DMCA
Dynamics of co-evolutionary learning (1996)
| Venue: | In Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior |
| Citations: | 31 - 8 self |
BibTeX
@INPROCEEDINGS{Juille96dynamicsof,
author = {Hugues Juille and Jordan B. Pollack},
title = {Dynamics of co-evolutionary learning},
booktitle = {In Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior},
year = {1996},
pages = {526--534},
publisher = {MIT Press}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Co-evolutionary learning, which involves the embedding of adaptive learning agents in a t-ness environment which dynamically responds to their progress, is a potential solution for many technological chicken and egg problems, and is at the heart of several recent and surprising successes, such as Sim's arti cial robot and Tesauro's backgammon player. We recently solved the two spirals problem, a di cult neural network benchmark classi cation problem, using the genetic programming primitives set up by [Koza, 1992]. Instead of using absolute tness, we use a relative tness [Angeline & Pollack, 1993] based on a competition for coverage of the data set. As the population reproduces, the tness function driving the selection changes, and subproblem niches are opened, rather than crowded out. The solutions found by our method have a symbiotic structure which suggests that by holding niches open, crossover is better able to discover modular building blocks. 1
Keyphrases
co-evolutionary learning data set symbiotic structure spiral problem relative tness angeline pollack absolute tness t-ness environment tness function many technological chicken egg problem population reproduces backgammon player cial robot genetic programming primitive modular building block potential solution selection change subproblem niche surprising success
