Navigating the landscape of multiplayer games

Shayegan Omidshafiei (), Karl Tuyls, Wojciech M. Czarnecki, Francisco C. Santos, Mark Rowland, Jerome Connor, Daniel Hennes, Paul Muller, Julien Pérolat, Bart De Vylder, Audrunas Gruslys and Rémi Munos
Additional contact information
Shayegan Omidshafiei: DeepMind
Karl Tuyls: DeepMind
Wojciech M. Czarnecki: DeepMind
Francisco C. Santos: INESC-ID and Instituto Superior Técnico, Universidade de Lisboa
Mark Rowland: DeepMind
Jerome Connor: DeepMind
Daniel Hennes: DeepMind
Paul Muller: DeepMind
Julien Pérolat: DeepMind
Bart De Vylder: DeepMind
Audrunas Gruslys: DeepMind
Rémi Munos: DeepMind

Nature Communications, 2020, vol. 11, issue 1, 1-17

Abstract: Abstract Multiplayer games have long been used as testbeds in artificial intelligence research, aptly referred to as the Drosophila of artificial intelligence. Traditionally, researchers have focused on using well-known games to build strong agents. This progress, however, can be better informed by characterizing games and their topological landscape. Tackling this latter question can facilitate understanding of agents and help determine what game an agent should target next as part of its training. Here, we show how network measures applied to response graphs of large-scale games enable the creation of a landscape of games, quantifying relationships between games of varying sizes and characteristics. We illustrate our findings in domains ranging from canonical games to complex empirical games capturing the performance of trained agents pitted against one another. Our results culminate in a demonstration leveraging this information to generate new and interesting games, including mixtures of empirical games synthesized from real world games.

Date: 2020
References: Add references at CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://www.nature.com/articles/s41467-020-19244-4 Abstract (text/html)

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:natcom:v:11:y:2020:i:1:d:10.1038_s41467-020-19244-4

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

DOI: 10.1038/s41467-020-19244-4

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

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