This paper introduces the concept of Hierarchical Neural Networks as a viable strategy for behavior-based decision making in certain contexts. Hierarchical Neural Networks, or HNNs, refers in this case to a system in which multiple neural networks are connected in a manner similar to an acyclic graph. In this way, responsibility can be divided between each neural network in every layer simplifying the vector of inputs, of outputs, and the overall complexity of each network resulting in improved performance. This approach is shown to outperform a single neural network when both systems are tasked to learn to a survival strategy incorporating several behaviors in a real-time environment.

PDF

Technical Report HR-10-02, Department of Computer Science, The University of Texas at Austin.

@techreport{robson:ugthesis10, title={Hierarchical Neural Networks for Behavior-Based Decision Making}, author={David Robson}, number={HR-10-02}, institution={Department of Computer Science, The University of Texas at Austin}, type={Undergraduate Honors Thesis}, url="http://www.cs.utexas.edu/users/ai-lab?robson:ugthesis10", year={2010} }