AlphaZero explained by one creator

Discussion of anything and everything relating to chess playing software and machines.

Moderators: bob, hgm, Harvey Williamson

Forum rules
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.
Post Reply
mario carbonell
Posts: 7
Joined: Tue Dec 12, 2017 6:14 pm

AlphaZero explained by one creator

Post by mario carbonell » Tue Dec 19, 2017 10:22 am

I found this youtube video very explanatory about the way AlphaZero works. I think it is not very technical and everybody can understand what he says.

He explains how Monte Carlo Tree Search works without rollouts.

Keynote David Silver NIPS 2017 Deep Reinforcement Learning Symposium AlphaZero

https://www.youtube.com/watch?v=A3ekFcZ3KNw

User avatar
AdminX
Posts: 5154
Joined: Mon Mar 13, 2006 1:34 pm
Location: Acworth, GA
Contact:

Re: AlphaZero explained by one creator

Post by AdminX » Tue Dec 19, 2017 10:47 am

mario carbonell wrote:I found this youtube video very explanatory about the way AlphaZero works. I think it is not very technical and everybody can understand what he says.

He explains how Monte Carlo Tree Search works without rollouts.

Keynote David Silver NIPS 2017 Deep Reinforcement Learning Symposium AlphaZero

https://www.youtube.com/watch?v=A3ekFcZ3KNw
Thank You! Interesting discussion.
"Good decisions come from experience, and experience comes from bad decisions."
__________________________________________________________________
Ted Summers

Post Reply