• Publications
  • Influence
XCS and the Monk's Problems
TLDR
This paper presents some first results in the application of Learning Classifier Systems to a particular Data Mining task. Expand
  • 68
  • 4
  • PDF
A formal framework and extensions for function approximation in learning classifier systems
TLDR
We formalize the function approximation part, by providing a clear problem definition, a formalization of the LCS function approximation architecture, and a definition of function approximation aim. Expand
  • 33
  • 2
  • PDF
Data Mining using Learning Classifier Systems
TLDR
Walsh and Ungson ([105]) identify that information within organizations can be considered in terms of “Organizational Memories” ...the scattered fragments of data, interpreted by individuals as information, that exists in many forms (written, social, roles, images, ...) throughout an organization. Expand
  • 26
  • 2
Limits in Long Path Learning with XCS
  • A. Barry
  • Mathematics, Computer Science
  • GECCO
  • 12 July 2003
TLDR
The development of the XCS Learning Classifier System [26] has produced a stable implementation, able to consistently identify the accurate and optimally general population of classifiers mapping a given reward landscape. Expand
  • 17
  • 1
  • PDF
Mixing independent classifiers
TLDR
We formalise the mixing problem, which concerns combining the prediction of independently trained local models to form a global prediction, and provide both analytical and heuristic approaches to solving it. Expand
  • 10
  • 1
  • PDF
A formal framework for reinforcement learning with function approximation in learning classifier systems
TLDR
A formal framework that captures all components of classifier systems, that is, function approximation, reinforcement learning, and classifier replacement, and permits the modelling of them separately and in their interaction. Expand
  • 7
  • 1
  • PDF
The stability of long action chains in XCS
  • A. Barry
  • Mathematics, Computer Science
  • Soft Comput.
  • 1 June 2002
TLDR
We investigate the limits of XCS learning within multiple-step environments with the introduction of the Triggered Chaining Operator. Expand
  • 21
XCS with eligibility traces
TLDR
The development of the XCS Learning Classifier System has produced a robust and stable implementation that performs competitively in direct-reward environments. Expand
  • 11
  • PDF
Aliasing in XCS and the Consecutive State Problem: 2 - Solutions
  • A. Barry
  • Mathematics, Computer Science
  • GECCO
  • 13 July 1999
TLDR
The 'Aliasing Problem' within XCS (Wilson, 1995, 1998), first identified by Lanzi (1997), does not only appear whenever the aliased states occur in separate environmental locations but also when they occur consecutively (Barry, 1999). Expand
  • 11
  • PDF
Aliasing in XCS and the Consecutive State Problem: 1 - Effects
  • A. Barry
  • Mathematics, Computer Science
  • GECCO
  • 13 July 1999
TLDR
This paper introduces a sub-class of the aliasing problem termed the 'Consecutive State Problem' and uses the subclass to identify the effects of consecutive state aliasing on the learning of the State × Action × Payoff mapping within XCS. Expand
  • 9
  • PDF
...
1
2
3
...