Knowledge Commons of Institute of Automation,CAS
Learning Deep Decentralized Policy Network by Collective Rewards for Real-Time Combat Game | |
Peixi Peng1; Junliang Xing1; Lili Cao1; Lisen Mu2; Chang Huang2 | |
2019 | |
会议名称 | International Joint Conference on Artificial Intelligence |
会议日期 | August 10-16, 2019 |
会议地点 | Macao, China |
摘要 | The task of real-time combat game is to coordinate multiple units to defeat their enemies controlled by the given opponent in a real-time combat scenario. It is difficult to design a high-level Artificial Intelligence (AI) program for such a task due to its extremely large state-action space and real-time requirements. This paper formulates this task as a collective decentralized partially observable Markov decision process, and designs a Deep Decentralized Policy Network (DDPN) to model the polices. To train DDPN effectively, a novel two-stage learning algorithm is proposed which |
关键词 | Multi-agent Learning Deep Decentralized Policy Network Real-time Combat Game |
收录类别 | SCI |
七大方向——子方向分类 | 决策智能理论与方法 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/26156 |
专题 | 智能系统与工程 |
通讯作者 | Junliang Xing |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.Horizon Robotics |
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 | Peixi Peng,Junliang Xing,Lili Cao,et al. Learning Deep Decentralized Policy Network by Collective Rewards for Real-Time Combat Game[C],2019. |
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 | ||
IJCAI19StarCraftFina(762KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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