Efficient Reinforcement Learning Through Evolving Neural Network Topologies
Efficient Reinforcement Learning Through Evolving Neural Network Topologies
复制标题
DOI：
--
复制
发表时间：
2002-07
期刊：
影响因子：
--
通讯作者：
Kenneth O. Stanley;R. Miikkulainen
中科院分区：
文献类型：
--
作者：
Kenneth O. Stanley;R. Miikkulainen
神经进化是目前在极点平衡基准强化学习任务上最强大的方法。虽然早期的研究表明，进化网络拓扑结构和连接权重具有优势，但领先的神经进化系统进化固定网络。进化的结构是否能提高绩效是一个悬而未决的问题。在这篇文章中，我们介绍了这样一个系统，神经进化的增强拓扑（NEAT）。我们表明，当结构进化时（1）采用有原则的交叉方法，（2）通过保护结构创新，以及（3）通过从最小结构的增量增长，学习比最好的固定拓扑方法显着更快、更强。NEAT还表明，有可能进化出越来越大的基因组群体，实现高度复杂的解决方案，否则很难优化。
Neuroevolution is currently the strongest method on the pole-balancing benchmark reinforcement learning tasks. Although earlier studies suggested that there was an advantage in evolving the network topology as well as connection weights, the leading neuroevolution systems evolve fixed networks. Whether evolving structure can improve performance is an open question. In this article, we introduce such a system, NeuroEvolution of Augmenting Topologies (NEAT). We show that when structure is evolved (1) with a principled method of crossover, (2) by protecting structural innovation, and (3) through incremental growth from minimal structure, learning is significantly faster and stronger than with the best fixed-topology methods. NEAT also shows that it is possible to evolve populations of increasingly large genomes, achieving highly complex solutions that would otherwise be difficult to optimize.