Historic Milestone: AlphaZero

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

Moderators: hgm, Harvey Williamson, bob

User avatar
MikeGL
Posts: 693
Joined: Thu Sep 01, 2011 12:49 pm

Re: Much weaker than Stockfish

Post by MikeGL » Thu Dec 07, 2017 2:18 am

Lyudmil Tsvetkov wrote:
MikeGL wrote:
Lyudmil Tsvetkov wrote:
MikeGL wrote:
Lyudmil Tsvetkov wrote:The training matches are different from the 100 games match with Stockfish.
Yes, the plot on the diagram is the training game, but 100 games per openning was played. 50-50, and the score below the diagram is on AlphaZero perspective.
12 openings with reversed colours don't square in any way with 100 played games, so did they actually left some openings played more than others, or did not they flip colours?
12 opennings x 100 = 1,200 games total.
Before we were talking about 300 and 100, now 1200 suddenly appears...
The 64/36 score certainly comes from 100 games, unless they assigned random points for a win.
And in that sample, I see Alpha playing just 1.d4 and 1.Nf3.
Read the series of posts properly. It is 100 games per openning, you clearly don't understand Table 2.

300 games because you were talking about 1.e4 earlier which appears in 6 diagrams.
How many is 50 x 6 ?
You were claiming that AlphaZero didn't play 1.e4, i told you it did! 300 times it did play 1.e4 against SF8.

See the total summation below: 1,200 games for all 12 opennings. Come on man, even this very
basic stuff we argue?
Do you have the pgn for the training games, which, btw., are claimed to run into the thousands?
Note that all Training games are self-play (no SF8 involved). The 1,200 are all match games against SF8.
No data given in PDF about the total number of self-play for learning, neither were the self-play PGN published. Only SF8 match was published.
100 game match versus SF8 was played on all 12 common ECO openings.
I guess you are confused of the plotted graph being put beside the
diagram. The graph is self-play, the diagram is SF8 match.
Try to read the caption of Table 2 properly. 37 times if need be.

User avatar
MikeB
Posts: 2505
Joined: Thu Mar 09, 2006 5:34 am
Location: Pen Argyl, Pennsylvania

Re: Historic Milestone: AlphaZero

Post by MikeB » Thu Dec 07, 2017 2:36 am

JJJ wrote:Game 5 :
White:
AlphaZero
Black:
Stockfish

[pgn]1. d4 Nf6 2. c4 e6 3. Nf3 b6 4. g3 Bb7 5. Bg2 Be7 6. 0-0 0-0 7. d5 exd5 8. Nh4 c6 9. cxd5 Nxd5 10.
Nf5 Nc7 11. e4 Bf6 12. Nd6 Ba6 13. Re1 Ne8 14. e5 Nxd6 15. exf6 Qxf6 16. Nc3 Nb7 17. Ne4 Qg6
18. h4 h6 19. h5 Qh7 20. Qg4 Kh8 21. Bg5 f5 22. Qf4 Nc5 23. Be7 Nd3 24. Qd6 Nxe1 25. Rxe1 fxe4
26. Bxe4 Rf5 27. Bh4 Bc4 28. g4 Rd5 29. Bxd5 Bxd5 30. Re8+ Bg8 31. Bg3 c5 32. Qd5 d6 33. Qxa8
Nd7 34. Qe4 Nf6 35. Qxh7+ Kxh7 36. Re7 Nxg4 37. Rxa7 Nf6 38. Bxd6 Be6 39. Be5 Nd7 40. Bc3 g6
41. Bd2 gxh5 42. a3 Kg6 43. Bf4 Kf5 44. Bc7 h4 45. Ra8 h5 46. Rh8 Kg6 47. Rd8 Kf7 48. f3 Bf5 49.
Bh2 h3 50. Rh8 Kg6 51. Re8 Kf7 52. Re1 Be6 53. Bc7 b5 54. Kh2 Kf6 55. Re3 Ke7 56. Re4 Kf7 57.
Bd6 Kf6 58. Kg3 Kf7 59. Kf2 Bf5 60. Re1 Kg6 61. Kg1 c4 62. Kh2 h4 63. Be7 Nb6 64. Bxh4 Na4 65.
Re2 Nc5 66. Re5 Nb3 67. Rd5 Be6 68. Rd6 Kf5 69. Be1 Ke5 70. Rb6 Bd7 71. Kg3 Nc1 72. Rh6 Kd5
73. Bc3 Bf5 74. Rh5 Ke6 75. Kf2 Nd3+ 76. Kg1 Nf4 77. Rh6+ Ke7 78. Kh2 Nd5 79. Kg3 Be6 80. Rh5
Ke8 81. Re5 Kf7 82. Bd2 Ne7 83. Bb4 Nd5 84. Bc3 Ke7 85. Bd2 Kf6 86. f4 Ne7 87. Rxb5 Nf5+ 88.
Kh2 Ke7 89. Ra5 Nh4 90. Bb4+ Kf7 91. Rh5 Nf3+ 92. Kg3 Kg6 93. Rh8 Nd4 94. Bc3 Nf5+ 95. Kxh3
Bd7 96. Kh2 Kf7 97. Rb8 Ke6 98. Kg1 Bc6 99. Rb6 Kd5 100. Kf2 Bd7 101. Ke1 Ke4 102. Bd2 Kd5
103. Rf6 Nd6 104. Rh6 Nf5 105. Rh8 Ke4 106. Rh7 Bc8 107. Rc7 Ba6 108. Rc6 Bb5 109. Rc5 Bd7
110. Rxc4+ Kd5 111. Rc7 Kd6 112. Rc3 Ke6 113. Rc5 Nd4 114. Be3 Nf5 115. Bf2 Nd6 116. Rc3 Ne4
117. Rd3 1-0[/pgn]
21.Bg5! is an A++ Tier 1 move, much better than b4 that a few engines like ...
[d]rn3r1k/pn1p1ppq/bpp4p/7P/4N1Q1/6P1/PP3PB1/R1B1R1K1 w - - 3 21

User avatar
MikeB
Posts: 2505
Joined: Thu Mar 09, 2006 5:34 am
Location: Pen Argyl, Pennsylvania

Re: Historic Milestone: AlphaZero

Post by MikeB » Thu Dec 07, 2017 2:51 am

MikeB wrote:
JJJ wrote:Game 5 :
White:
AlphaZero
Black:
Stockfish

[pgn]1. d4 Nf6 2. c4 e6 3. Nf3 b6 4. g3 Bb7 5. Bg2 Be7 6. 0-0 0-0 7. d5 exd5 8. Nh4 c6 9. cxd5 Nxd5 10.
Nf5 Nc7 11. e4 Bf6 12. Nd6 Ba6 13. Re1 Ne8 14. e5 Nxd6 15. exf6 Qxf6 16. Nc3 Nb7 17. Ne4 Qg6
18. h4 h6 19. h5 Qh7 20. Qg4 Kh8 21. Bg5 f5 22. Qf4 Nc5 23. Be7 Nd3 24. Qd6 Nxe1 25. Rxe1 fxe4
26. Bxe4 Rf5 27. Bh4 Bc4 28. g4 Rd5 29. Bxd5 Bxd5 30. Re8+ Bg8 31. Bg3 c5 32. Qd5 d6 33. Qxa8
Nd7 34. Qe4 Nf6 35. Qxh7+ Kxh7 36. Re7 Nxg4 37. Rxa7 Nf6 38. Bxd6 Be6 39. Be5 Nd7 40. Bc3 g6
41. Bd2 gxh5 42. a3 Kg6 43. Bf4 Kf5 44. Bc7 h4 45. Ra8 h5 46. Rh8 Kg6 47. Rd8 Kf7 48. f3 Bf5 49.
Bh2 h3 50. Rh8 Kg6 51. Re8 Kf7 52. Re1 Be6 53. Bc7 b5 54. Kh2 Kf6 55. Re3 Ke7 56. Re4 Kf7 57.
Bd6 Kf6 58. Kg3 Kf7 59. Kf2 Bf5 60. Re1 Kg6 61. Kg1 c4 62. Kh2 h4 63. Be7 Nb6 64. Bxh4 Na4 65.
Re2 Nc5 66. Re5 Nb3 67. Rd5 Be6 68. Rd6 Kf5 69. Be1 Ke5 70. Rb6 Bd7 71. Kg3 Nc1 72. Rh6 Kd5
73. Bc3 Bf5 74. Rh5 Ke6 75. Kf2 Nd3+ 76. Kg1 Nf4 77. Rh6+ Ke7 78. Kh2 Nd5 79. Kg3 Be6 80. Rh5
Ke8 81. Re5 Kf7 82. Bd2 Ne7 83. Bb4 Nd5 84. Bc3 Ke7 85. Bd2 Kf6 86. f4 Ne7 87. Rxb5 Nf5+ 88.
Kh2 Ke7 89. Ra5 Nh4 90. Bb4+ Kf7 91. Rh5 Nf3+ 92. Kg3 Kg6 93. Rh8 Nd4 94. Bc3 Nf5+ 95. Kxh3
Bd7 96. Kh2 Kf7 97. Rb8 Ke6 98. Kg1 Bc6 99. Rb6 Kd5 100. Kf2 Bd7 101. Ke1 Ke4 102. Bd2 Kd5
103. Rf6 Nd6 104. Rh6 Nf5 105. Rh8 Ke4 106. Rh7 Bc8 107. Rc7 Ba6 108. Rc6 Bb5 109. Rc5 Bd7
110. Rxc4+ Kd5 111. Rc7 Kd6 112. Rc3 Ke6 113. Rc5 Nd4 114. Be3 Nf5 115. Bf2 Nd6 116. Rc3 Ne4
117. Rd3 1-0[/pgn]
21.Bg5! is an A++ Tier 1 move, much better than b4 that a few engines like ...
[d]rn3r1k/pn1p1ppq/bpp4p/7P/4N1Q1/6P1/PP3PB1/R1B1R1K1 w - - 3 21
[d]rn3r1k/p2pB1pq/bpp4p/2n2p1P/4NQ2/6P1/PP3PB1/R3R1K1 b - - 3 23
23.Nd3 is horrible - game is probably lost , but after Nd3 it is definitely lost after 23 moves, Ne6 offers stiffer resistance.

with some back and forth

Code: Select all

dep	score	nodes	time	(not shown:  tbhits	knps	seldep)
 36	+4.03 	1.65G	1:21.24	Qd6 fxe4 Bxe4 Rf5 Bh4 Nxe1 Rxe1 Be2 Rxe2 Na6 Qxd7 Raf8 g4 R5f7 Qd3 Nb4 Bxh7 Nxd3 Bxd3 Rf4 Be7 Rxg4+ Kh2 Re8 Bg6 Rg8 Be4 Re8 Bxc6 Rb8 Be4 Re8 Bg6 Ra8 Rd2 Rc4 Rd7 Rac8 Rxa7 R4c7 Rxc7 Rxc7 Bb4 Rc4 a3 Kg8 Kg3 Rc1 Kf3 Rg1 Bd2 Rd1 Bc3 
 35	+3.75 	853.5M	0:41.70	Qd6 fxe4 Bxe4 Rf5 Bh4 Nxe1 Rxe1 Be2 Rxe2 Na6 Qxd7 Raf8 g4 R5f7 Qd3 Nb4 Qd6 Qg8 Qxb4 Rf4 f3 Qf7 Kh2 Re8 Bg3 Rf6 Qc3 Rfe6 Rd2 Qe7 Kh3 c5 Qd3 Qf6 Qd5 Qg5 Qxg5 hxg5 Rd5 Rxe4 fxe4 Rxe4 
 34	+3.58 	627.0M	0:30.53	Qd6 fxe4 Bxe4 Rf5 Bh4 Nxe1 Rxe1 Bc4 g4 Rd5 Bxd5 Bxd5 Re8+ Bg8 Bg3 c5 Qd5 d6 Bxd6 Nd7 Rxa8 Qb1+ Kg2 Nf6 Qf5 Qd1 Be7 Qxg4+ Qxg4 Nxg4 Rxa7 Ne5 Bf8 Bf7 Bd6 Bd5+ Kg3 Nc6 Rb7 Nd4 Rxb6 Nf5+ Kf4 Nxd6 Rxd6 Bxa2 Rc6 c4 Rc7 Kh7 Ke4 Bb3 Rc 
 33	+3.58 	601.6M	0:29.28	Qd6 fxe4 Bxe4 Rf5 Bh4 Nxe1 Rxe1 Bc4 g4 Rd5 Bxd5 Bxd5 Re8+ Bg8 Bg3 c5 Qd5 d6 Bxd6 Nd7 Rxa8 Qb1+ Kg2 Nf6 Qf5 Qd1 Be7 Qxg4+ Qxg4 Nxg4 Rxa7 Ne5 Bf8 Bf7 Bd6 Bd5+ Kg3 Nc6 Rb7 Nd4 Rxb6 Nf5+ Kf4 Nxd6 Rxd6 Bxa2 Rc6 c4 Rc7 Kh7 Ke4 Bb3 Rc 
 33	+3.52!	509.4M	0:24.84	Qd6! 
 32	+3.17 	308.7M	0:15.10	Qd6 fxe4 Bxe4 Rf5 Bh4 Nxe1 Rxe1 Bc4 g4 Rd5 Bxd5 Bxd5 Re8+ Bg8 Bg3 c5 Qd5 d6 Bxd6 Nd7 Rxa8 Qb1+ Kg2 Nf6 Qf5 Qd1 Be7 Qxg4+ Qxg4 Nxg4 Rxa7 Ne5 Bf8 Bf7 Bd6 Bd5+ Kg3 Nf7 Bc7 b5 Kf4 Kg8 Bb6 c4 Bd4 Bc6 Rc7 Bg2 Ke3 Kf8 f3 Ke8 Bxg7 
 31	+3.05 	157.8M	0:07.69	Qd6 fxe4 Bxe4 Rf5 Bh4 Nxe1 Rxe1 Bc4 g4 Rd5 Bxd5 Bxd5 Re8+ Bg8 Bg3 c5 Qd5 d6 Bxd6 Nd7 Rxa8 Qb1+ Kg2 Nf6 Qf5 Qd1 Be7 Qxg4+ Qxg4 Nxg4 Rxa7 Ne5 Bf8 Bf7 Bd6 Bd5+ Kg3 Nf7 Bc7 b5 Kf4 Kg8 Bb6 Ng5 Bxc5 Bf7 Bd4 Ne6+ Ke5 Nxd4 Kxd4 Bxh5 
 31	+3.15?	153.4M	0:07.46	Qd6 fxe4? 
 31	+3.44!	141.2M	0:06.86	Qd6! 
 31	+3.31?	131.0M	0:06.37	Qd6 fxe4? 
 31	+3.42?	130.6M	0:06.35	Qd6 fxe4? 
 31	+3.50?	130.4M	0:06.34	Qd6 fxe4? 
 30	+3.57 	128.0M	0:06.22	Qd6 fxe4 Bxe4 Rf5 Bh4 Nxe1 Rxe1 Bc4 g4 Na6 Bxf5 Qg8 Re7 Rf8 Rxd7 Nc5 Rxa7 Bd5 Be7 Rxf5 gxf5 Ne4 Qd8 Qxd8 Bxd8 b5 f6 gxf6 f3 Nd2 Bxf6+ Kg8 f4 Bf3 Rg7+ Kf8 Rh7 Bxh5 Rxh6 Bf3 Bc3 Nc4 Kf2 Bd5 b3 Nb6 f5 Kf7 Kg3 Nd7 Kf4 Ke8 Be5 Nc5 R 
 29	+3.44 	91.7M  	0:04.45	Qd6 fxe4 Bxe4 Rf5 Bh4 Ne5 g4 Nxg4 Qg3 d5 Bb1 Nd7 Qxg4 Raf8 Re7 Ne5 Rxe5 Rxe5 Bxh7 Kxh7 Qg6+ Kg8 Qxc6 Rxh5 Qe6+ Kh7 Qe7 Rf4 Bg3 Rf6 Rd1 Bb5 Rd4 Rg6 Qxa7 Be2 Kg2 Rf5 Qa3 
 28	+3.41 	47.0M  	0:02.25	Qd6 Nxe1 Rxe1 fxe4 Bxe4 Rf5 Bh4 Bc4 g4 Rd5 Bxd5 Bxd5 Re8+ Bg8 Bg3 c5 Qd5 d6 Bxd6 Nd7 Rxa8 Qb1+ Kg2 Nf6 Qf5 Qd1 Be7 Qxg4+ Qxg4 Nxg4 Rxa7 Ne5 Bf8 Bf7 Bd6 Bd5+ Kg3 Nc6 Ra6 b5 Bxc5 Kg8 Rb6 Ne5 Rxb5 Nd7 Bd4 Bxa2 
 27	+3.43 	40.1M  	0:01.92	Qd6 Nxe1 Rxe1 fxe4 Bxe4 Rf5 Bh4 Bc4 g4 Rd5 Bxd5 Bxd5 Re8+ Bg8 Bg3 c5 Qd5 d6 Bxd6 Nd7 Rxa8 Nf6 Qf5 Qxf5 gxf5 a5 Bc7 b5 Rxa5 Bc4 Bd6 Nxh5 Bxc5 Bd5 Kh2 Bc6 Kh3 Nf4+ Kg4 Nd3 Bd4 Be8 Ra7 
 26	+3.42 	33.2M  	0:01.59	Qd6 Nxe1 Rxe1 fxe4 Bxe4 Rf5 Bh4 Bc4 g4 Rd5 Bxd5 Bxd5 Re8+ Bg8 Bg3 c5 Qd5 d6 Bxd6 Nd7 Rxa8 Qb1+ Kg2 Nf6 Qf5 Qxf5 gxf5 Nxh5 Be5 a5 Kf3 Nf6 Bxf6 gxf6 Rb8 Kg7 Rb7+ Bf7 a3 h5 Rxb6 Be8 Kf4 c4 Rb7+ Kg8 Rc7 Bf7 Rc5 h4 
 25	+3.41 	14.3M  	0:00.67	Qd6 fxe4 Bxe4 Rf5 Bh4 Ne5 g4 Nxg4 Qg3 Bc4 Qxg4 Be6 Bxf5 Qxf5 Qxf5 Bxf5 Re8+ Kh7 Bg3 a5 Rxb8 Rxb8 Bxb8 a4 f3 g6 hxg6+ Kxg6 Kf2 Be6 Rg1+ Kf6 Rh1 Bxa2 Bf4 Be6 Rxh6+ Kg7 Ke3 b5 
 24	+3.43 	13.8M  	0:00.64	Qd6 fxe4 Bxe4 Rf5 Bh4 Ne5 g4 Nxg4 Qg3 Bc4 Qxg4 Be6 Bxf5 Qxf5 Qxf5 Bxf5 Re8+ Kh7 Bg3 a5 Rxb8 Rxb8 Bxb8 a4 f3 g6 hxg6+ Kxg6 Kf2 h5 Rg1+ Kf6 Ba7 b5 a3 Ke5 Rg5 h4 Rh5 Ke6 Rh6+ Kf7 Rxh4 
 23	+3.27 	9.84M  	0:00.46	Qd6 fxe4 Bxe4 Rf5 Bh4 Ne5 g4 Nxg4 Qg3 d5 Bb1 Nd7 Qxg4 Raf8 Re7 Ne5 Rxe5 Rxe5 Bxh7 Kxh7 Qg6+ Kg8 Qxc6 Rxh5 Qe6+ Kh7 Qe7 Rff5 Rd1 Re5 Qxa7 Be2 Rd4 Bf3 
 22	+3.35 	8.22M  	0:00.38	Qd6 fxe4 Bxe4 Rf5 Bh4 Ne5 g4 Nxg4 Qg3 Bc4 Qxg4 Be6 Bxf5 Qxf5 Qxf5 Bxf5 Re8+ Kh7 Bg3 Bg4 Rxb8 Rxb8 Bxb8 a6 Re1 Bxh5 Re7 Bg4 Be5 h5 Kg2 Kh6 Bxg7+ Kg6 
 21	+3.32 	7.26M  	0:00.34	Qd6 fxe4 Bxe4 Rf5 Bh4 Ne5 g4 Nxg4 Qg3 d5 Bb1 Nd7 Qxg4 Raf8 Re7 Ne5 Rxe5 Rxe5 Bxh7 Kxh7 Qg6+ Kh8 Qd6 Ref5 Re1 Bd3 Re7 Be4 Rxa7 
 20	+2.88 	6.49M  	0:00.30	Qd6 fxe4 Bxe4 Rf5 Bh4 Ne5 g4 Nxg4 Qg3 d5 Bb1 Nd7 Qxg4 Raf8 Re7 Ne5 Rxe5 Rxe5 Bxh7 Kxh7 Qg6+ Kg8 Bg3 Rf6 Bxe5 Rxg6+ hxg6 c5 Rd1 d4 
 19	+2.82 	5.22M  	0:00.24	Qd6 fxe4 Bxe4 Rf5 Bh4 Ne5 g4 Nxg4 Qg3 d5 Bb1 Nd7 Qxg4 Raf8 Re7 Rf4 Qxd7 Bc8 Qd6 Qg8 Bg3 R4f6 Qc7 Bf5 Bxf5 Rxf5 Qxc6 d4 Qe4 Rxh5 Qxd4 Rd8 Qg4 Rg5 Qe4 Qd5 
 18	+3.19 	3.79M  	0:00.17	Qd6 fxe4 Bxe4 Rf5 Bh4 Ne5 g4 Nxg4 Qg3 Bc4 Qxg4 Be6 Bxf5 Qxf5 Qxf5 Bxf5 Re8+ Kh7 Bg3 Bg4 Rae1 Be6 Rxb8 Rxb8 Bxb8 a6 Bc7 b5 b3 c5 Bd6 c4 bxc4 bxc4 Be5 Bf7 Rd1 
 17	+3.20 	2.67M  	0:00.12	Qd6 fxe4 Bxe4 Rf5 Bh4 Ne5 g4 Nxg4 Qg3 Bc4 Qxg4 Be6 Bxf5 Qxf5 Qxf5 Bxf5 Re8+ Kh7 Bg3 Be6 Rxb8 Rxb8 Bxb8 a6 Bf4 b5 Rd1 g6 hxg6+ Kxg6 Kh2 h5 Kg3 Kf7 
 16	+3.08 	1.72M  	0:00.08	Qd6 fxe4 Bxe4 Rf5 Bh4 Ne5 g4 Nxg4 Qg3 Bc4 Qxg4 Be6 Bxf5 Qxf5 Qxf5 Bxf5 Re8+ Kh7 Bg3 Be6 Rxb8 Rxb8 Bxb8 a6 Re1 g6 Be5 b5 b3 a5 Bc7 gxh5 
 15	+2.72 	643491	0:00.03	Qd6 fxe4 Bxe4 Rf5 Bh4 Ne5 g4 Nxg4 Qg3 d5 Bb1 Nd7 Qxg4 Raf8 Re7 Rf4 Qxd7 Bc8 Qd6 Qg8 Bg3 R4f6 Qc7 Re6 Bg6 Rxe7 Qxe7 
 14	+2.62 	397143	0:00.02	Qd6 fxe4 Bxe4 Rf5 Bh4 Ne5 f4 Bc4 fxe5 Na6 Rad1 Bd5 Rxd5 cxd5 Bb1 Raf8 g4 Rf1+ Kg2 
 13	+2.80 	222297	0:00.01	Qd6 fxe4 Bxe4 Rf5 Bh4 Ne5 g4 Nxg4 Qg3 Nxf2 Bb1 Ne4 Bxe4 Rf1+ Rxf1 Qxe4 Rf8+ Kh7 Re1 Qd4+ Kg2 Qxb2+ Kh1 
 12	+2.75 	113750	0:00.01	Qd6 fxe4 Bxe4 Rf5 Bh4 Ne5 g4 Nxg4 Qg3 d5 Bb1 Nd7 Qxg4 Raf8 Re7 Rf4 Qxd7 
 11	+2.75 	98151  	0:00.00	Qd6 fxe4 Bxe4 Rf5 Bh4 Ne5 g4 Nxg4 Qg3 d5 Bb1 Nd7 Qxg4 
 10	+2.75 	70974  	0:00.00	Qd6 fxe4 Bxe4 Rf5 Bh4 Ne5 g4 Nxg4 Qg3 d5 Bb1 
  9	+2.72 	63784  	0:00.00	Qd6 fxe4 Bxe4 Rf5 Bh4 Ne5 g4 Nxg4 Qg3 
  8	+2.75 	34505  	0:00.00	Qd6 fxe4 Bxe4 Rf5 Bh4 Ne5 g4 Nxg4 
  7	+1.82 	25080  	0:00.00	Qd6 fxe4 Bxe4 Rf5 Bh4 Ne5 f4 
  6	+2.75 	17530  	0:00.00	Qd6 fxe4 Bxe4 Rf5 Bh4 Nxf2 
  5	+0.67 	10917  	0:00.00	Qd6 fxe4 Bxf8 Nxe1 Rxe1 
  4	+2.60 	4780    	0:00.00	Qd6 fxe4 Bxe4 Rf5 
  3	+2.77 	2541    	0:00.00	Qd6 Rc8 Nf6 
  2	+2.77 	1401    	0:00.00	Qd6 Rc8 
  1	+2.60 	374      	0:00.00	Qd6 
One common theme in all of these games is how well alphazero played the opening ...

Albert Silver
Posts: 2681
Joined: Wed Mar 08, 2006 8:57 pm
Location: Rio de Janeiro, Brazil

Re: Historic Milestone: AlphaZero

Post by Albert Silver » Thu Dec 07, 2017 3:29 am

MikeB wrote:One common theme in all of these games is how well alphazero played...
Fixed.
"Tactics are the bricks and sticks that make up a game, but positional play is the architectural blueprint."

User avatar
MikeGL
Posts: 693
Joined: Thu Sep 01, 2011 12:49 pm

Re: Historic Milestone: AlphaZero

Post by MikeGL » Thu Dec 07, 2017 3:33 am

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

see the Qh8 of SF8 looks like a setup position
[D]5rkq/3r1p1p/5RpP/2p3P1/p1B2Q2/8/P4PK1/8 b - - 0 54

SF8 in a very difficult bind, no pieces can move already. Except the Rd7 which is also forced to defend f7.

User avatar
MikeB
Posts: 2505
Joined: Thu Mar 09, 2006 5:34 am
Location: Pen Argyl, Pennsylvania

Re: Historic Milestone: AlphaZero

Post by MikeB » Thu Dec 07, 2017 4:12 am

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 

User avatar
MikeGL
Posts: 693
Joined: Thu Sep 01, 2011 12:49 pm

Re: Historic Milestone: AlphaZero

Post by MikeGL » Thu Dec 07, 2017 4:17 am

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: 17
Joined: Wed Aug 19, 2015 7:06 pm
Contact:

Re: Much weaker than Stockfish

Post by KWRegan » Thu Dec 07, 2017 5:04 am

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: 3278
Joined: Thu Mar 16, 2006 6:10 pm

Re: Much weaker than Stockfish

Post by M ANSARI » Thu Dec 07, 2017 5:47 am

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 9:01 pm
Location: Irvine, CA, USA

Re: Historic Milestone: AlphaZero

Post by Dirt » Thu Dec 07, 2017 7:22 am

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.

Post Reply