Many experiments have been performed that use evolutionary algorithms for learning the topology and connection weights of a neural network that controls a robot or virtual agent. These experiments are not only performed to better understand basic biological principles, but also with the hope that with further progress of the methods, they will become competitive for automatically creating robot behaviors of interest. However, current methods are limited with respect to the (Kolmogorov) complexity of evolved behavior. Using the evolution of robot trajectories as an example, we show that by adding four features, namely (1) freezing of previously evolved structure, (2) temporal scaffolding, (3) a homogeneous transfer function for output nodes, and (4) mutations that create new pathways to outputs, to standard methods for the evolution of neural networks, we can achieve an approximately linear growth of the complexity of behavior over thousands of generations. Overall, evolved complexity is up to two orders of magnitude over that achieved by standard methods in the experiments reported here, with the major limiting factor for further growth being the available run time. Thus, the set of methods proposed here promises to be a useful addition to various current neuroevolution methods.
翻译:许多实验都用进化算法来学习控制机器人或虚拟物剂的神经网络的地形和连接重量。这些实验不仅是为了更好地了解基本生物原理而进行的,而且希望随着方法的进一步发展,它们将成为自动创造引起兴趣的机器人行为的竞争者。然而,目前的方法在进化行为的复杂性(Kolmogorov)方面是有限的。以机器人轨迹的演进为例,我们通过增加四个特征,即:(1) 冻结先前形成的结构,(2) 时间搭建,(3) 输出节点的同质传输功能,(4) 创造产出新途径的突变功能,以及神经网络的演变标准方法。总体来说,演化的复杂程度比这里所报告的实验标准方法所达到的复杂程度高出了两级,而进一步增长的主要限制因素是现有的运行时间。因此,这里提出的一套方法有望对当前各种神经进化方法起到有益的补充作用。