TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Much More Efficient Self-Play Learning in Go

2 pointsby jedharrisalmost 5 years ago

2 comments

jedharrisalmost 5 years ago
The author&#x27;s most recent version of KataGo averages about 50 times greater learning efficiency from self-play.<p>See &lt;<a href="https:&#x2F;&#x2F;blog.janestreet.com&#x2F;deep-learning-the-hardest-go-problem-in-the-world&#x2F;&gt;" rel="nofollow">https:&#x2F;&#x2F;blog.janestreet.com&#x2F;deep-learning-the-hardest-go-pro...</a>. This covers developments since the initial post, plus the headline problem (which is still open).
jedharrisalmost 5 years ago
Related demos, repositories, papers and posts:<p>More recent and extensive post: <a href="https:&#x2F;&#x2F;blog.janestreet.com&#x2F;deep-learning-the-hardest-go-problem-in-the-world&#x2F;" rel="nofollow">https:&#x2F;&#x2F;blog.janestreet.com&#x2F;deep-learning-the-hardest-go-pro...</a><p>Site to play against KataGo: <a href="https:&#x2F;&#x2F;online-go.com&#x2F;player&#x2F;592684&#x2F;" rel="nofollow">https:&#x2F;&#x2F;online-go.com&#x2F;player&#x2F;592684&#x2F;</a><p>Arxiv paper on KataGo design: <a href="https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;1902.10565" rel="nofollow">https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;1902.10565</a><p>GitHub repository of KataGo: <a href="https:&#x2F;&#x2F;github.com&#x2F;lightvector&#x2F;KataGo" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;lightvector&#x2F;KataGo</a><p>Another writer commenting on the history of Go AI, and significance of KataGo: <a href="https:&#x2F;&#x2F;brantondemoss.com&#x2F;writing&#x2F;kata.html" rel="nofollow">https:&#x2F;&#x2F;brantondemoss.com&#x2F;writing&#x2F;kata.html</a>