Department of Computer Science and Creative Technologies, University of the West of England, Bristol, BS16 1QY, United Kingdom
Evol Comput. 2013 Fall;21(3):361-87. doi: 10.1162/EVCO_a_00080. Epub 2012 Jun 25.
A number of representation schemes have been presented for use within learning classifier systems, ranging from binary encodings to artificial neural networks. This paper presents results from an investigation into using a temporally dynamic symbolic representation within the XCSF learning classifier system. In particular, dynamical arithmetic networks are used to represent the traditional condition-action production system rules to solve continuous-valued reinforcement learning problems and to perform symbolic regression, finding competitive performance with traditional genetic programming on a number of composite polynomial tasks. In addition, the network outputs are later repeatedly sampled at varying temporal intervals to perform multistep-ahead predictions of a financial time series.
已经提出了许多表示方案用于学习分类器系统中，从二进制编码到人工神经网络。本文介绍了在 XCSF 学习分类器系统中使用时变符号表示的研究结果。特别是，动态算术网络用于表示传统的条件-动作产生系统规则，以解决连续值强化学习问题并执行符号回归，在多个复合多项式任务上与传统遗传编程具有竞争性能。此外，网络输出稍后在不同的时间间隔重复采样，以对金融时间序列进行多步预测。
