CASIA OpenIR
Learning Deep Decentralized Policy Network by Collective Rewards for Real-Time Combat Game
Peixi Peng1; Junliang Xing1; Lili Cao1; Lisen Mu2; Chang Huang2
2019
Conference NameInternational Joint Conference on Artificial Intelligence
Conference DateAugust 10-16, 2019
Conference PlaceMacao, China
Abstract

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
combines imitation learning from opponent and reinforcement learning by no-regret dynamics.  Extensive experimental results on various combat
scenarios indicate that proposed method can defeat different opponent models and significantly outperforms many state-of-the-art approaches.

KeywordMulti-agent Learning Deep Decentralized Policy Network Real-time Combat Game
Indexed BySCI
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/26156
Collection中国科学院自动化研究所
Corresponding AuthorJunliang Xing
Affiliation1.Institute of Automation, Chinese Academy of Sciences
2.Horizon Robotics
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
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.
Files in This Item: Download All
File Name/Size DocType Version Access License
IJCAI19StarCraftFina(762KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Peixi Peng]'s Articles
[Junliang Xing]'s Articles
[Lili Cao]'s Articles
Baidu academic
Similar articles in Baidu academic
[Peixi Peng]'s Articles
[Junliang Xing]'s Articles
[Lili Cao]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Peixi Peng]'s Articles
[Junliang Xing]'s Articles
[Lili Cao]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: IJCAI19StarCraftFinal.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.