Authors: Hengliang Tang; Anqi Wang; Xi Yang
Addresses: School of Information, Beijing Wuzi University, Beijing 101149, China ' School of Information, Beijing Wuzi University, Beijing 101149, China ' School of Information, Beijing Wuzi University, Beijing 101149, China
Abstract: A major obstacle to traditional reinforcement learning is that rewards need to be artificially set to have a strong subjectivity. The inverse reinforcement learning algorithm solves this problem. Traditional inverse reinforcement learning requires an optimised demonstration, which is often not met in reality. Therefore, an interactive learning method was proposed to enhance the learned reward function by combining the feedback with the demonstration and using the improved Bayesian rule iteration of the imagery to improve the Agent strategy. The proposed method was tested in experimental and simulation tasks. The results showed that the efficiency of the method was significantly improved under different degrees of non-optimal proof.
Keywords: inverse reinforcement learning; Bayesian rule; IRLDF algorithm; demonstration and feedback.
International Journal of Wireless and Mobile Computing, 2019 Vol.17 No.4, pp.361 - 366
Received: 02 May 2019
Accepted: 23 May 2019
Published online: 30 Sep 2019 *