Self-adaptation of learning rate in XCS working in noisy and dynamic environments

An extended classifier system (XCS) is an adaptive rule-based technique that uses evolutionary search and reinforcement learning to evolve complete, accurate, and maximally general payoff map of an environment. The payoff map is represented by a set of condition-action rules called classifiers. Despite this insight, till now parameter-setting problem associated with LCS/XCS has important drawbacks. Moreover, the optimal values of some parameters are strongly influenced by properties of the environment like its complexity, changeability, and the level of noise. The aim of this paper is to overcome some of these difficulties by a self-adaptation of a learning rate parameter, which plays a key role in reinforcement learning, since it is used for updates of classifier parameters: prediction, prediction error, fitness, and action set estimation. Self-adaptive control of prediction learning rate is investigated in the XCS, whereas the fitness and error learning rates remain fixed. Simultaneous self-adaptation of prediction learning rate and mutation rate also undergo experiments. Self-adaptive XCS solves one-step problems in noisy and dynamic environments.     

Imitation guided learning in learning classifier systems

In this paper, we study the means of developing an imitation process allowing to improve learning in the framework of learning classifier systems. We present three different approaches in the way a behavior observed may be taken into account through a guidance interaction: two approaches using a model of this behavior, and one without modelling. Those approaches are evaluated and compared in different environments when they are applied to three major classifier systems: ZCS, XCS and ACS. Results are analyzed and discussed. They highlight the importance of using a model of the observed behavior to enable an efficient imitation. Moreover, they show the advantages of taking this model into account by a specialized internal action. Finally, they bring new results of comparison between ZCS, XCS and ACS.

Problem solution sustenance in XCS: Markov chain analysis of niche support distributions and the impact on computational complexity

Michigan-style learning classifier systems iteratively evolve a distributed solution to a problem in the form of potentially overlapping subsolutions. Each problem niche is covered by subsolutions that are represented by a set of predictive rules, termed classifiers. The genetic algorithm is designed to evolve classifier structures that together cover the whole problem space and represent a complete problem solution. An obvious challenge for such an online evolving, distributed knowledge representation is to continuously sustain all problem subsolutions covering all problem niches, that is, to ensure niche support. Effective niche support depends both on the probability of reproduction and on the probability of deletion of classifiers in a niche. In XCS, reproduction is occurrence-based whereas deletion is support-based. In combination, niche support is assured effectively. In this paper we present a Markov chain analysis of the niche support in XCS, which we validate experimentally. Evaluations in diverse Boolean function settings, which require non-overlapping and overlapping solution structures, support the theoretical derivations. We also consider the effects of mutation and crossover on niche support. With respect to computational complexity, the paper shows that XCS is able to maintain (partially overlapping) niches with a computational effort that is linear in the inverse of the niche occurrence frequency.

基于XCS10的高精度多功能时间校验仪系统

以W78E58和XCS10为核心,以高精度石英晶体为频率标准,以GPS所提供的日期、时间为时间标准,并配以TMP82C79按键模块和LG12864液晶显示模块,设计和实现了高精度多功能时间校验仪系统.该系统可以测试复费率和多功能电能表的计时基准频率和时段投切误差,并给被校表授时.     

HXCS and its application to financial time series forecasting

Many techniques have been used to predict financial time series data in order to make profitable transaction decisions. Conventional time series are usually identified as a global model. However, in the financial world, time series fluctuates rapidly in time, and so are difficult to be recognized by a single model. Therefore here, we propose a Hierarchical eXtended Classifier System (XCS) model, which is composed of multiple local models. Each local model represents an individual agent. In the lower levels of the hierarchy, agents are trained by the XCS method to learn and forecast. These agents are only appropriate for some of the changing patterns in the time series data, and they fail to describe other changing patterns. For the upper levels of the hierarchy, Reinforcement Learning (RL) is used to determine how to shift among those local models for a changing trend. With the hierarchical learning structure, multiple agents work alternatively and the limitation of a single agent can be overcome. To evaluate the prediction performance, we mainly adopt the prediction accuracy of changing tendency of the next time (up or down), which is measured by the changing direction hit‐rate. Experiments have been performed on several well‐known stock indexes and stock markets. The results show that the proposed method achieves good performance. © 2006 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.