ChessUSA.com TalkChess.com
Hosted by Your Move Chess & Games
 
 FAQFAQ   SearchSearch   MemberlistMemberlist   UsergroupsUsergroups   RegisterRegister 
 ProfileProfile   Log in to check your private messagesLog in to check your private messages   Log inLog in 

Search found 1613 matches
TalkChess.com Forum Index
Author Message
  Topic: Google's AlphaGo team has been working on chess
Milos Stanisavljevic

Replies: 107
Views: 17665

PostForum: Computer Chess Club: Programming and Technical Discussions   Posted: Wed Dec 13, 2017 12:37 am   Subject: Re: Google's AlphaGo team has been working on chess
But I am looking at the (so-called MC) tree it builds, starting with a 1-node tree and growing it by successively expanding leaf nodes (whether by NN or some other means). That is how automatic book b ...
  Topic: Historic Milestone: AlphaZero
Milos Stanisavljevic

Replies: 191
Views: 46363

PostForum: Computer Chess Club: General Topics   Posted: Mon Dec 11, 2017 5:43 pm   Subject: Re: Much weaker than Stockfish
It was not 4 hours of thinking, but 4 hours of (self-)playing 20 million games.
What we don't know is what were the starting positions of those 20 million self-played games.
Dirichlet noise and temp ...
  Topic: Google's AlphaGo team has been working on chess
Milos Stanisavljevic

Replies: 107
Views: 17665

PostForum: Computer Chess Club: Programming and Technical Discussions   Posted: Mon Dec 11, 2017 4:45 pm   Subject: Re: Google's AlphaGo team has been working on chess
They are not playing out any games "to the very end". And the randomness of the selection is also quite limited (if not completely absent - the paper states that the edge is selected that ma ...
  Topic: Alpha Zero vs Stockfish 8 tournament conditions.
Milos Stanisavljevic

Replies: 82
Views: 9868

PostForum: Computer Chess Club: General Topics   Posted: Mon Dec 11, 2017 4:16 pm   Subject: Re: Alpha Zero vs Stockfish 8 tournament conditions.
A0 is not about NN evaluation it's about MCTS i.e. UCT without rollouts (based only on eval) actually being superior than classical minimax when parallelization resources are enormous coz its parallel ...
  Topic: Historic Milestone: AlphaZero
Milos Stanisavljevic

Replies: 191
Views: 46363

PostForum: Computer Chess Club: General Topics   Posted: Mon Dec 11, 2017 3:59 pm   Subject: Re: Much weaker than Stockfish
It was not 4 hours of thinking, but 4 hours of (self-)playing 20 million games.
That counts as thinking (i.e. information processing without any exchange of information with the outside world). It is ...
  Topic: Historic Milestone: AlphaZero
Milos Stanisavljevic

Replies: 191
Views: 46363

PostForum: Computer Chess Club: General Topics   Posted: Mon Dec 11, 2017 3:55 pm   Subject: Re: Much weaker than Stockfish
Try to concentrate on content.
Sorry, but you offer none, nothing to concentrate on, just similar kind of rumblings like Anil. You clearly don't understand how Alpha0 works, how it is trained, and wh ...
  Topic: Historic Milestone: AlphaZero
Milos Stanisavljevic

Replies: 191
Views: 46363

PostForum: Computer Chess Club: General Topics   Posted: Mon Dec 11, 2017 3:03 pm   Subject: Re: Much weaker than Stockfish
Try to concentrate on content.
Sorry, but you offer none, nothing to concentrate on, just similar kind of rumblings like Anil. You clearly don't understand how Alpha0 works, how it is trained, and wh ...
  Topic: Historic Milestone: AlphaZero
Milos Stanisavljevic

Replies: 191
Views: 46363

PostForum: Computer Chess Club: General Topics   Posted: Mon Dec 11, 2017 2:38 pm   Subject: Re: Much weaker than Stockfish
Thatís not the point.
AZ plays more human like stockfish etc.

Although these programs were made by men.
The grandmasters and IMs and Kiebitzes arround world are all compeletY happy to see steinit ...
  Topic: Historic Milestone: AlphaZero
Milos Stanisavljevic

Replies: 191
Views: 46363

PostForum: Computer Chess Club: General Topics   Posted: Mon Dec 11, 2017 2:35 pm   Subject: Re: Much weaker than Stockfish
It just took the rules, and after 4 hours of thinking about them it reached a conclusion of how to best play the game decribed by those rules, that was good enough to perform at 3000+ Elo level.
It ...
  Topic: Is Houdini only TOP3 engine with NUMA support in TCEC?
Milos Stanisavljevic

Replies: 2
Views: 569

PostForum: Computer Chess Club: General Topics   Posted: Mon Dec 11, 2017 2:29 pm   Subject: Re: Is Houdini only TOP3 engine with NUMA support in TCEC?
I remember to read, that neither SF nor Komodo has real NUMA support. According to Houdini document it has +50% boost to nodespeed with dual XEON and NUMA!
Brainfish works pretty good with NUMA (and ...
 
Page 1 of 162 Goto page 1, 2, 3 ... 160, 161, 162  Next
All times are GMT
Jump to:  




Powered by phpBB © 2001, 2005 phpBB Group
Enhanced with Moby Threads