Vision-based control in the open racing car simulator with deep and reinforcement learning

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

	Vision-based control in the open racing car simulator with deep and reinforcement learning
	Yuanheng Zhu; Dongbin Zhao
发表期刊	Journal of Ambient Intelligence and Humanized Computing
	2019
页码	doi={10.1007/s12652-019-01503-y}
摘要	With decades of development, computer intelligence has now reached a really high level. Especially deep learning (DL) and reinforcement learning (RL) endow computers the perception and decision abilities. This paper aims to design a vision-based system that is able to play The Open Racing Car Simulator (TORCS) like a human player that uses images. With the DLtrained perception module, useful and low-dimensional information is extracted from frst-person images. Based on that, the RL-trained module further manipulates the simulated car in the middle of the lane. The two modules are separately trained, and both DL and RL advantages are maximally utilized. Experiments on diferent tracks show the promising performance of the method.
七大方向——子方向分类	人工智能基础理论
国重实验室规划方向分类	智能计算与学习
是否有论文关联数据集需要存交	否
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/51533
专题	多模态人工智能系统全国重点实验室_深度强化学习
推荐引用方式 GB/T 7714	Yuanheng Zhu,Dongbin Zhao. Vision-based control in the open racing car simulator with deep and reinforcement learning[J]. Journal of Ambient Intelligence and Humanized Computing,2019:doi={10.1007/s12652-019-01503-y}.
APA	Yuanheng Zhu,&Dongbin Zhao.(2019).Vision-based control in the open racing car simulator with deep and reinforcement learning.Journal of Ambient Intelligence and Humanized Computing,doi={10.1007/s12652-019-01503-y}.
MLA	Yuanheng Zhu,et al."Vision-based control in the open racing car simulator with deep and reinforcement learning".Journal of Ambient Intelligence and Humanized Computing (2019):doi={10.1007/s12652-019-01503-y}.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Zhu-Zhao2019_Article（2210KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览