Back to Search
Start Over
Kernel-Based Online NEAT for Keepaway Soccer.
- Source :
- Bio-Inspired Computational Intelligence & Applications; 2007, p100-107, 8p
- Publication Year :
- 2007
-
Abstract
- This paper presents a kernel-based online neuroevolutionary of augmenting topology (KO-NEAT) algorithm, which borrowing the selection mechanisms used in temporal difference (TD) algorithms and combining the kernel function approximator for individual fitness initiation. KO-NEAT can improve evolution's online performance of NEAT and learns more quickly. Empirical results in keepaway soccer problem demonstrate that KO-NEAT can substantially improve the original algorithm. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISBNs :
- 9783540747680
- Database :
- Complementary Index
- Journal :
- Bio-Inspired Computational Intelligence & Applications
- Publication Type :
- Book
- Accession number :
- 33107478
- Full Text :
- https://doi.org/10.1007/978-3-540-74769-7_12