Page 2 of 2 FirstFirst 12
Results 16 to 18 of 18

Thread: Classic chess learnings are a straight jacket

  1. | #16
    Volunteer MOZ's Avatar
    Join Date
    Jul 2007
    Location
    MOZ* is my main signon; PMs to me should be directed here. Other special purpose signons are used.
    Posts
    5,097

    Default Not just Danny King

    FReedom though Fischer-Random chess to enjoy the whole game.

  2. | #17
    Siberian Chess Tiger Axiom's Avatar
    Join Date
    Aug 2007
    Location
    Australia
    Posts
    4,875

    Default

    Is Alpha Zero currently the strongest chess playing entity on the planet? Is that simply a matter of how many football fields of hardware are involved, or something else?

    Could Alpha Zero play enough self-learning games to approach an asymptotic limit of the perfect game?
    Last edited by Axiom; 21-12-18 at 09:20 PM.
    "Don't let the snow get down the back of your pants" ~ SCT

  3. | #18
    Volunteer MOZ's Avatar
    Join Date
    Jul 2007
    Location
    MOZ* is my main signon; PMs to me should be directed here. Other special purpose signons are used.
    Posts
    5,097

    Default

    Quote Originally Posted by Axiom View Post
    Is Alpha Zero currently the strongest chess playing entity on the planet?
    Some of the evidence is pointing to that conclusion. And if Alpha Zero can knock off all other computers then we will be faced with the question, "How did it learn so quickly".

    Quote Originally Posted by Axiom View Post
    Is that simply a matter of how many football fields of hardware are involved, or something else?
    Probably not because the early evidence is that Stockfish, and some other 'engines' running on significantly larger platforms than Alpha Zero, is not being out-muscled nor out-leaved but simply outplayed.

    Quote Originally Posted by Axiom View Post
    Could Alpha Zero play enough self-learning games to approach an asymptotic limit of the perfect game?
    No, I don't think it can play the perfect game. Because it is not searching to infinity. It is only searching 'branches and limbs' to a limited horizon; that horizon is not even as deep as STOCKFISH.
    FReedom though Fischer-Random chess to enjoy the whole game.

Page 2 of 2 FirstFirst 12

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •