Papers › Accelerating Self-Play Learning in Go

Accelerating Self-Play Learning in Go

27 Feb 2019arXiv:1902.10565archive 2025-07-28

David J. Wu

By introducing several improvements to the AlphaZero process and architecture, we greatly accelerate self-play learning in Go, achieving a 50x reduction in computation over comparable methods. Like AlphaZero and replications such as ELF OpenGo and Leela Zero, our bot KataGo only learns from neural-net-guided Monte Carlo tree search self-play. But whereas AlphaZero required thousands of TPUs over several days and ELF required thousands of GPUs over two weeks, KataGo surpasses ELF's final model after only 19 days on fewer than 30 GPUs. Much of the speedup involves non-domain-specific improvements that might directly transfer to other problems. Further gains from domain-specific techniques reveal the remaining efficiency gap between the best methods and purely general methods such as AlphaZero. Our work is a step towards making learning in state spaces as large as Go possible without large-scale computational resources.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

lightvector/KataGo officialmentioned in papermentioned on GitHubtfNOASSERTION report
030helios/Kata2Surakarta mentioned on GitHubNOASSERTION report
MarkTakken/KataGoToroidal mentioned on GitHubNOASSERTION report
alextrudeau/go_exploit mentioned on GitHubpytorchApache-2.0 report
alignmentresearch/katago-custom mentioned on GitHubNOASSERTION report
rsdmse/KataGo mentioned on GitHubtfNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Game of Go

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AlphaZero

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections