Page 1 of 1
Matthew Sadler analysis of A0 vs SF [Edit: A0 published in Science?]
Posted: Thu Dec 06, 2018 8:27 pm
by trulses
Not sure if these videos are being posted in another thread but it might be interesting,
https://www.youtube.com/watch?v=JacRX6cKIaY
edit: published here apparently
http://science.sciencemag.org/content/362/6419/1140
Re: Matthew Sadler analysis of A0 vs SF [Edit: A0 published in Science?]
Posted: Fri Dec 07, 2018 4:23 am
by Geonerd
And the superb Daniel King analyzes another.
https://www.youtube.com/watch?v=pFtY7gNRVRI
Re: Matthew Sadler analysis of A0 vs SF [Edit: A0 published in Science?]
Posted: Fri Dec 07, 2018 1:20 pm
by Look
From the "article" :
[...]
AlphaZero is a generic reinforcement learning and search algorithm—originally devised for the game of Go—that achieved superior results within a few hours, searching
as many positions, given no domain knowledge except the rules of chess.
[...]
What did Carlsen learn during his early hours as a chess affectionate?