Isn’t this an odd configuration of Wins/Losses/Ties? Alpha Zero is never losing but usually it ties. This suggests to me it’s opponent is playing almost perfectly and gives very small room for an edge. Or with more training could Alpha Zero usually win and not tie?
In just a few hours, [AlphaZero] plays more games against itself than have been recorded in human chess history.... It quickly becomes strong enough to defeat the best chess-playing entities in the world. -- @Kasparov63
http://science.sciencemag.org/content/362/6419/1087 …
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Please teach it tic-tac-toe early! https://m.youtube.com/watch?v=F7qOV8xonfY …
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Not to worry fellow carbon based peeps as soon as I figure out the horsey piece I will kick robot butt........the queen can move anywhere right?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Phrasing is akin to: "The system goes online on August 4th, 1997. Human decisions are removed from strategic defense. Skynet begins to learn at a geometric rate. It becomes self-aware at 2:14 AM, Eastern time, August 29th. In a panic, they try to pull the plug."
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
In your opinion, could it be that chess-playing algorithms develop into general (i.e., creative) intelligences?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Yeah but does it know the joy of winning a tournament on a frozen Sunday fuelled only by a sausage roll and a desperate need to be noticed. I don’t think so...
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.