Learning and Optimization in Hierarchical Adaptive Critic Design
Haibo He, Zhen Ni, Dongbin Zhao · 2012
This chapter introduces a novel hierarchical adaptive critic design to improve learning and optimization over time. It proposes to integrate a hierarchical goal generator network to provide the learning system a more informative and detailed goal representation to guide its decision making. First, instead of using a typical binary reinforcement signal to represent “success” or “failure” of the system, the chapter also proposes a more informative reinforcement signal representation for the intelligent system to make better choice of actions. Second, in order to mimic certain levels of brain-like intelligence, the chapter considers it is important to introduce a multilevel goal representation into the adaptive critic design to guide the system’s decision-making to accomplish the long-term goal over time. The chapter presents the detailed system architecture, learning, and adaptation procedure, and a case study of the ball-and-beam system to demonstrate the learning and control capability of this approach. Controlled Vocabulary Terms learning (artificial intelligence); optimisation