AlphaStar: an integrated application of reinforcement learning algorithms

Yulong Zhang; Li Chen; Xingxing Liang; Jing Yang; Yang Ding; Yanghe Feng

doi:10.1117/12.2641019

2 December 2022 AlphaStar: an integrated application of reinforcement learning algorithms

Yulong Zhang, Li Chen, Xingxing Liang, Jing Yang, Yang Ding, Yanghe Feng

Proceedings Volume 12288, International Conference on Computer, Artificial Intelligence, and Control Engineering (CAICE 2022); 1228816 (2022) https://doi.org/10.1117/12.2641019
Event: International Conference on Computer, Artificial Intelligence, and Control Engineering (CAICE 2022), 2022, Zhuhai, China

Abstract

Deep Reinforcement Learning (DRL) is poised to revolutionize the field of AI and represents a step towards general intelligence. Currently, AlphaStar achieved the Grandmaster level in StarCraft gaming, which is a remarkable breakthrough in Real-Time Strategy (RTS) gaming. The paper discusses the general framework of RTS gaming agents, and presents the method innovation from baseline RL algorithms to the AlphaStar. We begin with the basic idea and taxonomy of DRL, then progress to the technical framework of AlphaStar from the perspective of state space design, action space design, policy and value net framework and multi-agent training methods, presenting key issue and feasible method in full-length scale of RTS gaming. Finally, we draw a brief conclusion.

Citation Download Citation

Yulong Zhang, Li Chen, Xingxing Liang, Jing Yang, Yang Ding, and Yanghe Feng "AlphaStar: an integrated application of reinforcement learning algorithms", Proc. SPIE 12288, International Conference on Computer, Artificial Intelligence, and Control Engineering (CAICE 2022), 1228816 (2 December 2022); https://doi.org/10.1117/12.2641019

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available