Network Architecture for Optimizing Deep Deterministic Policy Gradient Algorithms

Author:

Zhang Haifei1ORCID,Xu Jian2,Zhang Jian3,Liu Quan3

Affiliation:

1. School of Computer and Information Engineering, Nantong Institute of Technology, Yongxing Road 211, Nantong 226002, China

2. School of Information Science and Technology, Nantong University, Seyuan Road 9, Nantong 226019, China

3. School of Computer Science and Technology, Soochow University, Shizi Street 1, Suzhou 215006, China

Abstract

The traditional Deep Deterministic Policy Gradient (DDPG) algorithm has been widely used in continuous action spaces, but it still suffers from the problems of easily falling into local optima and large error fluctuations. Aiming at these deficiencies, this paper proposes a dual-actor-dual-critic DDPG algorithm (DN-DDPG). First, on the basis of the original actor-critic network architecture of the algorithm, a critic network is added to assist the training, and the smallest Q value of the two critic networks is taken as the estimated value of the action in each update. Reduce the probability of local optimal phenomenon; then, introduce the idea of dual-actor network to alleviate the underestimation of value generated by dual-evaluator network, and select the action with the greatest value in the two-actor networks to update to stabilize the training of the algorithm process. Finally, the improved method is validated on four continuous action tasks provided by MuJoCo, and the results show that the improved method can reduce the fluctuation range of error and improve the cumulative return compared with the classical algorithm.

Funder

Training Project of Top Scientific Research Talents of Nantong Institute of Technology

Publisher

Hindawi Limited

Subject

General Mathematics,General Medicine,General Neuroscience,General Computer Science

Reference40 articles.

1. An information theoretic analysis of sequential decision-making;M. Dörpinghaus

2. A survey on deep reinforcement learning;Q. Liu;Chinese Journal of Computers,2018

3. Using continuous action spaces to solve discrete problems;H. V. Hasselt

4. A novel asynchronous deep reinforcement learning model with adaptive early forecasting method and reward incentive mechanism for short-term load forecasting

5. Multi‐robot path planning based on a deep reinforcement learning DQN algorithm

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3