A Proposal of Weighted Q-Learning for Continuous State and Action Spaces
| Authors: | Cheng Yuhu, Institute of Automation, Chinese Academy of Sciences, China
Yi Jianqiang, Institute of Automation, Chinese Academy of Sciences, China
Zhao Dongbin, Institute of Automation, Chinese Academy of Sciences, China |
|---|
| Topic: | 1.2 Adaptive and Learning Systems |
|---|
| Session: | Learning and Intelligent Control |
|---|
| Keywords: | continuous state space, continuous action space, weighted Q-Learning, neural gas algorithm, RBF network, mountain car. |
|---|
Abstract
A kind of weighted Q-Learning algorithm suitable for control systems with continuous state and action spaces was proposed. The hidden layer of RBF network was designed dynamically by virtue of the proposed modified growing neural gas algorithm so as to realize the adaptive understanding of the continuous state space. Based on the standard Q-Learning implemented by RBF network, the weighted Q-Learning was used to solve the control problem with continuous action outputs. Simulation result of mountain car control verified the validity of the proposed weighted Q-Learning algorithm.
