Generalization of Reinforcement Learning with CMAC
| Authors: | Kwon Sunggyu, Keimyung University, Korea, Republic of
Lee Kwang Y, The Pennsylvania State University, United States |
|---|
| Topic: | 3.2 Cognition and Control ( AI, Fuzzy, Neuro, Evolut.Comp.) |
|---|
| Session: | Neural Networks in Modelling and Control |
|---|
| Keywords: | CMAC, learning system, reinforcement learning, quantized states, neural networks |
|---|
Abstract
To implement a generalization of value functions in Adaptive Search Element (ASE)-reinforcement learning, CMAC is integrated into ASE controller. ASE-reinforcement learning scheme is briefly studied to discuss how CMAC is integrated into ASE controller. Neighbourhood Sequential Training concept is utilized to establish the look-up table of CMAC and to produce discrete control outputs. In computer simulation, an ASE controller and a couple of ASE-CMAC neural network are trained to balance the inverted pendulum on a cart. The number of trials until the controllers are established and the learning performance of the controllers are evaluated to find that generalization ability of the CMAC improves the speed of the ASE-reinforcement learning enough to realize the cartpole control system.
