of Khepera robot. However, its robustness in testing environments has not been analyzed in detail yet. In this paper, the learning mechanism in the testing environment is introduced and it is confirmed that GNP-RL can show the robustness using a robot simulator WEBOTS, especially when unexperienced sensor troubles suddenly occur. The simulation results show that GNP-RL works well in the testing even if wrong sensor information is given because GNP-RL has a function to change programs using alternative actions automatically. In addition, the analysis on the effects of the parameters of GNP-RL is carried out in both training and testing simulations.
Keywords :
genetic algorithms; learning (artificial intelligence); mobile robots; robust control; sensors; GNP-RL; Khepera robot; WEBOTS; elevator group supervisory control system; evolutionary algorithm; genetic network programming; reinforcement learning; robot simulator; sensor information; stock trading model; testing environment; tile world problem; unexperienced sensor; wall following behavior; Economic indicators; Variable speed drives; Wheels; Khepera robot; evolutionary computation; genetic network programming; reinforcement learning; robustness;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Systems Man and Cybernetics (SMC), 2010 IEEE International Conference on
Conference_Location :
Istanbul
ISSN :
1062-922X
Print_ISBN :
978-1-4244-6586-6
Type :
conf
DOI :
10.1109/ICSMC.2010.5642323
Filename :
5642323
Link To Document :
بازگشت