Title :
Comparing PSO structures to learn the game of checkers from zero knowledge
Author :
Franken, Nelis ; Engelbrecht, Andries P.
Author_Institution :
Dept. of Comput. Sci., Pretoria Univ., South Africa
Abstract :
This paper investigates the effectiveness of various particle swarm optimiser structures to learn how to play the game of checkers. Co-evolutionary techniques are used to train the game playing agents. Performance is compared against a player making moves at random. Initial experimental results indicate definite advantages in using certain information sharing structures and swarm size configurations to successfully learn the game of checkers.
Keywords :
cooperative systems; evolutionary computation; games of skill; learning (artificial intelligence); optimisation; tree searching; PSO structures; checkers game; coevolutionary techniques; game playing agents; information sharing structures; particle swarm optimiser; random movement; swarm size configurations; zero knowledge; Africa; Computer science; Databases; Law; Legal factors; Machine learning; Minimax techniques; Neural networks; Particle swarm optimization; Spine;
Conference_Titel :
Evolutionary Computation, 2003. CEC '03. The 2003 Congress on
Print_ISBN :
0-7803-7804-0
DOI :
10.1109/CEC.2003.1299580
