Revision History
AlphaStar · 11 revisions
Sizes are character counts of the article source. The signed number is the change from the previous revision.
Recent edit summaries
Detailed summaries recorded by editors. Generic maintenance summaries are omitted here; every recorded revision remains below. Dates describe the edit, not necessarily the event it covers.
- Correction: Corrected AlphaStar's Nature-version training figures (32 TPUs per agent over 44 days, not the January demo's 16 TPUs and 14 days), the reward description (draws and strategy pseudo-rewards were used), the date the Grandmaster rank was reached, a TLO quote that was attributed to the January 2019 series but came from October 2019, and OpenAI Five's compute figures in the comparison table (plus 19 minor fixes)
Version 11 · Nov 4, 2026, 10:31 PM
- Update: added an official video.
Version 10 · Nov 1, 2026, 08:01 AM
- Improve internal links (2026-10-13)
Version 9 · Oct 13, 2026, 10:10 AM
- Added 6 contextual internal links
Version 8 · Jul 23, 2026, 03:14 PM