← All works
Research paper

Grandmaster level in StarCraft II using multi-agent reinforcement learning

At a glance

AlphaStar reached Grandmaster level in StarCraft II through competitive AI training.

In one paragraph

Introduced AlphaStar, which learned from human games and a league of competing AI players to reach Grandmaster level in StarCraft II. It ranked above 99.8% of human players across all three playable factions.

Authors 42

  1. Oriol Vinyals
  2. Igor Babuschkin
  3. Wojciech Czarnecki
  4. Michaël Mathieu
  5. Andrew Dudzik
  6. Junyoung Chung
  7. David H. Choi
  8. Richard Powell
  9. Timo Ewalds
  10. Petko Georgiev
  11. Junhyuk Oh
  12. Dan Horgan
  13. Manuel Kroiss
  14. Ivo Danihelka
  15. Aja Huang
  16. Laurent Sifre
  17. Trevor Cai
  18. John P. Agapiou
  19. Max Jaderberg
  20. Alexander S. Vezhnevets
  21. Rémi Leblond
  22. Toby Pohlen
  23. Valentin Dalibard
  24. David Budden
  25. Yury Sulsky
  26. James Molloy
  27. Tom L. Paine
  28. Caglar Gulcehre
  29. Ziyu Wang
  30. Tobias Pfaff
  31. Yuhuai (Tony) Wu
  32. Roman Ring
  33. Dani Yogatama
  34. Dario Wünsch
  35. Katrina McKinney
  36. Oliver Smith
  37. Tom Schaul
  38. Timothy Lillicrap
  39. Koray Kavukcuoglu
  40. Demis Hassabis
  41. Chris Apps
  42. David Silver

Organizations

Credited for this work at publication.