Title :
Genetic TD(λ) learning algorithm for policy evaluation problems
Author :
Xin, Xu ; Han-gen, He
Author_Institution :
Dept. of Autom. Control, Nat. Univ. of Defense Technol., Changsha, China
Abstract :
In this paper, tabular TD(λ) learning algorithm is combined with genetic algorithm (GA) to solve stochastic policy evaluation problems. Unlike conventional TD(λ) algorithm which has fixed control parameters, the proposed genetic TD(λ) algorithm makes use of GA to optimize the control parameters while evaluating stochastic policies. Simulated experiments on stochastic policy evaluation problems show that genetic TD(λ) algorithms not only realize the auto-tuning of control parameters but also have improved performance
Keywords :
genetic algorithms; learning (artificial intelligence); learning systems; auto-tuning; genetic algorithm; optimisation; reinforcement learning; stochastic policy evaluation; Algorithm design and analysis; Automatic control; Computer science; Convergence; Electronic mail; Genetic algorithms; Helium; Machine learning; Machine learning algorithms; Stochastic processes;
Conference_Titel :
Intelligent Control and Automation, 2000. Proceedings of the 3rd World Congress on
Conference_Location :
Hefei
Print_ISBN :
0-7803-5995-X
DOI :
10.1109/WCICA.2000.860017
