AlphaZero beats AlphaGo Zero, Stockfish, and Elmo

[zenpawn]

Seems to play a mean game of chess. The endgames is where it excels. Many games looked equal to the naked eye but Alpha went on to win. If this thing follows the Go project then expect in a few months a monster that will beat it's current version quite easily.

Well, in this case, they skipped straight to the technique that created that monster, i.e., self-play from the start rather than training with grandmaster games (hence the addition of Zero to its name).

[Eelco de Groot]

Seems to play a mean game of chess. The endgames is where it excels. Many games looked equal to the naked eye but Alpha went on to win. If this thing follows the Go project then expect in a few months a monster that will beat it's current version quite easily.

I am just looking at the first game where Alpha Zero wins with Black, but it seems to me that it excels specifically in showing big holes in Stockfish'eval That that is in the endgame is not a big surprise.

For instance this position from that game is lost, but even Kaissa needs a long time to see that and it knows a little bit about the power of the bishop pair, but apparently is still blind and this is after going backwards from about move 40...


[D]5bk1/r5p1/7p/2p1N3/4PP2/1P1P2Pb/2P4P/6RK w - -

Engine: Kaissa HT (512 MB)
by T. Romstad, M. Costalba, J. Kiiski, G. Linscott

23/34 0:01 -0.13 35.Rc1 g5 36.Kg1 Bg7 37.Kf2 Bxe5
38.fxe5 Kf7 39.Ke3 Ke6 40.Rb1 Kxe5
41.b4 Rb7 42.c3 Ke6 43.b5 Bg4 44.d4 c4
45.Rb4 Kd6 46.Rxc4 Rxb5 47.Rb4 Bd7
48.h4 (16.663.353) 11013

24/37 0:02 -0.08 35.Rc1 g5 36.Kg1 Bg7 37.Kf2 Bxe5
38.fxe5 Kf7 39.Ke3 Ke6 40.Rb1 Kxe5
41.b4 Rb7 42.c3 Ke6 43.b5 Bg4 44.d4 c4
45.Rb4 Kd6 46.Rxc4 Rxb5 47.Rb4 Bd7
48.h4 (23.026.784) 10991

25/47 0:02 -0.08 35.Rc1 g5 36.Kg1 Bg7 37.Kf2 Bxe5
38.fxe5 Kf7 39.Ke3 Ke6 40.Rb1 Kxe5
41.b4 Rb7 42.c3 h5 43.Ra1 cxb4
44.Ra6 Be6 45.d4+ Kf6 46.cxb4 Ke7
47.Ra5 Rxb4 48.Rxg5 (28.983.490) 10966

26/43 0:03 -0.08 35.Rc1 g5 36.Kg1 Bg7 37.Kf2 Bxe5
38.fxe5 Kf7 39.Ke3 Ke6 40.Rb1 Kxe5
41.b4 Rb7 42.c3 h5 43.Ra1 cxb4
44.Ra6 Be6 45.d4+ Kf6 46.cxb4 Ke7
47.Ra5 Rxb4 48.Rxg5 (35.577.502) 10866

27/42 0:03 -0.15-- 35.Rc1 g5 (36.923.800) 10847

27/42 0:03 -0.16 35.Rc1 g5 36.Kg1 Bg7 37.Kf2 Bxe5
38.fxe5 Kf7 39.Ke3 Ke6 40.Rb1 Kxe5
41.b4 Rb7 42.c3 Ke6 43.b5 Kd6 44.d4 Ra7
45.Kd3 Rf7 46.Ke3 Bg4 47.Kd3 Be6
48.d5 (37.708.832) 10807

28/34 0:04 -0.09++ 35.Rc1 (51.000.093) 10644

28/46 0:05 -0.19 35.Rc1 g5 36.Kg1 Bg7 37.Kf2 Bxe5
38.fxe5 Kf7 39.Ke3 Ke6 40.Rb1 Kxe5
41.b4 Rb7 42.c3 Ke6 43.b5 Ra7 44.d4 Kd6
45.Rb2 c4 46.e5+ Kd5 47.b6 Rb7
48.Rb5+ (53.393.487) 10653

29/48 0:06 -0.12++ 35.Rc1 (68.805.142) 10682

29/48 0:06 -0.23 35.Rc1 g5 36.Kg1 Bg7 37.Kf2 Bxe5
38.fxe5 Kf7 39.Ke3 Ke6 40.Rb1 Kxe5
41.b4 Rb7 42.c3 Ke6 43.b5 Ra7 44.d4 Kd6
45.Rb2 cxd4+ 46.Kxd4 Ra4+ 47.Rb4 Rxb4+
48.cxb4 (74.412.423) 10676

30/43 0:07 -0.16++ 35.Rc1 (82.421.949) 10673

30/46 0:08 -0.19 35.Rc1 g5 36.Kg1 Bg7 37.Kf2 Bxe5
38.fxe5 Kf7 39.Ke3 Ke6 40.Rb1 Kxe5
41.b4 Rb7 42.c3 Ke6 43.b5 Ra7 44.Rb2 Kd6
45.Rf2 Be6 46.b6 Rb7 47.Rf6 Rxb6
48.d4 (93.753.062) 10713

31/49 0:13 -0.12++ 35.Rc1 (139.848.293) 10743

31/49 0:23 -0.08 35.Rc1 Bd6 36.Nc4 Bc7 37.Kg1 Kf7
38.Kf2 Ra2 39.Ke3 Be6 40.e5 g6 41.d4 cxd4+
42.Kxd4 Ra8 43.Kc3 Rc8 44.Kd3 Rd8+
45.Kc3 Ra8 46.Kd4 Ke7 47.Kc3 Rc8
48.Kd3 (244.712.523) 10606
.
.
.
36/56 4:49 -1.11 35.Ng6 Bd6 36.Re1 Kf7 37.f5 Ra2
38.Rc1 c4 39.dxc4 Bc5 40.Nf4 Be3
41.Re1 Bxf4 42.gxf4 Rxc2 43.c5 Rxc5
44.Kg1 Bg4 45.Re3 Rb5 46.Rg3 Bd1
47.Rc3 Rb7 48.Kf2 (3.200.571.460) 11070
.
.
.
41/57 42:36 -1.62 35.Ng6 Bd6 36.Re1 Kf7 37.f5 Ra2
38.Rc1 c4 39.dxc4 h5 40.Nf4 Bg4
41.Kg2 Ba3 42.Rf1 Bc5 43.h3 Rxc2+
44.Kh1 Be2 45.Nxe2 Rxe2 46.Rd1 Rxe4
47.Rd7+ Kf6 48.Kg2 (28.571.692.284) 11175

42/53 43:11 -1.55++ 35.Ng6 (28.964.033.275) 11177

42/54 43:40 -1.57 35.Ng6 Bd6 36.Re1 Kf7 37.f5 Ra2
38.Rc1 c4 39.dxc4 h5 40.Nf4 Bg4
41.Kg2 Ba3 42.Rf1 Bc5 43.h3 Rxc2+
44.Kh1 Be2 45.Nxe2 Rxe2 46.Rd1 Rxe4
47.Rd7+ Kf6 48.Kg2 (29.291.863.573) 11179

43/58 44:39 -1.64-- 35.Ng6 Bd6 (29.972.203.243) 11186

43/64 58:05 -1.57++ 35.Nc4 (38.982.302.684) 11183

43/64 61:17 -1.45++ 35.Nc4 (41.056.108.916) 11164

43/67 65:26 -1.42 35.Nc4 g5 36.Rc1 Bg7 37.Ne5 Bxe5
38.fxe5 Kf7 39.Kg1 Ke6 40.Kf2 Kxe5
41.Ke3 Ra2 42.Kf3 Be6 43.Ke3 Rb2
44.h4 g4 45.b4 Rxb4 46.Ra1 Rb2
47.Kd2 Kd4 48.Ra8 (43.816.279.380) 11159

44/60 69:13 -1.50-- 35.Nc4 g5 (46.318.745.058) 11150

44/63 72:37 -1.57-- 35.Nc4 g5 (48.608.234.304) 11156

44/63 84:14 -1.69-- 35.Nc4 g5 (56.236.277.156) 11126

Lyudmil should appreciate that it is specifically playing Anti-Stockfish chess. Opponent modeling. If it would play against Lyudmil, in 4 hours it would not just beat him but show him where to improve his game. I think Chessbase would love to have a tool like this for sale.

I'm not sure the team is willing to pursue chess, I have not read much of the paper but I understood they are not interested in chess? After Deep Blue beat Kasparov it was no longer interesting to get stronger. And not much to learn from humans anymore...

[Leo]

Not 10-0.

Result: +28 =72 -0

Was it to inconvenient to download the latest SF? You could also beef SF up with the cerebellum book. I don't trust these Google people at all. They spend way to much time saying what great things they are doing for humanity. Pride comes before the fall.

[jhellis3]

Lol, it wouldn't have mattered at all.

Though perhaps a better example would have been to train it for crazyhouse. SF is nearing 4000 "Elo" there, and the games are almost all decisive, so it would have been able to demonstrate its superiority much more clearly.

[Ras]

Was it to inconvenient to download the latest SF?

Because it isn't an official release and has not been tested as exhaustively. That's the point of releases. Just take a look at the TCEC what happened to Komodo when going with a dev version.

Besides, the release has been rated in many games while the "dev version of today" has not.

[pilgrimdan]

I agree with you.
Also what people who claim the HW was much faster..... what they don’t understand is that the thing learned from itself in a very short time!

What if we now give it 1 Year to further learn?


Side note, I looked at the games and they are really impressive!

I would not be surprised, if in a year's time it also starts speaking and thinking of itself.
I, Robot.

there may be a fine line
between self-learning
and self-consciousness ...

[Milos]

Was it to inconvenient to download the latest SF?

Because it isn't an official release and has not been tested as exhaustively. That's the point of releases. Just take a look at the TCEC what happened to Komodo when going with a dev version.

Besides, the release has been rated in many games while the "dev version of today" has not.

Oh so Google ppl actually cared that SF dev doesn't show some weakness due to it no being tested so they've chosen well tested version???
I guess that has something to do with Saint Nicholas Day today, I mean believing in Santa, etc.

[jhellis3]

So $100 US ok?

[IanO]

Speaking of which, I saw no mention of endgame tablebases used for either opponent. Anyone know if Stockfish had those available?

It would be interesting to see how well AlphaZero's endgame knowledge matches that of the endgame tablebases. If it performs well, it might actually be a smaller and more robust implementation of the same knowledge.

[Leo]

Lol, it wouldn't have mattered at all.

Though perhaps a better example would have been to train it for crazyhouse. SF is nearing 4000 "Elo" there, and the games are almost all decisive, so it would have been able to demonstrate its superiority much more clearly.

It would have mattered. It could have drawn more games. The score would have been different.