Abstract | ||
---|---|---|
We present two architectures, each designed to search 2-Dimensional mazes in order to locate a goal position, both of which perform on-line learning as the search proceeds. The first architecture is a form of Adaptive Heuristic Critic which uses a Genetic Algorithm to determine the Action Policy and a Radial Basis Function Neural Network to store the acquired knowledge of the Critic. The second is a stimulus-response Classifier System (CS) which uses a Genetic Algorithm, applied Michigan style, for rule generation and the Bucket Brigade algorithm for rule reinforcement. Experiments conducted using agents based upon each architectural model lead us to a comparison of performance, and some observations on the nature and relative levels of abstraction in the acquired knowledge. |
Year | DOI | Venue |
---|---|---|
1994 | 10.1007/3-540-58483-8_18 | Evolutionary Computing, AISB Workshop |
Keywords | Field | DocType |
maze problems,genetic algorithm,2 dimensional | Heuristic,Architecture,Radial basis function,Abstraction,Computer science,Artificial intelligence,Classifier (linguistics),Architectural model,Machine learning,Genetic algorithm,Learning classifier system | Conference |
ISBN | Citations | PageRank |
3-540-58483-8 | 2 | 0.34 |
References | Authors | |
7 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Anthony G. Pipe | 1 | 255 | 39.08 |
Brian Carse | 2 | 259 | 26.31 |