Compound Asynchronous Exploration and Exploitation

摘要：

　　Data efficiency has always been a significant key topic for deep reinforcement learning.The main progress has been on sufficient exploration and effective exploitation.However,the two are often discussed separately.Profit from distributed systems,we propose an asynchronous approach to deep reinforcement learning by combining exploration and exploitation.We apply our framework to off-the-shelf deep reinforcement learning algorithms,and experimental results show that our algorithm is superior in final performance and efficiency.

关键词： Deep Reinforcement Learning Exploration and Exploitation Asynchronous Methods

作者: Jie Bai Li Liu Yaobing Wang Haoyu Zhang Jianfei Li

作者单位: Beijing Key Laboratory of Intelligent Space Robotic Systems Technology and Applications,Beijing Inst College of Engineering,Peking University,Beijing,China Science and Technology on Space Intelligent Control Laboratory,Beijing Institute of Control Engineer

会议类型: 国际会议

会议名称: 2019 2nd International Conference on Mechanical, Electronic and Engineering Technology (MEET 2019) 2019年第二届机电与工程技术国际会议

会议地点: 西安

会议语种:英文

页码: 371-379

在线出版日期: 2019-01-19（万方平台首次上网日期，不代表论文的发表时间）