A Model-Based Exploration Policy in Deep Q-Network

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 空间自动化技术研究室

	A Model-Based Exploration Policy in Deep Q-Network
	Li SL(李帅龙)2,3,4; Zhang W(张伟)2,4; Leng YQ(冷雨泉)1; Zhang X(张鑫)2,4
	2021
会议日期	December 3-4, 2021
会议地点	Virtual, Chengdu, China
关键词	reinforcement learning exploration and exploitation dilemma model-based exploration method
页码	336-343
英文摘要	Reinforcement learning has successfully been used in many applications and achieved prodigious performance (such as video games), and DQN is a well-known algorithm in RL. However, there are some disadvantages in practical applications, and the exploration and exploitation dilemma is one of them. To solve this problem, common strategies about exploration like -greedy have risen. Unfortunately, there are sample inefficient and ineffective because of the uncertainty of later exploration. In this paper, we propose a model-based exploration method that learns the state transition model to explore. Using the training rules of machine learning, we can train the state transition model networks to improve exploration efficiency and sample efficiency. We compare our algorithm with -greedy on the Deep Q-Networks (DQN) algorithm and apply it to the Atari 2600 games. Our algorithm outperforms the decaying -greedy strategy when we evaluate our algorithm across 14 Atari games in the Arcade Learning Environment (ALE).
产权排序	1
会议录	2021 International Conference on Digital Society and Intelligent Systems, DSInS 2021
会议录出版者	IEEE
会议录出版地	New York
语种	英语
ISBN号	978-1-6654-0630-7
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/30505]
专题	沈阳自动化研究所_空间自动化技术研究室
通讯作者	Zhang W(张伟); Leng YQ(冷雨泉)
作者单位	1.Department of Mechanical and Energy Engineering, Southern University of Science and Technology, Shenzhen, China 2.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China 3.University of Chinese Academy of Sciences, Shenyang, China 4.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China
推荐引用方式 GB/T 7714	Li SL,Zhang W,Leng YQ,et al. A Model-Based Exploration Policy in Deep Q-Network[C]. 见:. Virtual, Chengdu, China. December 3-4, 2021.