Reusing learned functionality in XCS

Abstract

This paper expands on work previously conducted on the XCS system using code fragments, which are GP-like trees that encapsulate building blocks of knowledge. The usage of code fragments in the XCS system enabled the solution of previously intractable, complex, boolean problems, e.g. the 135 bit multiplexer domain. However, it was not previously possible to replace functionality at nodes with learned relationships, which restricted scaling to larger problems and related domains. The aim of this paper is to reuse learned rule sets as functions. The functions are to be stored along with the code fragments produced as a solution for a problem. The results show for the first time that these learned functions can be reused in the inner nodes of the code fragment trees. The results are encouraging as there was no statistically significant difference in terms of classification. For the simpler problems the new system XCSCF 2 , required much less instances than the XCSCFC to solve the problems. However, for the more complex problems, the XCSCF 2 required more instances than XCSCFC; but the additional time was not prohibitive for the continued development of this approach. The main contribution of this investigation is that functions can be learned and later reused in the inner nodes of a code fragment tree. This is anticipated to lead to a reduced search space and increased performance both in terms of instances needed to solve a problem and classification accuracy.

ConCS: A Continual Classifier System for Continual Learning of Multiple Boolean Problems

“…Such problems are difficult for machine learning algorithms as the search space consists of multiple interacting patterns that are often repeated, which obfuscates the decision boundaries. Based on XCSCFC, Alvarez et al [16] later introduced ruleset functions in CFs in XCSCF 2 to enable the reusability of CFs with learned ruleset functions for the function nodes. This system can solve hierarchical problems, such as 18-bit Hierarchical Mux problem, with transfer learning.…”

“…We do not divide the initial subproblems any further although it was demonstrated that CF-based XCSs could learn such functions from even smaller subproblems [16]. Future work with ConCS will explore the intellectually interesting question of "what are smallest axioms that can initialize learning?"…”

“…XCSCFC enabled feature reusability where relevant building blocks of knowledge was transferred in the form of CFs [9]. Alvarez et al showed that an LCS-produced ruleset could be treated as a function, 3 which is reusable in future tasks [16]. He then extended the reusability of ruleset functions to produce XCSCF* [17] with LL.…”