Hierarchical Relative Entropy Policy Search: An Information Theoretic Learning Algorithm in Multimodal Solution Spaces for Real Robots
by Gerhard Neumann, Christian Daniel
An information-theoretic policy search algorithm for optimizing robotic control in complex, multimodal environments using hierarchical relative entropy methods.
About This Book
This work introduces Hierarchical Relative Entropy Policy Search, an algorithm designed to optimize policies for robotic systems.
The approach leverages information theory to manage complex, multimodal solution spaces encountered in real-world robotics.
Emphasis is placed on practical applicability, enabling learning algorithms to function effectively on physical robots.
The research addresses challenges in exploration and optimization within high-dimensional control problems.
Reviews
No reviews yet. Be the first to review this book!