Affiliation:
1. Methodist University College Ghana, Ghana
Abstract
The objective of this chapter is the introduction of reinforcement learning in the context of graphs. In particular, a linkage between reinforcement learning theory and graph theory is established. Within the context of semi-supervised pattern recognition, reinforcement learning theory is introduced and discussed in basic steps. Motivation, leading to learning agent development with reinforcement capabilities for massive data pattern learning is also given. The main contribution of this book chapter is the provision of a basic introductory text authored in less mathematical rigor for the benefit of students, tutors, lecturers, researchers, and/or professionals who wish to delve into the foundation, representations, concepts, and theory of graph based semi-supervised intelligent systems.
Reference51 articles.
1. Purposive behavior acquisition for a real robot by vision-based reinforcement learning
2. Barto, A. G., & Mahadevan, S. (2003). Recent advances in hierarchical reinforcement learning. Journal of Discrete Event Dynamic Systems - Theory and Applications, 13(1-2), 41-77.
3. Prediction of splice sites with dependency graphs and their expanded bayesian networks
4. Damien, E., Marée, R., & Wehenkel, L. (2006). Reinforcement learning with raw image pixels as state input. In Proceedings of International Workshop on Intelligent Computing in Pattern Analysis/Synthesis (IWICPAS). Proceedings Series: Lecture Notes in Computer Science, Vol. 4153, Xi'an, China (pp. 446-454). Springer.
5. Computational learning techniques for intraday FX trading using popular technical indicators