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.
DOI10.1109/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
专题复杂系统管理与控制国家重点实验室_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
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zhao Dongbin]的文章
[Zhu Yuanheng]的文章
[Lv Le]的文章
百度学术
百度学术中相似的文章
[Zhao Dongbin]的文章
[Zhu Yuanheng]的文章
[Lv Le]的文章
必应学术
必应学术中相似的文章
[Zhao Dongbin]的文章
[Zhu Yuanheng]的文章
[Lv Le]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 07727794.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。