Cognitive learning with automatic goal acquisition

Authors:
Josef Kittler;Mikhail Shevchenko;David Windridge
Affiliations:
Center for Vision, Speech and Signal Processing, University of Surrey, Guildford, GU2 7XH, United Kingdom, {j.kittler,m.shevchenko,d.windridge}@surrey.ac.uk;Center for Vision, Speech and Signal Processing, University of Surrey, Guildford, GU2 7XH, United Kingdom, {j.kittler,m.shevchenko,d.windridge}@surrey.ac.uk;Center for Vision, Speech and Signal Processing, University of Surrey, Guildford, GU2 7XH, United Kingdom, {j.kittler,m.shevchenko,d.windridge}@surrey.ac.uk
Venue:
Proceedings of the 2006 conference on STAIRS 2006: Proceedings of the Third Starting AI Researchers' Symposium
Year:
2006

Citing 4
Cited 0

Reinforcement learning and its application to control

Reinforcement learning and its application to control
The spatial semantic hierarchy

Artificial Intelligence
The St. Thomas common sense symposium: designing architectures for human-level intelligence

AI Magazine
Reinforcement learning: a survey

Journal of Artificial Intelligence Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

Traditional algorithms of machine learning implemented in cognitive architectures demonstrate lack of autonomous exploration in an unknown environment. However, the latter is one of the most distinctive attributes of cognitive behaviour. The paper proposes an approach of self-reinforcement cognitive learning combining unsupervised goal acquisition, active Markov-based goal attaining and spatial-semantic hierarchical representation within an open-ended system architecture. The novelty of the method consists in division of goals into the classes of parameter goal, invariant goal and context goal. The system exhibits incremental learning in such a manner as to allow effective transferable representation of high-level concepts.