[1712.01815] Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
5
Public whispers
5
Contributors
2026-07-23 10:05:08
First whispered
Public whispers on this page
Text Highlight2026-07-23 13:26:08
Original Highlight Excerpt
"arXivLabs is a framework that allows collaborators to develop and share new arXiv features"
Whisper Note
Huh, I thought arXiv was just a paper dump, didn't know they had labs for devs.
Text Highlight2026-07-23 13:17:08
Original Highlight Excerpt
"arXivLabs is a framework that allows collaborators to develop and share new arXiv features"
Whisper Note
Wait, so this is like an open-source playground for arXiv itself? Cool.
Text Highlight2026-07-23 10:23:08
Original Highlight Excerpt
"The game of chess is the most widely-studied domain in the history of artificial intelligence"
Whisper Note
I wonder if AlphaZero's chess style will change how human grandmasters think about openings.
Text Highlight2026-07-23 10:14:08
Original Highlight Excerpt
"The game of chess is the most widely-studied domain in the history of artificial intelligence"
Whisper Note
Still, this paper basically ends the debate—self-play beats all that handcrafted stuff.
Text Highlight2026-07-23 10:05:08
Original Highlight Excerpt
"The game of chess is the most widely-studied domain in the history of artificial intelligence"
Whisper Note
True, but chess AI history is basically a arms race of human tweaks, not pure learning.
Share this page's whispers
Short link
https://domwhisper.com/s/f14fdc9c4246Embed snippet
<iframe src="https://domwhisper.com/embed/f14fdc9c4246" width="100%" height="480" style="border:0;border-radius:16px" loading="lazy"></iframe>See what people are discussing on arxiv.org
Install DomWhisper to view live whispers as you browse, and join the discussion.
Get the extension