{c}
{title2=2024}

https://deepmind.google/discover/blog/ai-solves-imo-problems-at-silver-medal-level/
> AI achieves silver-medal standard solving <International Mathematical Olympiad> problems

Uses <autoformalization> down to <Lean>, and then <AlphaZero>. Cool.


AlphaProof

{c}
{tag=Open source software}
{wiki}

Related to <Leela Zero>, a <Go engine>

= Lc0
{c}
{synonym}
{title2}

<Deep learning> implementation, a bit analogous to <AlphaZero>, but for <chess> only.


Leela Chess Zero

{c}
{tag=Chess engine}
{tag=Go engine}
{title2=2017}
{wiki}

Generalization of <AlphaGo Zero> that plays <Go (game)>, <chess> and shogi.
* https://www.science.org/doi/10.1126/science.aar6404[] A general <reinforcement learning> algorithm that masters <chess>, <shogi>, and <Go (game)> through self-play by Silver et al. (2018), <published without source code>
* https://www.quora.com/Is-there-an-Open-Source-version-of-AlphaZero-specifically-the-generic-game-learning-tool-distinct-from-AlphaGo

https://www.quora.com/Which-chess-engine-would-be-stronger-Alpha-Zero-or-Stockfish-12/answer/Felix-Zaslavskiy explains that it beat <Stockfish (chess)> 8. But then Stockfish was developed further and would start to beat it. We know this because although AlphaZero was closed source, they released the <trained artificial neural network>, so it was possible to replay AlphaZero at its particular stage of training.


Ciro Santilli @cirosantilli 37

 Incoming links: AlphaZero