Grandmaster level in StarCraft II using multi-agent reinforcement learning

Many real-world applications require artificial agents to compete and coordinate with other agents in complex environments. As a stepping stone to this goal, the domain of StarCraft has emerged as an important challenge for artificial intelligence research, owing to its iconic and enduring status am...

Full description

Saved in:

Bibliographic Details
Published in:	Nature (London) Vol. 575; no. 7782; pp. 350 - 354
Main Authors:	Vinyals, Oriol, Babuschkin, Igor, Czarnecki, Wojciech M., Mathieu, Michaël, Dudzik, Andrew, Chung, Junyoung, Choi, David H., Powell, Richard, Ewalds, Timo, Georgiev, Petko, Oh, Junhyuk, Horgan, Dan, Kroiss, Manuel, Danihelka, Ivo, Huang, Aja, Sifre, Laurent, Cai, Trevor, Agapiou, John P., Jaderberg, Max, Vezhnevets, Alexander S., Leblond, Rémi, Pohlen, Tobias, Dalibard, Valentin, Budden, David, Sulsky, Yury, Molloy, James, Paine, Tom L., Gulcehre, Caglar, Wang, Ziyu, Pfaff, Tobias, Wu, Yuhuai, Ring, Roman, Yogatama, Dani, Wünsch, Dario, McKinney, Katrina, Smith, Oliver, Schaul, Tom, Lillicrap, Timothy, Kavukcuoglu, Koray, Hassabis, Demis, Apps, Chris, Silver, David
Format:	Journal Article
Language:	English
Published:	London Nature Publishing Group UK 01-11-2019 Nature Publishing Group
Subjects:	639/705/117 639/705/531 Actors Agents (artificial intelligence) Algorithms Artificial Intelligence Cameras Complexity Computer & video games Domains Game theory Humanities and Social Sciences Humans Learning Machine learning Methods Multiagent systems multidisciplinary Multiplayer online games Neural networks Pattern recognition Players Rankings Reinforcement Reinforcement learning (Machine learning) Reinforcement, Psychology Science Science (multidisciplinary) Technology application Video Games United Kingdom
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Many real-world applications require artificial agents to compete and coordinate with other agents in complex environments. As a stepping stone to this goal, the domain of StarCraft has emerged as an important challenge for artificial intelligence research, owing to its iconic and enduring status among the most difficult professional esports and its relevance to the real world in terms of its raw complexity and multi-agent challenges. Over the course of a decade and numerous competitions 1 – 3 , the strongest agents have simplified important aspects of the game, utilized superhuman capabilities, or employed hand-crafted sub-systems 4 . Despite these advantages, no previous agent has come close to matching the overall skill of top StarCraft players. We chose to address the challenge of StarCraft using general-purpose learning methods that are in principle applicable to other complex domains: a multi-agent reinforcement learning algorithm that uses data from both human and agent games within a diverse league of continually adapting strategies and counter-strategies, each represented by deep neural networks 5 , 6 . We evaluated our agent, AlphaStar, in the full game of StarCraft II, through a series of online games against human players. AlphaStar was rated at Grandmaster level for all three StarCraft races and above 99.8% of officially ranked human players. AlphaStar uses a multi-agent reinforcement learning algorithm and has reached Grandmaster level, ranking among the top 0.2% of human players for the real-time strategy game StarCraft II.
Bibliography:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ISSN:	0028-0836 1476-4687
DOI:	10.1038/s41586-019-1724-z