CASIA OpenIR  > 复杂系统管理与控制国家重点实验室  > 深度强化学习
StarCraft Micromanagement With Reinforcement Learning and Curriculum Transfer Learning
Kun Shao1,2; Yuanheng Zhu1,2; Dongbin Zhao1,2
Source PublicationIEEE Transactions on Emerging Topics in Computational Intelligence
ISSN2471-285X
2019-02
Volume3Issue:1Pages:73-84
Abstract

Real-time strategy games have been an important
field of game artificial intelligence in recent years. This paper
presents a reinforcement learning and curriculum transfer learning method to control multiple units in StarCraft micromanagement. We define an efficient state representation, which breaks
down the complexity caused by the large state space in the game
environment. Then, a parameter sharing multi-agent gradientdescent Sarsa(λ) algorithm is proposed to train the units. The
learning policy is shared among our units to encourage cooperative
behaviors. We use a neural network as a function approximator
to estimate the action–value function, and propose a reward function to help units balance their move and attack. In addition, a
transfer learning method is used to extend our model to more difficult scenarios, which accelerates the training process and improves
the learning performance. In small-scale scenarios, our units successfully learn to combat and defeat the built-in AI with 100%
win rates. In large-scale scenarios, the curriculum transfer learning method is used to progressively train a group of units, and it
shows superior performance over some baseline methods in target
scenarios. With reinforcement learning and curriculum transfer
learning, our units are able to learn appropriate strategies in StarCraft micromanagement scenarios.

KeywordReinforcement Learning, Transfer Learning, Curriculum Learning, Neural Network, Game Ai
MOST Discipline Catalogue工学
Indexed ByEI
Language英语
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/23362
Collection复杂系统管理与控制国家重点实验室_深度强化学习
Corresponding AuthorDongbin Zhao
Affiliation1.State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Kun Shao,Yuanheng Zhu,Dongbin Zhao. StarCraft Micromanagement With Reinforcement Learning and Curriculum Transfer Learning[J]. IEEE Transactions on Emerging Topics in Computational Intelligence,2019,3(1):73-84.
APA Kun Shao,Yuanheng Zhu,&Dongbin Zhao.(2019).StarCraft Micromanagement With Reinforcement Learning and Curriculum Transfer Learning.IEEE Transactions on Emerging Topics in Computational Intelligence,3(1),73-84.
MLA Kun Shao,et al."StarCraft Micromanagement With Reinforcement Learning and Curriculum Transfer Learning".IEEE Transactions on Emerging Topics in Computational Intelligence 3.1(2019):73-84.
Files in This Item: Download All
File Name/Size DocType Version Access License
StarCraft Micromanag(4125KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Kun Shao]'s Articles
[Yuanheng Zhu]'s Articles
[Dongbin Zhao]'s Articles
Baidu academic
Similar articles in Baidu academic
[Kun Shao]'s Articles
[Yuanheng Zhu]'s Articles
[Dongbin Zhao]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Kun Shao]'s Articles
[Yuanheng Zhu]'s Articles
[Dongbin Zhao]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: StarCraft Micromanagement With Reinforcement Learning and Curriculum Transfer Learning.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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