Convolutional fitted Q iteration for vision-based control problems

doi:10.1109/IJCNN.2016.7727794

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 深度强化学习

	Convolutional fitted Q iteration for vision-based control problems
	Zhao Dongbin; Zhu Yuanheng; Lv Le; Chen Yaran; Zhang Qichao
	2016-11
会议名称	The 2016 International Joint Conference on Neural Networks
会议日期	24-29 July 2016
会议地点	Vancouver, BC, Canada
摘要	In this paper a deep reinforcement learning (DRL) method is proposed to solve the control problem which takes raw image pixels as input states. A convolutional neural network (CNN) is used to approximate Q functions, termed as Q-CNN. A pretrained network, which is the result of a classification challenge on a vast set of natural images, initializes the parameters of Q-CNN. Such initialization assigns Q-CNN with the features of image representation, so it is more concentrated on the control tasks. The weights are tuned under the scheme of fitted Q iteration (FQI), which is an offline reinforcement learning method with the stable convergence property. To demonstrate the performance, a modified Food-Poison problem is simulated. The agent determines its movements based on its forward view. In the end the algorithm successfully learns a satisfied policy which has better performance than the results of previous researches.
DOI	10.1109/IJCNN.2016.7727794
引用统计
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/14476
专题	多模态人工智能系统全国重点实验室_深度强化学习
作者单位	he State Key Laboratory of Management and Control for Complex Systems, In- stitution of Automation, Chinese Academy of Sciences, Beijing 100190, China.
推荐引用方式 GB/T 7714	Zhao Dongbin,Zhu Yuanheng,Lv Le,et al. Convolutional fitted Q iteration for vision-based control problems[C],2016.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
07727794.pdf（240KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载