Learning battles in ViZDoom via deep 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

	Learning battles in ViZDoom via deep reinforcement learning
	Kun Shao1,2 ; Dongbin Zhao1,2 ; Nannan Li1,2 ; Yuanheng Zhu1,2
	2018-10
会议名称	IEEE Conference on Computational Intelligence and Games
会议日期	2018-08
会议地点	Maastricht, The Netherlands
摘要	First-person shooter (FPS) video games play an important role in game artificial intelligence (AI). In this paper, we present an effective deep reinforcement learning (DRL) method to learn battles in ViZDoom. Our approach utilizes the actorcritic with Kronecker-factored trust region (ACKTR), a sampleefficient and computationally inexpensive DRL method. We train our ACKTR agents in two battle scenarios, and compare with the advantage actor-critic (A2C) baseline agent. The experimental results demonstrate that DRL methods successfully teach agents to battle in these scenarios. In addition, the ACKTR agents significantly outperform the A2C agents in terms of all the metrics by a significant margin.
其他摘要
关键词	Reinforcement Learning, Deep Learning, Game Ai
学科门类	工学
收录类别	EI
语种	英语
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/23364
专题	多模态人工智能系统全国重点实验室_深度强化学习
通讯作者	Dongbin Zhao
作者单位	1.The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Kun Shao,Dongbin Zhao,Nannan Li,et al. Learning battles in ViZDoom via deep reinforcement learning[C],2018.

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
Learning Battles in （446KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载