|
| << previous |
Journal description
All volumes of the corresponding journal
All issues of the corresponding volume
All articles of the corresponding issues
Details for article 6 of 6 found articles
| Title: |
The metacognitive loop I: Enhancing reinforcement learning with metacognitive monitoring and control for improved perturbation tolerance |
| Author: |
Anderson, Michael L. Oates, Tim Chong, Waiyian Perlis, Don |
| Appeared in: |
Journal of experimental & theoretical artificial intelligence |
| Paging: | Volume 18 (2006) nr. 3 pages 387-411 |
| Year: |
2006-09-01 |
| Contents: |
Maintaining adequate performance in dynamic and uncertain settings has been a perennial stumbling block for intelligent systems. Nevertheless, any system intended for real-world deployment must be able to accommodate unexpected change—that is, it must be perturbation tolerant. We have found that metacognitive monitoring and control—the ability of a system to self-monitor its own decision-making processes and ongoing performance, and to make targeted changes to its beliefs and action-determining components—can play an important role in helping intelligent systems cope with the perturbations that are the inevitable result of real-world deployment. In this article we present the results of several experiments demonstrating the efficacy of metacognition in improving the perturbation tolerance of reinforcement learners, and discuss a general theory of metacognitive monitoring and control, in a form we call the metacognitive loop. |
| Publisher: |
Taylor & Francis |
| Source file: |
Elektronische Wetenschappelijke Tijdschriften |
Details for article 6 of 6 found articles
| << previous |