Your browser doesn't support javascript.
loading
A Layered Learning Approach to Scaling in Learning Classifier Systems for Boolean Problems.
Alvarez, Isidro M; Nguyen, Trung B; Browne, Will N; Zhang, Mengjie.
Afiliação
  • Alvarez IM; School of Engineering and Computer Science, Victoria University of Wellington, Kelburn,Wellington 6140, New Zealand yummyhumans@gmail.com.
  • Nguyen TB; School of Engineering and Computer Science, Victoria University of Wellington, Kelburn,Wellington 6140, New Zealand trung.nguyen@auckland.ac.nz.
  • Browne WN; School of Electrical Engineering and Robotics, Queensland University of Technology, Brisbane 4001, Australia will.browne@qut.edu.au.
  • Zhang M; School of Engineering and Computer Science, Victoria University of Wellington, Kelburn,Wellington 6140, New Zealand mengjie.zhang@ecs.vuw.ac.nz.
Evol Comput ; : 1-25, 2024 May 06.
Article em En | MEDLINE | ID: mdl-38713737
ABSTRACT
Evolutionary Computation (EC) often throws away learned knowledge as it is reset for each new problem addressed. Conversely, humans can learn from small-scale problems, retain this knowledge (plus functionality) and then successfully reuse them in larger-scale and/or related problems. Linking solutions to problems together has been achieved through layered learning, where an experimenter sets a series of simpler related problems to solve a more complex task. Recent works on Learning Classifier Systems (LCSs) has shown that knowledge reuse through the adoption of Code Fragments, GP-like tree-based programs, is plausible. However, random reuse is inefficient. Thus, the research question is how LCS can adopt a layered-learning framework, such that increasingly complex problems can be solved efficiently? An LCS (named XCSCF*) has been developed to include the required base axioms necessary for learning, refined methods for transfer learning and learning recast as a decomposition into a series of subordinate problems. These subordinate problems can be set as a curriculum by a teacher, but this does not mean that an agent can learn from it. Especially if it only extracts over-fitted knowledge of each problem rather than the underlying scalable patterns and functions. Results show that from a conventional tabula rasa, with only a vague notion of what subordinate problems might be relevant, XCSCF* captures the general logic behind the tested domains and therefore can solve any n-bit Multiplexer, n-bit Carry-one, n-bit Majority-on, and n-bit Even-parity problems. This work demonstrates a step towards continual learning as learned knowledge is effectively reused in subsequent problems.
Palavras-chave

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Idioma: En Ano de publicação: 2024 Tipo de documento: Article

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Idioma: En Ano de publicação: 2024 Tipo de documento: Article