AlphaZero vs. Stockfish 8

OK, AlphaGo has morphed into AlphaZero, a self-learning neural net that is claimed to have trounced Stockfish 8, the current champ chess engine.

There were 100 games between the two, ten of which were published in this paper:

Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm (arxiv)

Now, lots of sites have the 10 games available for replay, but the PGN isn’t easy to find for download (if it exists at all). So I’ve copied out the games from the pdf, and normalized the headers, for the convenience of you, dear reader.

z-PGN: AlphaZero vs. Stockfish 8.pgn

I took the date from chess24, which put it one day previous to the pdf’s publication date.

OK, that’s that  (but, for the interested, here is the wiki link for further reading: AlphaZero)

 

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

w

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.