Next Article in Journal
Policy-Based Composition and Embedding of Extended Virtual Networks and SFCs for IIoT
Previous Article in Journal
Study on Multi-Objective Optimization-Based Climate Responsive Design of Residential Building
Open AccessArticle

Feasibility Analysis and Application of Reinforcement Learning Algorithm Based on Dynamic Parameter Adjustment

College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, China
*
Author to whom correspondence should be addressed.
Algorithms 2020, 13(9), 239; https://doi.org/10.3390/a13090239
Received: 22 August 2020 / Revised: 12 September 2020 / Accepted: 16 September 2020 / Published: 22 September 2020
Reinforcement learning, as a branch of machine learning, has been gradually applied in the control field. However, in the practical application of the algorithm, the hyperparametric approach to network settings for deep reinforcement learning still follows the empirical attempts of traditional machine learning (supervised learning and unsupervised learning). This method ignores part of the information generated by agents exploring the environment contained in the updating of the reinforcement learning value function, which will affect the performance of the convergence and cumulative return of reinforcement learning. The reinforcement learning algorithm based on dynamic parameter adjustment is a new method for setting learning rate parameters of deep reinforcement learning. Based on the traditional method of setting parameters for reinforcement learning, this method analyzes the advantages of different learning rates at different stages of reinforcement learning and dynamically adjusts the learning rates in combination with the temporal-difference (TD) error values to achieve the advantages of different learning rates in different stages to improve the rationality of the algorithm in practical application. At the same time, by combining the Robbins–Monro approximation algorithm and deep reinforcement learning algorithm, it is proved that the algorithm of dynamic regulation learning rate can theoretically meet the convergence requirements of the intelligent control algorithm. In the experiment, the effect of this method is analyzed through the continuous control scenario in the standard experimental environment of ”Car-on-The-Hill” of reinforcement learning, and it is verified that the new method can achieve better results than the traditional reinforcement learning in practical application. According to the model characteristics of the deep reinforcement learning, a more suitable setting method for the learning rate of the deep reinforcement learning network proposed. At the same time, the feasibility of the method has been proved both in theory and in the application. Therefore, the method of setting the learning rate parameter is worthy of further development and research. View Full-Text
Keywords: reinforcement learning; control system; parameter adjustment reinforcement learning; control system; parameter adjustment
Show Figures

Figure 1

MDPI and ACS Style

Li, M.; Gu, X.; Zeng, C.; Feng, Y. Feasibility Analysis and Application of Reinforcement Learning Algorithm Based on Dynamic Parameter Adjustment. Algorithms 2020, 13, 239.

AMA Style

Li M, Gu X, Zeng C, Feng Y. Feasibility Analysis and Application of Reinforcement Learning Algorithm Based on Dynamic Parameter Adjustment. Algorithms. 2020; 13(9):239.

Chicago/Turabian Style

Li, Menglin; Gu, Xueqiang; Zeng, Chengyi; Feng, Yuan. 2020. "Feasibility Analysis and Application of Reinforcement Learning Algorithm Based on Dynamic Parameter Adjustment" Algorithms 13, no. 9: 239.

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop