Grandmaster level in StarCraft II using multi-agent reinforcement learning

Oriol Vinyals (), Igor Babuschkin, Wojciech M. Czarnecki, Michaël Mathieu, Andrew Dudzik, Junyoung Chung, David H. Choi, Richard Powell, Timo Ewalds, Petko Georgiev, Junhyuk Oh, Dan Horgan, Manuel Kroiss, Ivo Danihelka, Aja Huang, Laurent Sifre, Trevor Cai, John P. Agapiou, Max Jaderberg, Alexander S. Vezhnevets, Rémi Leblond, Tobias Pohlen, Valentin Dalibard, David Budden, Yury Sulsky, James Molloy, Tom L. Paine, Caglar Gulcehre, Ziyu Wang, Tobias Pfaff, Yuhuai Wu, Roman Ring, Dani Yogatama, Dario Wünsch, Katrina McKinney, Oliver Smith, Tom Schaul, Timothy Lillicrap, Koray Kavukcuoglu, Demis Hassabis, Chris Apps and David Silver ()
Additional contact information
Oriol Vinyals: DeepMind
Igor Babuschkin: DeepMind
Wojciech M. Czarnecki: DeepMind
Michaël Mathieu: DeepMind
Andrew Dudzik: DeepMind
Junyoung Chung: DeepMind
David H. Choi: DeepMind
Richard Powell: DeepMind
Timo Ewalds: DeepMind
Petko Georgiev: DeepMind
Junhyuk Oh: DeepMind
Dan Horgan: DeepMind
Manuel Kroiss: DeepMind
Ivo Danihelka: DeepMind
Aja Huang: DeepMind
Laurent Sifre: DeepMind
Trevor Cai: DeepMind
John P. Agapiou: DeepMind
Max Jaderberg: DeepMind
Alexander S. Vezhnevets: DeepMind
Rémi Leblond: DeepMind
Tobias Pohlen: DeepMind
Valentin Dalibard: DeepMind
David Budden: DeepMind
Yury Sulsky: DeepMind
James Molloy: DeepMind
Tom L. Paine: DeepMind
Caglar Gulcehre: DeepMind
Ziyu Wang: DeepMind
Tobias Pfaff: DeepMind
Yuhuai Wu: DeepMind
Roman Ring: DeepMind
Dani Yogatama: DeepMind
Dario Wünsch: Team Liquid
Katrina McKinney: DeepMind
Oliver Smith: DeepMind
Tom Schaul: DeepMind
Timothy Lillicrap: DeepMind
Koray Kavukcuoglu: DeepMind
Demis Hassabis: DeepMind
Chris Apps: DeepMind
David Silver: DeepMind

Nature, 2019, vol. 575, issue 7782, 350-354

Abstract: Abstract 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 competitions1–3, the strongest agents have simplified important aspects of the game, utilized superhuman capabilities, or employed hand-crafted sub-systems4. 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 networks5,6. 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.

Date: 2019
References: Add references at CitEc
Citations: View citations in EconPapers (40)

Downloads: (external link)
https://www.nature.com/articles/s41586-019-1724-z Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:nature:v:575:y:2019:i:7782:d:10.1038_s41586-019-1724-z

Ordering information: This journal article can be ordered from
https://www.nature.com/

DOI: 10.1038/s41586-019-1724-z

Access Statistics for this article

Nature is currently edited by Magdalena Skipper

More articles in Nature from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().