Learning battles in ViZDoom via deep reinforcement learning | |
Kun Shao1,2; Dongbin Zhao1,2; Nannan Li1,2; Yuanheng Zhu1,2 | |
2018-10 | |
会议日期 | 2018-08 |
会议地点 | Maastricht, The Netherlands |
关键词 | Reinforcement Learning, Deep Learning, Game Ai |
英文摘要 | 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 |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/23364] |
专题 | 复杂系统管理与控制国家重点实验室_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 |
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]. 见:. Maastricht, The Netherlands. 2018-08. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论