Historic Milestone: AlphaZero

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

Moderators: hgm, Harvey Williamson, bob

pferd
Posts: 92
Joined: Thu Jul 24, 2014 12:49 pm

Re: MCTS-NN vs alpha-beta

Post by pferd » Thu Dec 07, 2017 1:45 pm

MikeGL wrote:
Thanks for this line. Looks like your SF modded version finds the winning line played by AlphaZero correctly.
There is nothing special to this version. It contains just 2 small changes:
1) I removed the lazy eval.
2) I applied pull request #1289

I will give stockfish-master a try and see how things work out...

duncan
Posts: 6809
Joined: Mon Jul 07, 2008 8:50 pm

Re: Historic Milestone: AlphaZero

Post by duncan » Thu Dec 07, 2017 1:55 pm

Lyudmil Tsvetkov wrote:
duncan wrote:
maac wrote:https://arxiv.org/pdf/1712.01815.pdf

To say that i'm impressed is a understatement. Shocking.
Take note that SF was at 64 cores!
25 wins for white and only 3 wins for black. is such a big difference what you would expect ?
When I have been claiming, the stronger the engines, the more they score with white, everyone has been laughing.
At some point, there will be only 11111111111111111s.
but it is 'only' 100 elo stronger

pferd
Posts: 92
Joined: Thu Jul 24, 2014 12:49 pm

Re: MCTS-NN vs alpha-beta

Post by pferd » Thu Dec 07, 2017 2:42 pm

pferd wrote: I will give stockfish-master a try and see how things work out...

Code: Select all

info depth 49 seldepth 93 multipv 1 score cp 160 nodes 20247541053 nps 10265501 hashfull 999 tbhits 10770118 time 1972387 pv d3g6 e7g5 g4g5 f7g6 f4f5 h8g8 g5h6 e8f7 f5f6 d7d8 e3f3 g6g5 h4g5 g8g6 h6h4 g6g8 c2f2 b7c8 f3g4 c8d7 h4h5 g8g6 f2h2 f7g8 g4f4 d7e8 h5h7 e8f7 h7g8 g6g8 h2c2 g8h8 g5g6 f7g6 c2c6 g6f7 c6b6 d8c8 b6a6 c8b7 a6a5 h8h4 f4e3 h4h3 e3d2 f7g6 a5a6 h3d3 d2c2 d3d4 c2b3 d4d3 b3b4 d3d4 b4c5 d4c4 c5d6 d5d4 d6e6 d4d3 a6d6 c4c8 d6d7 b7b6
Master finds the key move too, but it has a slightly different pv which should be winning, too.

Milos
Posts: 2975
Joined: Wed Nov 25, 2009 12:47 am

Re: Historic Milestone: AlphaZero

Post by Milos » Thu Dec 07, 2017 3:49 pm

Werewolf wrote:1 GB hash allows them to say SF nps are really high while hiding that they’ve weakened its search.

I would like to see a rematch at a better time control, much more hash, all tablebases, and a tournament quality opening book and the latest asmfish.

I bet it’d be much closer then.
If you look at results of B40 Sicilian difference is only 38.5Elo.
With the lastest Brainfish using Cerebellum limited to for example 12 moves, 32GB hash, 6-men Syzygy and 60'+15'' TC I'm pretty confident Alpha0 would not win, at the best result would be indecisive.
If I had access to the training games, I could construct the book that would give SF +100 Elo advantage without much trouble.

Lion
Posts: 488
Joined: Fri Mar 31, 2006 11:26 am
Location: Switzerland

Re: Historic Milestone: AlphaZero

Post by Lion » Thu Dec 07, 2017 3:56 pm

While I understand why you would like to do that (so would I), I believe it will never happen.
This is surely not the original intend of the team that worked on AlphaZero.

They just proved that by letting an IA develop within a few hours it could get more than a match for a regular program on which several thousands of hours were spent....

Unfortunately, the proof is done and they will likely move to the next things. SF with opening book, this or that..... is most probably of little interest to them.

rgds

Jouni
Posts: 1782
Joined: Wed Mar 08, 2006 7:15 pm

Re: Historic Milestone: AlphaZero

Post by Jouni » Thu Dec 07, 2017 3:59 pm

Did this published paper give any estimate for perfect chess? One figure has 3500 limit or +100 from SF8. Are we near? Where is Kai, when we need him :) ?
Jouni

Lion
Posts: 488
Joined: Fri Mar 31, 2006 11:26 am
Location: Switzerland

Re: Historic Milestone: AlphaZero

Post by Lion » Thu Dec 07, 2017 4:00 pm

Why would they have a clue of what is perfect chess?

IanO
Posts: 449
Joined: Wed Mar 08, 2006 8:45 pm
Location: Portland, OR
Contact:

Re: Historic Milestone: AlphaZero

Post by IanO » Thu Dec 07, 2017 4:57 pm

corres wrote:2, Alpha Zero did not start from zero knowledge about chess
because it was [fed] a lot of human games at start up.
Where did you see that? My impression is the opposite, they explicitly did not use any prior human chess knowledge besides the basic rules, hence the "Zero" in AlphaZero.

Spliffjiffer
Posts: 117
Joined: Thu Aug 02, 2012 5:48 pm
Location: Germany

Re: Historic Milestone: AlphaZero

Post by Spliffjiffer » Thu Dec 07, 2017 5:13 pm

personally i have no doubt that the "4 hours thing" is the truth...and even if its 4 days, thats no difference imo....the fact, that that "process" manages to get to such a ultra-high level of playingstrengh is nothing other than revolutionary and thats simply a scary, very scary, fact that we are faced with :-(
Wahrheiten sind Illusionen von denen wir aber vergessen haben dass sie welche sind.

Albert Silver
Posts: 2741
Joined: Wed Mar 08, 2006 8:57 pm
Location: Rio de Janeiro, Brazil

Re: MCTS-NN vs alpha-beta

Post by Albert Silver » Thu Dec 07, 2017 5:34 pm

Rebel wrote:Can't believe it without a press release from Google.
They did more than that. They published a scientific paper anyone can read.

https://en.chessbase.com/post/the-futur ... arns-chess
"Tactics are the bricks and sticks that make up a game, but positional play is the architectural blueprint."

Post Reply