A neural learning classifier system with self-adaptive constructivism for mobile robot control

Hurst, Jacob; Bull, Larry

Abstract

For artificial entities to achieve true autonomy and display complex lifelike behavior, they will need to exploit appropriate adaptable learning algorithms. In this context adaptability implies flexibility guided by the environment at any given time and an open-ended ability to learn appropriate behaviors. This article examines the use of constructivism-inspired mechanisms within a neural learning classifier system architecture that exploits parameter self-adaptation as an approach to realize such behavior. The system uses a rule structure in which each rule is represented by an artificial neural network. It is shown that appropriate internal rule complexity emerges during learning at a rate controlled by the learner and that the structure indicates underlying features of the task. Results are presented in simulated mazes before moving to a mobile robot platform. ©2006 Jacob Hurst and Larry Bull.

• Journal Article Type: Article
• Publication Date: Jun 1, 2006
• Journal: Artificial Life
• Print ISSN: 1064-5462
• Electronic ISSN: 1530-9185
• Publisher: Massachusetts Institute of Technology Press (MIT Press)
• Peer Reviewed: Not Peer Reviewed
• Volume: 12
• Issue: 3
• Pages: 353-380
• DOI: https://doi.org/10.1162/artl.2006.12.3.353
• Keywords: adaptation, genetic algorithm, neural network, reinforcement learning, robotics
• Public URL: https://uwe-repository.worktribe.com/output/1044236
• Publisher URL: http://dx.doi.org/10.1162/artl.2006.12.3.353