Historic Milestone: AlphaZero

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

Moderators: hgm, Rebel, chrisw

MikeGL
Posts: 1010
Joined: Thu Sep 01, 2011 2:49 pm

Re: Historic Milestone: AlphaZero

Post by MikeGL »

MikeB wrote:
MikeGL wrote:Q is forcibly trapped starting with exchange sac Rxc5 by AlphaZero.

I wonder why RxN is not even in the radar of SF8 while searching.
Play is almost perfect chess, IMO.

RxN!! Which engine can find this in infinite mode?
[D]3r2kq/p2prp1p/1p4pP/2nR4/1Q6/1B3RP1/P4PK1/8 w - - 4 47

...[snip]
latest dev-SF-McB - sometimes it goes back and forth with Qh4 , which appress to transpose to the Rxc5 line, with longer searches , score tends to go down to hover around 1.00 ...

Code: Select all

dep	score	nodes	time	(not shown:  tbhits	knps	seldep)
 38	+1.26?	945.9M	0:43.48	Rxc5 bxc5? 
 38	+1.37?	924.0M	0:42.48	Rxc5 bxc5? 
 38	+1.45?	920.7M	0:42.34	Rxc5 bxc5? 
 37	+1.52 	846.2M	0:39.01	Rxc5 bxc5 Qh4 Rde8 Rf6 Kf8 Qf4 Qg8 Qc7 c4 Qxc4 Rd8 g4 Ke8 Qd4 Qf8 g5 Re6 Rf3 Re7 Bc4 Re6 Bd5 a6 Bb3 Qd6 Qh8+ Qf8 Qxh7 d5 Qg7 Qxg7 hxg7 Ke7 Bxd5 a5 Bxe6 Kxe6 Rf6+ Ke7 Ra6 Rg8 f4 Rxg7 Rxa5 Rg8 Ra7+ Ke6 Ra6+ Ke7 a4 Rc8 Kf3 Rc3+ Kg 
 36	+1.42 	783.6M	0:36.14	Rxc5 bxc5 Qh4 Rde8 Rf6 Kf8 Qf4 Qg8 Qc7 c4 Qxc4 Rd8 g4 Ke8 Qd4 Qf8 g5 Re6 Rf3 Qe7 Qh8+ Qf8 Qxh7 d5 Qg7 Qxg7 hxg7 Ke7 Bxd5 Rg8 Bxe6 Kxe6 Rf6+ Ke7 Ra6 Rxg7 f4 Rg8 Rxa7+ Ke6 Ra6+ Ke7 a4 Rd8 a5 Rd3 Rf6 Ra3 a6 Ke8 Kf2 Kd8 Ke2 Ke7 Rb6 
 36	+1.40!	683.5M	0:31.62	Rxc5! 
 36	+1.28?	648.2M	0:30.02	Rxc5 bxc5? 
 35	+1.35 	615.2M	0:28.53	Rxc5 bxc5 Qh4 Rde8 Rf6 Kf8 Qf4 Qg8 Qc7 c4 Qxc4 Rd8 g4 Ke8 Qd4 Qf8 g5 Re6 Rf3 Qe7 Qh8+ Qf8 Qxh7 d5 Qg7 Qxg7 hxg7 Ke7 Bxd5 Rg8 Bxe6 Kxe6 Rf6+ Ke7 Ra6 Rxg7 Rxa7+ Ke6 f4 Rg8 Ra6+ Kd5 a4 Rd8 Kf3 Rd7 Rf6 Kc5 a5 Re7 a6 Kb5 
 34	+1.32 	547.0M	0:25.51	Rxc5 bxc5 Qh4 Rde8 Rf6 Kf8 Qf4 c4 Bxc4 Qg8 g4 Rd8 Qd4 Ke8 g5 Qf8 Bb3 Re6 Rf3 Qe7 Qh8+ Qf8 Qxh7 d5 Qg7 Qxg7 hxg7 Ke7 Bxd5 Rg8 Bxe6 Kxe6 Rf6+ Ke7 Ra6 Rxg7 Rxa7+ Ke6 f4 Rg8 Ra6+ Kd5 a4 Rd8 Kf3 Rd7 Rf6 Kc5 a5 Re7 Kg4 
 34	+1.33?	540.4M	0:25.23	Rxc5 bxc5? 
 33	+1.40 	534.1M	0:24.94	Rxc5 bxc5 Qh4 Rde8 Rf6 Kf8 Qf4 c4 Bxc4 Qg8 g4 Rd8 Qd4 Ke8 g5 Qf8 Bb3 Re6 Rf3 Qe7 Qh8+ Qf8 Qxh7 d5 Qg7 Qxg7 hxg7 Ke7 Bxd5 Rg8 Bxe6 Kxe6 Rf6+ Ke7 Ra6 Rxg7 a4 Rg8 Rxa7+ Ke6 a5 Rc8 f4 Rc3 Ra6+ Ke7 Rf6 Ra3 a6 Ke8 Rb6 Ke7 Kf2 
 32	+1.33 	437.9M	0:20.62	Rxc5 bxc5 Qh4 Rde8 Rf6 Kf8 Qf4 Qg8 Qc7 c4 Qxc4 Rd8 g4 Ke8 Qd4 Qf8 g5 a5 Rf3 Rc8 Ba4 Rd8 Rc3 Re6 Bxd7+ Rxd7 Rc8+ Ke7 Qxd7+ Kxd7 Rxf8 Re7 Ra8 Kd6 Rxa5 Ke6 Kf3 Rd7 Kg4 f5+ Kf4 Rb7 Ke3 Kd6 Kd4 Kc6 Ra6+ Kb5 
 32	+1.32!	398.2M	0:18.80	Rxc5! 
 32	+1.20?	374.2M	0:17.68	Rxc5 bxc5? 
 31	+1.27 	365.9M	0:17.30	Rxc5 bxc5 Qh4 Rde8 Rf6 Kf8 Qf4 c4 Bxc4 Qg8 g4 Rd8 Bb3 Ke8 Qd4 Qf8 g5 Re6 Rf3 Re7 Qc5 Re6 Qc3 Re7 Bd5 Re6 Qd4 a6 Bb3 Ke7 Qb4+ Ke8 Qc3 Ke7 Bd5 Ke8 Qd4 Ke7 Qa4 
 31	+1.24!	353.9M	0:16.76	Rxc5! 
 30	+1.10 	322.1M	0:15.34	Rxc5 bxc5 Qh4 Rde8 Rf6 Kf8 Qf4 c4 Bxc4 Qg8 Qd6 Rc8 Bxf7 Qxf7 Rxf7+ Kxf7 Qd5+ Kf8 Qb7 Rc6 Qxa7 g5 Qa5 Rg6 a4 Ke8 Qa8+ Kf7 a5 Ree6 Qc8 Rd6 a6 Rxa6 Qxd7+ Kf8 Qxh7 Rae6 Qc7 Rxh6 Qd8+ Kg7 Qxg5+ Rhg6 Qf4 Rgf6 Qc4 
 29	+1.13 	305.5M	0:14.60	Qh4 Rde8 Rxc5 bxc5 Rf6 Kf8 Qf4 c4 Bxc4 Qg8 Qd6 Rc8 Bxf7 Qxf7 Rxf7+ Kxf7 Qd5+ Kf8 Qd4 Kf7 Qxa7 d5 Qd4 Rd7 a4 Rc4 Qh8 Ke6 a5 Rc6 Qd4 Ra6 f4 Kf7 Qg7+ Ke6 Qc3 Rda7 Qe5+ Kf7 Qxd5+ Ke7 Qe5+ Kf7 Qh8 Ke6 Qe8+ Kf6 g4 Rxa5 
 29	+1.04!	290.6M	0:13.93	Qh4! 
 28	+0.91 	283.3M	0:13.60	Qh4 Rde8 Rxc5 bxc5 Rf6 Kf8 Qf4 c4 Bxc4 Qg8 Qd6 Rc8 Bxf7 Qxf7 Rxf7+ Kxf7 Qd5+ Kf8 Qd4 Kf7 Qxa7 d5 Qd4 Rd7 a4 Rc4 Qh8 Ke6 Qg8+ Kd6 a5 Kc7 Kf3 Rc6 Qa8 Kd6 Qf8+ Ke6 Qa3 Rf7+ Kg4 d4 Qb3+ Ke7 
 28	+0.92!	237.5M	0:11.50	Qh4! 
 28	+0.63!	221.4M	0:10.76	Qh4! 
 28	+0.42!	219.3M	0:10.65	Qh4! 
 28	+0.26!	213.5M	0:10.38	Qh4! 
 28	+0.15!	213.0M	0:10.35	Qh4! 
 28	+0.07!	211.6M	0:10.29	Qh4! 
 27	  0.00 	99.7M  	0:04.92	Rd6 Qe5 Rd5 Qa1 Rd1 Qe5 Rd5 
 26	  0.00 	80.1M  	0:03.96	Rd6 Qe5 Rd5 Qh8 Rd6 
 25	  0.00 	53.0M  	0:02.64	Rd6 Qe5 Rd5 Qh8 Rd6 
 24	  0.00 	43.1M  	0:02.18	Rd6 Qe5 Rd5 Qh8 Rd6 
 23	  0.00 	25.0M  	0:01.31	Rd6 Qe5 Rd5 Qh8 Rd6 
 22	  0.00 	9.80M  	0:00.52	Rd6 Qa1 Rd1 Qe5 Rd5 Qh8 Rd6 
 21	  0.00 	7.63M  	0:00.40	Rd6 Qa1 Rd1 Qe5 Rd5 Qh8 Rd6 
 20	  0.00 	6.35M  	0:00.34	Rd6 Qe5 Rd5 Qh8 Rd6 
 19	  0.00 	5.16M  	0:00.28	Rd6 Qe5 Rd5 Qh8 Rd6 
 18	  0.00 	3.67M  	0:00.20	Rd6 Qe5 Rd5 Qh8 Rd1 Qe5 Rd5 
 17	  0.00 	3.03M  	0:00.16	Rd6 Qa1 Rd1 Qe5 Rd5 Qh8 Rd6 
 16	  0.00 	1.71M  	0:00.10	Rd6 Qe5 Rd5 Qh8 Rd6 
 15	  0.00 	1.40M  	0:00.08	Rd6 Qe5 Rd5 Qh8 Rd6 
Thanks for the PV by latest SF-McBrain dev version. I would grab a copy once you release that version ;)


regards,
KWRegan
Posts: 18
Joined: Wed Aug 19, 2015 9:06 pm

Re: Much weaker than Stockfish

Post by KWRegan »

Lyudmil Tsvetkov wrote:Why don't they disclose what their evaluation is: that will be a big step towards knowing the truth.
They can't. The evaluation is a sequence of numbers specifying myriad weights on umpteen-dozen layers of a neural network. This aspect (of the original AlphaGo) in contrast to Stockfish is addressed in my Feb. 2016 article https://rjlipton.wordpress.com/2016/02/07/magic-to-do/ That this is endemic to "deep learning" has energized a counter-push toward "Explainable AI."


What I wish to know better, incidentally, is the memory footprint of their trained network and how portable it is.
User avatar
M ANSARI
Posts: 3707
Joined: Thu Mar 16, 2006 7:10 pm

Re: Much weaker than Stockfish

Post by M ANSARI »

Some of the games are really remarkable. I think a PC can be configured to play in a similar fashion. Maybe massive GPU floating point calculations can actually work for chess ... just needs a different approach. I always thought that a chess engine that can use a Monte Carlo based GPU as a partner would be a very powerful thing. Especially in avoiding locked positions where the horizon effect hurts traditional engines in identifying fortress positions. This really is a game changer, although I would want to know how the hardware stacks up. Hard to tell if we are comparing hardware of similar strength. But some of the positions it seems that even very powerful hardware cannot find the moves on a normal chess engine given enough time to equalize the hardware. Need more information on this but it does look like a major breakthrough.
Dirt
Posts: 2851
Joined: Wed Mar 08, 2006 10:01 pm
Location: Irvine, CA, USA

Re: Historic Milestone: AlphaZero

Post by Dirt »

I doubt that Google wants to be in the chess playing, or go playing or shogi playing business. I wonder what their goal is?

One possibility is self-driving cars, although they have competition there. Natural language recognition, and possibly translation, is also interesting. Maybe civil engineering?
Deasil is the right way to go.
MikeGL
Posts: 1010
Joined: Thu Sep 01, 2011 2:49 pm

Re: Historic Milestone: AlphaZero

Post by MikeGL »

Dirt wrote:I doubt that Google wants to be in the chess playing, or go playing or shogi playing business. I wonder what their goal is?

One possibility is self-driving cars, although they have competition there. Natural language recognition, and possibly translation, is also interesting. Maybe civil engineering?
I think this type of AI is generic, can be applied in StarCraft/WarCraft online to win against humans,
or other similarly sophisticated games. Could predict stockmarket fluctuations more accurately.
Could help in very complex real wars involving jet fighters, submarines and aircraft carriers too.
MikeGL
Posts: 1010
Joined: Thu Sep 01, 2011 2:49 pm

Re: MCTS-NN vs alpha-beta

Post by MikeGL »

kranium wrote:
Lyudmil Tsvetkov wrote:It is not at all clear to me where were books used and where not.
I'm sure opening books were not used...
In the early self-play games things like 1.a3, 1.a4, etc. were probably tried by AlphaZero...
eventually it learned that 1. e4 or 1. d4 had the highest success rates.
Books or no books, I think AlphaZero would still demolish SF8.
Just look at this game 9, it was a decent French Defence by SF8, but it was dismantled with
amazing tactical and strategic shots by AlphaZero which seems to be beyond the reach of alpha-beta engines.

[pgn]
[Event "?"]
[Site "?"]
[Date "2017.12.06"]
[Round "9"]
[White "AlphaZero"]
[Black "Stockfish"]
[Result "1-0"]
[TimeControl "40/1260:300"]
[Termination "normal"]
[PlyCount "103"]
[WhiteType "human"]
[BlackType "human"]

1. d4 e6 2. e4 d5 3. Nc3 Nf6 4. e5 Nfd7 5. f4 c5 6. Nf3 cxd4 7. Nb5 Bb4+ 8.
Bd2 Bc5 9. b4 Be7 10. Nbxd4 Nc6 11. c3 a5 12. b5 Nxd4 13. cxd4 Nb6 14. a4
Nc4 15. Bd3 Nxd2 16. Kxd2 Bd7 17. Ke3 b6 18. g4 h5 19. Qg1 hxg4 20. Qxg4
Bf8 21. h4 Qe7 22. Rhc1 g6 23. Rc2 Kd8 24. Rac1 Qe8 25. Rc7 Rc8 26. Rxc8+
Bxc8 27. Rc6 Bb7 28. Rc2 Kd7 29. Ng5 Be7 30. Bxg6 Bxg5 31. Qxg5 fxg6 32. f5
Rg8 33. Qh6 Qf7 34. f6 Kd8 35. Kd2 Kd7 36. Rc1 Kd8 37. Qe3 Qf8 38. Qc3 Qb4
39. Qxb4 axb4 40. Rg1 b3 41. Kc3 Bc8 42. Kxb3 Bd7 43. Kb4 Be8 44. Ra1 Kc7
45. a5 Bd7 46. axb6+ Kxb6 47. Ra6+ Kb7 48. Kc5 Rd8 49. Ra2 Rc8+ 50. Kd6 Be8
51. Ke7 g5 52. hxg5 1-0
[/pgn]

not sure if 18.g4!, 30.Bxg6! and other would be found by current engines.

[d]r2qk2r/3bbppp/1p2p3/pP1pP3/P2P1P2/3BKN2/6PP/R2Q3R w kq - 0 18
After 17...b6 of black, can some engine consider 18.g4! in this position?



xxxxxxxxxxxxxxxxxxxxxxxxxxxxx
[d]4q2r/1b1kbp2/1p2p1p1/pP1pP1N1/P2P1PQP/3BK3/2R5/8 w - - 6 30
After 29...Be7, can current engines consider 30.Bxg6! here?


Would be nice if we can try to feed some difficult epd positions into AlphaZero,
to estimate its ELO strength.
User avatar
lantonov
Posts: 216
Joined: Sun Apr 13, 2014 5:19 pm

Re: MCTS-NN vs alpha-beta

Post by lantonov »

MikeGL wrote: [d]4q2r/1b1kbp2/1p2p1p1/pP1pP1N1/P2P1PQP/3BK3/2R5/8 w - - 6 30
After 29...Be7, can current engines consider 30.Bxg6! here?
For the second position SF-dev considers an N sac instead of B sac and finds nothing better than a draw. It's interesting that it finds Bxg6 on the very first ply but immediately rejects it

Code: Select all

  40	  0.00 	723.3M	14:37.16	Nxe6 fxe6 Bxg6 Qf8 h5 Ba3 Kf3 Qb4 Bf5 Re8 Qg7+ Re7 Bxe6+ Kxe6 Rc6+ Bxc6 Qf6+ Kd7 Qxc6+ Kd8 Qa8+ Kc7 Qa7+ Kc8 Qa8+ Kd7 Qc6+
 39	  0.00 	539.2M	10:47.12	Nxe6 fxe6 Bxg6 Qf8 h5 Ba3 Kf3 Qb4 Bf5 Re8 Qg7+ Re7 Bxe6+ Kxe6 Rc6+ Bxc6 Qf6+ Kd7 Qxc6+ Kd8 Qa8+ Kc7 Qa7+ Kc8 Qa8+ Kd7 Qc6+
 38	  0.00 	411.4M	7:49.51	Nxe6 fxe6 Bxg6 Qf8 h5 Ba3 Kf3 Qb4 Bf5 Re8 Qg7+ Re7 Bxe6+ Kxe6 Rc6+ Bxc6 Qf6+ Kd7 Qxc6+ Kd8 Qa8+ Kc7 Qa7+ Kc8 Qa8+ Kd7 Qc6+
 37	  0.00 	348.2M	6:30.79	Nxe6 fxe6 Bxg6 Qf8 h5 Ba3 Kf3 Qb4 Bf5 Re8 Qg7+ Re7 Bxe6+ Kxe6 Rc6+ Bxc6 Qf6+ Kd7 Qxc6+ Kd8 Qa8+ Kc7 Qa7+ Kc8 Qa8+ Kd7 Qc6+
 36	  0.00 	260.7M	4:52.26	Nxe6 fxe6 Bxg6 Qf8 h5 Ba3 Kf3 Qb4 Bf5 Re8 Qg7+ Re7 Bxe6+ Kxe6 Rc6+ Bxc6 Qf6+ Kd7 Qxc6+ Kd8 Qa8+ Kc7 Qa7+ Kc8 Qa8+ Kd7 Qc6+
 35	  0.00 	220.9M	4:09.16	Nxe6 fxe6 Bxg6 Qf8 h5 Ba3 Kf3 Qb4 Bf5 Re8 Qg7+ Re7 Bxe6+ Kxe6 Rc6+ Bxc6 Qf6+ Kd7 Qxc6+ Kd8 Qa8+ Kc7 Qa7+ Kc8 Qa8+ Kd7 Qc6+
 34	  0.00 	159.4M	3:00.63	Nxe6 fxe6 Bxg6 Qf8 h5 Ba3 Kf3 Qb4 Bf5 Re8 Qg7+ Re7 Bxe6+ Kxe6 Rc6+ Bxc6 Qf6+ Kd7 Qxc6+ Kd8 Qa8+ Kc7 Qa7+ Kc8 Qa8+ Kd7 Qc6+
 33	  0.00 	129.3M	2:24.57	Nxe6 fxe6 Bxg6 Qf8 h5 Ba3 Kf3 Qb4 Bf5 Re8 Qg7+ Re7 Bxe6+ Kxe6 Rc6+ Bxc6 Qf6+ Kd7 Qxc6+ Kd8 Qa8+ Kc7 Qa7+ Kc8 Qa8+ Kd7 Qc6+
 32	  0.00 	105.5M	1:57.98	Nxe6 fxe6 Bxg6 Qf8 h5 Ba3 Kf3 Qb4 Bf5 Re8 Qg7+ Re7 Bxe6+ Kxe6 Rc6+ Bxc6 Qf6+ Kd7 Qxc6+ Kd8 Qa8+ Kc7 Qa7+ Kc8 Qa8+ Kd7 Qc6+
 31	  0.00 	96.5M  	1:47.70	Nxe6 fxe6 Bxg6 Qf8 h5 Ba3 Kf3 Qb4 Bf5 Re8 Qg7+ Re7 Bxe6+ Kxe6 Rc6+ Bxc6 Qf6+ Kd7 Qxc6+ Kd8 Qa8+ Kc7 Qa7+ Kc8 Qa8+ Kd7 Qc6+
 30	  0.00 	69.1M  	1:17.59	Nxe6 fxe6 Bxg6 Qf8 h5 Ba3 f5 exf5 Bxf5+ Kd8 Ke2 Qf7 Bg6 Qe7 Bf5 Qf7
 29	  0.00 	61.1M  	1:08.41	Nxe6 fxe6 Bxg6 Qf8 h5 Ba3 f5 exf5 Bxf5+ Kd8 Ke2 Qf7 Bg6 Qe7 Bf5 Qf7
 28	  0.00 	49.5M  	0:55.47	Nxe6 fxe6 Bxg6 Qf8 h5 Ba3 f5 exf5 Bxf5+ Kd8 Ke2 Qf7 Bg6 Qe7 Bf5 Qf7
 28	+0.13?	45.2M  	0:50.72	Nxe6 fxe6?
 28	+0.42?	39.5M  	0:44.19	Nxe6 fxe6?
 28	+0.64?	35.6M  	0:39.84	Nxe6 fxe6?
 28	+0.80?	34.0M  	0:38.03	Nxe6 fxe6?
 28	+0.91?	31.6M  	0:35.39	Nxe6 fxe6?
 28	+1.06!	31.1M  	0:34.81	Nxe6!
 27	+0.98!	24.1M  	0:27.16	Nxe6!
 27	+0.77!	21.1M  	0:23.87	Nxe6!
 27	+0.61!	20.0M  	0:22.76	Nxe6!
 27	+0.50!	19.4M  	0:22.05	Nxe6!
 27	+0.42!	18.5M  	0:21.06	Nxe6!
 26	+0.35 	17.1M  	0:19.59	Nxe6 fxe6 Bxg6 Qf8 h5 Rg8 Ke2 Qg7 f5 Qh6 Kf3 Rc8 fxe6+ Kd8 Qf4 Qxf4+ Kxf4 Rc4 Rxc4 dxc4 h6 Bf8 Kg5 Ke7 Bf5 c3 Kg6 Bxh6 Kxh6 Bd5 Bc2 Kxe6 Kg5 Bc4 Kf4 Kd5
 26	+0.72!	16.9M  	0:19.27	Nxe6!
 26	+0.56!	16.2M  	0:18.54	Nxe6!
 26	+0.45!	15.4M  	0:17.68	Nxe6!
 26	+0.37!	14.7M  	0:16.89	Nxe6!
 25	+0.30 	12.3M  	0:14.25	Nxe6 fxe6 Bxg6 Qf8 h5 Rg8 Ke2 Qg7 f5 Qh6 Kf3 Rc8 fxe6+ Kd8 Qf4 Qg7 Qf7 Qxf7+ exf7 Rxc2 Bxc2 Bf8 Kg4 Ke7 Kg5 Kxf7 Bg6+ Ke7 h6 Bc8 Bh5 Be6 h7 Bg7 Kg6
 25	+0.35?	11.6M  	0:13.58	Nxe6 fxe6?
 25	+0.60!	10.8M  	0:12.66	Nxe6!
 25	+0.51?	10.6M  	0:12.39	Nxe6 fxe6?
 25	+0.62?	10.4M  	0:12.22	Nxe6 fxe6?
 25	+0.70?	10.3M  	0:12.05	Nxe6 fxe6?
 24	+0.77 	9.67M  	0:11.37	Nxe6 fxe6 Bxg6 Qf8 h5 Bb4 Kf3 Be7 Ke2 Rg8 f5 Qh6 Kf3 Rf8 f6 Bb4 Bd3 Kd8 Qg6 Bd2 Qxh6 Bxh6 Rg2 Rh8 Rg6 Ke8 Rg7 Bxg7 fxg7 Rg8 h6 Kf7 h7 Kxg7 hxg8=Q+ Kxg8 Kf4
 24	+0.72!	7.58M  	0:09.01	Nxe6!
 24	+0.51!	6.74M  	0:08.09	Nxe6!
 24	+0.35!	5.94M  	0:07.22	Nxe6!
 24	+0.24!	5.77M  	0:07.06	Nxe6!
 24	+0.16!	5.72M  	0:07.00	Nxe6!
 23	+0.09 	5.49M  	0:06.78	Nxe6 fxe6 Bxg6 Qf8 h5 Bb4 Kf3 Qh6 f5 Rc8 fxe6+ Kd8 Rxc8+ Bxc8 Bf5 Kc7 e7 Bxf5 e8=Q Bxg4+ Kxg4 Bd2 Qe7+ Kc8 Qf6 Kd7 Qf7+ Kd8 Kf5 Be3 Qf6+ Kd7 Qxh6 Bxh6
 23	+0.15!	5.20M  	0:06.39	Nxe6!
 23	+0.07!	5.04M  	0:06.22	Nxe6!
 22	  0.00 	4.73M  	0:05.88	Nxe6 fxe6 Bxg6 Qf8 h5 Bb4 Kf3 Qh6 f5 Rc8 fxe6+ Kd8 Rxc8+ Bxc8 Bf5 Kc7 e7 Bxf5 e8=Q Bxg4+ Kxg4 Bd2 Qe7+ Kc8 Qf6 Kd7 e6+ Kd6 Qe5+ Ke7 Qc7+ Kxe6 Qxb6+ Kd7 Qb7+ Ke8 Qb8+ Ke7 Qe5+ Kf8 Qb8+ Kg7 Qb7+ Kf8 Qb8+
 21	  0.00 	4.40M  	0:05.47	Nxe6 fxe6 Bxg6 Qf8 h5 Bb4 Kf3 Qh6 f5 Rc8 fxe6+ Kd8 Rxc8+ Bxc8 Bf5 Kc7 e7 Bxf5 e8=Q Bxg4+ Kxg4 Bd2 Qe7+ Kc8 Qf6 Kd7 e6+ Kd6 Qe5+ Ke7 Qc7+ Kxe6 Qxb6+ Kd7 Qb7+ Ke8 Qb8+ Ke7 Qe5+ Kf8 Qb8+ Kg7 Qb7+ Kf8 Qb8+
 21	+0.12?	4.20M  	0:05.22	Nxe6 fxe6?
 21	+0.24?	3.96M  	0:04.94	Nxe6 fxe6?
 21	+0.31?	3.81M  	0:04.76	Nxe6 fxe6?
 20	+0.39 	3.51M  	0:04.39	Nxe6 fxe6 Bxg6 Qf8 h5 Bb4 Kf3 Qh6 f5 Rc8 fxe6+ Kd8 Rxc8+ Bxc8 Qh4+ Be7 Qf4 Qxf4+ Kxf4 Bf8 Kf5 Ke7 Kg5 Bxe6 h6 Bh3 Bh5 Ke6 h7 Bg7 Kg6
 20	+0.52!	3.16M  	0:03.93	Nxe6!
 20	+0.27?	2.99M  	0:03.71	Nxe6 fxe6?
 20	+0.61!	2.67M  	0:03.33	Nxe6!
 20	+0.50!	2.55M  	0:03.13	Nxe6!
 19	+0.35 	2.04M  	0:02.55	Nxe6 fxe6 Bxg6 Qf8 h5 Bb4 Kf3 Qh6 f5 Rf8 Qf4 Qxf4+ Kxf4 Rc8 Rg2 Rh8 fxe6+ Kxe6 Bf5+ Kf7 Rg6 Bd2+ Kg4 Bc8 Bxc8 Rxc8 Rxb6 Rc4 Kf5 Rxa4 Rb7+ Ke8
 18	  0.00 	1.69M  	0:02.14	Nxe6 fxe6 Bxg6 Qf8 h5 Bb4 Kf3 Qh6 f5 Rf8 Qf4 Qxf4+ Kxf4 Rc8 Rxc8 Bd2+ Kf3 Bxc8 f6 Bb7 Ke2 Bf4 Kf3 Bg5 Ke2 Bh6
 17	  0.00 	1.27M  	0:01.64	Rh2 Rh6 Rh1 Ba3 f5 gxf5 Bxf5 exf5 Qxf5+ Kc7 Nxf7 Re6 Ng5 Rh6 Nf7
 16	  0.00 	554153	0:00.75	Rh2 Ba3 Rc2 Be7 Rh2
 15	  0.00 	506281	0:00.67	Rh2 Ba3 Rc2 Be7 Rh2
 14	  0.00 	473867	0:00.64	Rh2 Ba3 Rc2 Be7 Rh2
 13	  0.00 	441835	0:00.59	Rh2 Bd8 Qe2 Be7 Qg4
 12	  0.00 	98223  	0:00.16	Rc3 Qf8 Rc1 Bd8 Ke2 Qa3 Rc2 Qf8 Rc1
 11	  0.00 	82113  	0:00.13	Rc3 Qf8 Rc1 Bd8 Ke2 Qa3 Rc2 Qf8 Rc1
 10	  0.00 	78428  	0:00.13	Rc3 Qf8 Rc1 Bd8 Ke2 Qa3 Rc2 Qf8 Rc1
  9	  0.00 	23103  	0:00.03	Kf2 Qf8 Nf3 Ke8 Ng5 Kd7
  8	+0.12 	11936  	0:00.02	f5 gxf5 Bxf5 Qg8 Bd3 Qf8 Qf4 Ke8
  7	+0.35 	10001  	0:00.02	f5 Bxg5+ Qxg5 gxf5 Kf4 Qf8 Kg3
  6	+0.87 	2378    	0:00.01	Bf1 Bxg5 fxg5 Qe7 Bd3 Rc8
  5	+1.92 	447      	0:00.00	Bf1 Bd8 Bh3 Bxg5 Qxg5
  4	+1.92 	367      	0:00.00	Bf1 Bd8 Bh3 Bxg5 Qxg5
  3	+2.15 	201      	0:00.00	Nf3 g5 Nxg5
  2	+2.15 	152      	0:00.00	Nf3 g5 Nxg5
  1	+1.40 	55        	0:00.00	Bxg6
  0	#

User avatar
Rebel
Posts: 6991
Joined: Thu Aug 18, 2011 12:04 pm

Re: MCTS-NN vs alpha-beta

Post by Rebel »

Can't believe it without a press release from Google.
corres
Posts: 3657
Joined: Wed Nov 18, 2015 11:41 am
Location: hungary

Re: Historic Milestone: AlphaZero

Post by corres »

[quote="maac"]

Take note that SF was at 64 cores!

[/quote]

Another VERY IMPORTANT notes:
1, SF used only 1 GB (!!) hash table
2, Alpha Zero did not start from zero knowledge about chess
because it was feeded a lot of human games at start up.
This is the explanation why Alpha Zero plays openings so human like.
I think it would be more correct if Stockfish would get 64 GB hash
and a good human opening book like Fritz Power Book.
duncan
Posts: 12038
Joined: Mon Jul 07, 2008 10:50 pm

Re: Historic Milestone: AlphaZero

Post by duncan »

JJJ wrote:ALphaZero did win Stockfish in 100 game scored 64/100 that is 98 elo stronger than Stockfish TCEC 2016. Not bad ! I d like to see it more trained to see how far from perfect Stockfish really is !
and it did this after just 4 hours training. ? not sure why they did not train for at least a week to get an even better result.