[Computer-go] AlphaZero paper difference between 2017 and 2018

[Hiroshi Yamashita]

Hi,

Number of learned positions from a game record

                  pos     steps  minibatch       games
AlphaGoZero      293 (  700,000 * 2048) /   4,900,000                     3 days
AlphaGoZero      219 (3,100,000 * 2048) /  29,000,000    256 x 40 block, 40 days
AlphaZero 2017   137 (  700,000 * 4096) /  21,000,000
AlphaZero 2018    20 (  700,000 * 4096) / 140,000,000
ELF 2019         154 (1,500,000 * 2048) /  20,000,000
AlphaZero(Chess)  65 (  700,000 * 4096) /  44,000,000
AlphaZero(Shogi) 119 (  700,000 * 4096) /  24,000,000

All Network is 256 x 20 blocks, except AlphaGoZero 40 days.

Average of game moves are
Go    220
Chess  80
Shogi 120

So I had thought learning all positions(from a game) once is nice.
But AlphaZero2018 uses only 20 positions from a game.


By the way, I did not received any mails since Ingo's mail(Mar 1 2019).

Erik reported in Feb 17 2019,
> It looks like gmail is broken again for this list. I never got Remi's

Remi also reported in Mar 24 2019. (I found this from archives.)
> I have just found out that the list is not sending emails to my free.fr

Thanks,
Hiroshi Yamashita