,
Dynamics of Co-evolutionary Learning
Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior: From animals to animats 4, стр. 526--534. Cape Code, USA, MIT Press, (9-13 September 1996)
Аннотация
Co-evolutionary learning, which involves the embedding
of adaptive learning agents in a fitness 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 artificial robot
and Tesauro's backgammon player. We recently solved the
two spirals problem, a difficult neural network
benchmark classification problem, using the genetic
programming primitives set up by koza:book .
Instead of using absolute fitness, we use a relative
fitness icga93:angeline based on a
competition for coverage of the data set. As the
population reproduces, the fitness 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.
