期刊
EVOLUTIONARY COMPUTATION
卷 10, 期 2, 页码 99-127出版社
MIT PRESS
DOI: 10.1162/106365602320169811
关键词
genetic algorithms; neural networks; neuroevolution; network topologies; speciation; competing conventions
An important question in neuroevolution is how to gain an advantage from evolving neural network topologies along with weights. We present a method, NeuroEvolution of Augmenting Topologies (NEAT), which outperforms the best fixed-topology method on a challenging benchmark reinforcement learning, task. We claim that the increased efficiency is due to (1) employing a principled method of crossover of different topologies, (2) protecting structural innovation using speciation, and (3) incrementally growing from minimal structure. We test this claim through a series of ablation studies that demonstrate that each component is necessary to the system as a whole and to each other. What results is significantly faster learning. NEAT is also an important contribution to GAs because it shows how it is possible for evolution to both optimize mid complexify solutions simultaneously, offering the possibility of evolving increasingly complex solutions over generations, and strengthening, the analogy with biological evolution.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据