LCZero update

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

Moderators: hgm, Rebel, chrisw

jkiliani
Posts: 143
Joined: Wed Jan 17, 2018 1:26 pm

Re: LCZero update

Post by jkiliani »

Nay Lin Tun wrote:Thank you Carlos,

So, 1.I downloaded your files.
https://ibb.co/coLruc

2.I did test run my GPU, ok
https://ibb.co/hUD5LH

3. I try to install new engine in arena

https://ibb.co/dUc1Sx

And start arena, and Leele Zero is not running.
Am I missing something?
Did you pass on all necessary command line arguments to lczero when configuring Arena? I.e. did you link the path to the weight file you're planning to use, and test that lczero can actually find the file under this path?
User avatar
CMCanavessi
Posts: 1142
Joined: Thu Dec 28, 2017 4:06 pm
Location: Argentina

Re: LCZero update

Post by CMCanavessi »

Nay Lin Tun wrote:Thank you Carlos,

So, 1.I downloaded your files.
https://ibb.co/coLruc

2.I did test run my GPU, ok
https://ibb.co/hUD5LH

3. I try to install new engine in arena

https://ibb.co/dUc1Sx

And start arena, and Leele Zero is not running.
Am I missing something?
In Arena, point it to Play.bat, or add -w cd1a1e to the "Command line parameters" if you use the .exe

Like this, but change the network name:

Image[/code]
Follow my tournament and some Leela gauntlets live at http://twitch.tv/ccls
User avatar
Guenther
Posts: 4605
Joined: Wed Oct 01, 2008 6:33 am
Location: Regensburg, Germany
Full name: Guenther Simon

Re: LCZero update

Post by Guenther »

CMCanavessi wrote:
Nay Lin Tun wrote:Hey, Carlos, would you mind uploading the setup files in mediafire for Leelazero v3 to be able to run in my arena.

(i can setup client version 3 in the network with your previous files)
Here you go: client v3, latest network (gen 13) and latest lczero.exe (build 112)

http://www.mediafire.com/file/ilm2ixxpl ... en%2013.7z
[pgn][Event "RWBC"]
[Site "CAPPUCCINO"]
[Date "2018.03.21"]
[Round "-"]
[White "LCZero_Gen13"]
[Black "Cassandre_024"]
[Result "0-1"]
[TimeControl "40/180"]
[Annotator "1. -0.02 1... -0.09"]

1. e4 {-0.02/17} e5 {-0.09/6 3} 2. Nf3 {-0.13/18 4} Nc6 {+0.00/5 1.5} 3.
Nc3 {-0.23/18 4} Bc5 {+0.01/5 2.3} 4. Nxe5 {+0.18/18 4} Nxe5 {+0.03/5 2.1}
5. d4 {+0.65/18 4} Bxd4 {-0.01/5 1.8} 6. Qxd4 {+0.80/19 4} d6 {-0.04/5 1.2}
7. Qd1 {+0.58/19 4} Bg4 {+0.05/5 4} 8. f3 {+1.43/18 4} Qh4+ {+0.13/5 4} 9.
g3 {+1.54/18 4} Nxf3+ {+0.96/5 7} 10. Kf2 {+0.89/19 4} Qf6 {+0.11/5 4} 11.
Nd5 {+2.17/18 4} Qd8 {-0.08/5 3} 12. h3 {+2.07/19 4} Bh5 {-0.82/5 2.8} 13.
g4 {+2.31/19 4} Qh4+ {-0.75/5 2.2} 14. Kxf3 {+3.23/18 4} Bxg4+
{+1.01/5 1.5} 15. hxg4 {+2.49/19 4} Qxh1+ {+0.83/5 0.7} 16. Kg3
{+2.28/19 4} Qg1+ {+1.01/5 0.9} 17. Kf3 {+3.43/18 4} Qh1+ {+0.83/5 0.9} 18.
Kg3 {+2.26/20 4} Qg1+ {+1.01/5 0.9} 19. Kf4 {+2.62/18 4} Qh2+ {+0.98/5 0.9}
20. Kg5 {+2.43/18 4} h6+ {+2000.00/6 3} 21. Kf5 {-42.24/16 5} g6#
{+2000.00/6 4}
{Xboard adjudication: Checkmate} 0-1[/pgn]

Interesting blind spot on 20...h6 at least with my weak GPU

Code: Select all

1521636757.446 POLYGLOT FEN r3k1nr/ppp2ppp/3p4/3N4/4PKP1/8/PPP4q/R1BQ1B2 w kq - 8 20
1521636757.446 Adapter->Engine: position startpos moves e2e4 e7e5 g1f3 b8c6 b1c3 f8c5 f3e5 c6e5 d2d4 c5d4 d1d4 d7d6 d4d1 c8g4 f2f3 d8h4 g2g3 e5f3 e1f2 h4f6 c3d5 f6d8 h2h3 g4h5 g3g4 d8h4 f2f3 h5g4 h3g4 h4h1 f3g3 h1g1 g3f3 g1h1 f3g3 h1g1 g3f4 g1h2
1521636757.446 Adapter->Engine: go wtime 98010 btime 135630 movestogo 21
1521636757.446 Engine->Adapter: info depth 8 nodes 4 nps 2000 score cp 347 winrate 63.04% time 1 pv f4f5 c7c6 d5c7
1521636757.446 Adapter->GUI: 8 +347 0 4  0    2 0	Kf5 c6 Nc7+
1521636757.446 Engine->Adapter: info depth 9 nodes 9 nps 4500 score cp -122 winrate 45.29% time 1 pv f4f3 c7c6 d5c7 e8e7
1521636757.446 Adapter->GUI: 9 -122 0 9  0    4 0	Kf3 c6 Nc7+ Ke7
1521636757.446 Engine->Adapter: info depth 11 nodes 33 nps 11000 score cp 162 winrate 56.23% time 2 pv f4f3 c7c6 c1f4 c6d5 f4h2
1521636757.446 Adapter->GUI: 11 +162 0 33  0   11 0	Kf3 c6 Bf4 cxd5 Bxh2
1521636757.446 Engine->Adapter: info depth 12 nodes 49 nps 12250 score cp 220 winrate 58.41% time 3 pv f4f3 c7c6 d5c7 e8d7 c7a8
1521636757.446 Adapter->GUI: 12 +220 0 49  0   12 0	Kf3 c6 Nc7+ Kd7 Nxa8
1521636757.526 Engine->Adapter: info depth 13 nodes 84 nps 1024 score cp 276 winrate 60.46% time 81 pv f4f3 c7c6 c1f4 c6d5 f4h2 d5e4
1521636757.526 Adapter->GUI: 13 +276 8 84  0    1 0	Kf3 c6 Bf4 cxd5 Bxh2 dxe4+
1521636757.676 Engine->Adapter: info depth 14 nodes 160 nps 689 score cp 275 winrate 60.42% time 231 pv f4f3 h2h1
1521636757.676 Adapter->GUI: 14 +275 23 160  0    1 0	Kf3 Qh1+
1521636757.916 Engine->Adapter: info depth 15 nodes 312 nps 659 score cp 221 winrate 58.42% time 472 pv f4f3 h2h1
1521636757.916 Adapter->GUI: 15 +221 47 312  0    1 0	Kf3 Qh1+
1521636758.486 Engine->Adapter: info depth 16 nodes 521 nps 500 score cp 252 winrate 59.58% time 1041 pv f4g5 h2e5 g5h4 c7c6 d5c7 e8d7 c7a8 g8f6
1521636758.486 Adapter->GUI: 16 +252 104 521  0    0 0	Kg5 Qe5+ Kh4 c6 Nc7+ Kd7 Nxa8 Nf6
1521636759.436 Engine->Adapter: info depth 17 nodes 866 nps 435 score cp 261 winrate 59.94% time 1986 pv f4g5 a8d8 d1f3 g8e7 d5e7 e8e7 f3f7 e7f7
1521636759.436 Adapter->GUI: 17 +261 199 866  0    0 0	Kg5 Rd8 Qf3 Ne7 Nxe7 Kxe7 Qxf7+ Kxf7
1521636761.156 Engine->Adapter: info depth 18 nodes 1487 nps 401 score cp 256 winrate 59.73% time 3705 pv f4g5 a8d8 c1f4 h2h1 d5c7 e8e7 c7d5 e7d7 f4d6 d7d6
1521636761.156 Adapter->GUI: 18 +256 370 1487  0    0 0	Kg5 Rd8 Bf4 Qh1 Nxc7+ Ke7 Nd5+ Kd7 Bxd6 Kxd6
1521636761.966 Engine->Adapter: 
1521636761.966 Engine->Adapter: f4g5 ->    1272 (V: 60.68%) (N: 21.61%) PV: f4g5 a8d8 c1f4 h2h1 d5c7 e8e7 c7d5 e7d7 f4d6 d7d6
1521636761.966 Engine->Adapter: f4e3 ->     229 (V: 58.29%) (N: 17.86%) PV: f4e3 h2g3 e3d4 c7c6 d5c7 e8d8 c7a8
1521636761.966 Engine->Adapter: f4f3 ->     226 (V: 55.19%) (N: 37.39%) PV: f4f3 h2h1
1521636761.966 Engine->Adapter: f4f5 ->      81 (V: 50.91%) (N: 23.13%) PV: f4f5 h2e5
1521636761.966 Engine->Adapter: 
1521636761.966 Engine->Adapter: info depth 18 nodes 1808 nps 400 score cp 243 winrate 59.25% time 4519 pv f4g5 a8d8 c1f4 h2h1 d5c7 e8e7 c7d5 e7d7 f4d6 d7d6
1521636761.966 Adapter->GUI: 18 +243 452 1808  0    0 0	Kg5 Rd8 Bf4 Qh1 Nxc7+ Ke7 Nd5+ Kd7 Bxd6 Kxd6
1521636761.966 Engine->Adapter: bestmove f4g5
1521636761.966 Adapter->GUI: move f4g5
1521636761.966 POLYGLOT MOVE Kg5
1521636761.966 POLYGLOT THINK -> WAIT
1521636765.326 GUI->Adapter: time 9348
1521636765.326 GUI->Adapter: otim 13228
1521636765.326 GUI->Adapter: usermove h7h6
1521636765.326 POLYGLOT MOVE h6+
1521636765.326 POLYGLOT WAIT -> THINK
1521636765.326 POLYGLOT START SEARCH
1521636765.326 POLYGLOT FEN r3k1nr/ppp2pp1/3p3p/3N2K1/4P1P1/8/PPP4q/R1BQ1B2 w kq - 0 21
1521636765.326 Adapter->Engine: position startpos moves e2e4 e7e5 g1f3 b8c6 b1c3 f8c5 f3e5 c6e5 d2d4 c5d4 d1d4 d7d6 d4d1 c8g4 f2f3 d8h4 g2g3 e5f3 e1f2 h4f6 c3d5 f6d8 h2h3 g4h5 g3g4 d8h4 f2f3 h5g4 h3g4 h4h1 f3g3 h1g1 g3f3 g1h1 f3g3 h1g1 g3f4 g1h2 f4g5 h7h6
1521636765.326 Adapter->Engine: go wtime 93480 btime 132280 movestogo 20
1521636765.326 Engine->Adapter: info depth 5 nodes 1 nps 1000 score cp -1066 winrate 16.24% time 0 pv g5f5 c7c6
1521636765.326 Adapter->GUI: 5 -1066 0 1  0    1 0	Kf5 c6
1521636765.326 Engine->Adapter: info depth 9 nodes 10 nps 10000 score cp -59 winrate 47.71% time 0 pv g5f5 g8e7 d5e7 e8e7 c1f4 h2f4
1521636765.326 Adapter->GUI: 9 -59 0 10  0   10 0	Kf5 Ne7+ Nxe7 Kxe7 Bf4 Qxf4+
1521636765.336 Engine->Adapter: info depth 10 nodes 21 nps 1909 score cp 146 winrate 55.59% time 10 pv g5f5 c7c6 c1f4 c6d5 e4d5
1521636765.336 Adapter->GUI: 10 +146 1 21  0    2 0	Kf5 c6 Bf4 cxd5 exd5
1521636765.346 Engine->Adapter: info depth 11 nodes 25 nps 1315 score cp 181 winrate 56.94% time 18 pv g5f5 c7c6 c1f4 c6d5 e4d5
1521636765.346 Adapter->GUI: 11 +181 2 25  0    1 0	Kf5 c6 Bf4 cxd5 exd5
1521636765.396 Engine->Adapter: info depth 12 nodes 1491 nps 22590 score cp -2673 winrate  1.61% time 65 pv g5f5 g7g6
1521636765.396 Adapter->GUI: 12 -2673 6 1491  0   23 0	Kf5 g6#
1521636765.526 Engine->Adapter: info depth 13 nodes 4915 nps 25205 score cp -2977 winrate  1.01% time 194 pv g5f5 g7g6
1521636765.526 Adapter->GUI: 13 -2977 19 4915  0   25 0	Kf5 g6#
1521636765.756 Engine->Adapter: info depth 14 nodes 14072 nps 32649 score cp -3282 winrate  0.64% time 430 pv g5f5 g7g6
1521636765.756 Adapter->GUI: 14 -3282 43 14072  0   33 0	Kf5 g6#
1521636766.226 Engine->Adapter: info depth 15 nodes 39191 nps 43739 score cp -3588 winrate  0.40% time 895 pv g5f5 g7g6
1521636766.226 Adapter->GUI: 15 -3588 90 39191  0   44 0	Kf5 g6#
1521636767.526 Engine->Adapter: info depth 16 nodes 119011 nps 53973 score cp -3940 winrate  0.23% time 2204 pv g5f5 g7g6
1521636767.526 Adapter->GUI: 16 -3940 220 119011  0   54 0	Kf5 g6#
1521636769.866 Engine->Adapter: 
1521636769.866 Engine->Adapter: g5f5 ->  287931 (V:  0.15%) (N: 100.00%) PV: g5f5 g7g6
1521636769.866 Engine->Adapter: 
1521636769.866 Engine->Adapter: info depth 16 nodes 287931 nps 63365 score cp -4224 winrate  0.15% time 4543 pv g5f5 g7g6
1521636769.866 Adapter->GUI: 16 -4224 454 287931  0   63 0	Kf5 g6#
1521636769.866 Engine->Adapter: bestmove g5f5
1521636769.866 Adapter->GUI: move g5f5
1521636769.866 POLYGLOT MOVE Kf5
1521636769.866 POLYGLOT THINK -> WAIT
1521636773.796 GUI->Adapter: usermove g7g6
1521636773.796 POLYGLOT MOVE g6#
https://rwbc-chess.de

trollwatch:
Chessqueen + chessica + AlexChess + Eduard + Sylwy
User avatar
Guenther
Posts: 4605
Joined: Wed Oct 01, 2008 6:33 am
Location: Regensburg, Germany
Full name: Guenther Simon

Re: LCZero update

Post by Guenther »

With 5 times slower tc there was already an epic battle with the same opponent:

[pgn][Event "RWBC"]
[Site "CAPPUCCINO"]
[Date "2018.03.21"]
[Round "-"]
[White "LCZero_Gen13"]
[Black "Cassandre_024"]
[Result "1/2-1/2"]
[TimeControl "40/900"]
[Annotator "1. -0.04 1... -0.09"]

1. e4 {-0.04/20} e5 {-0.09/6 3} 2. Nf3 {-0.15/21 21} Nf6 {-0.04/6 7} 3. d3
{-0.13/21 21} d5 {-0.05/6 7} 4. exd5 {+0.25/21 21} Bc5 {-0.09/6 12} 5. Nxe5
{+1.11/21 21} Qxd5 {-0.09/5 3} 6. Qe2 {+1.73/21 21} Kf8 {-0.08/5 6} 7. Nc3
{+2.11/21 21} Bxf2+ {-0.09/5 4} 8. Kd1 {+2.58/21 22} Qd4 {+0.01/5 7} 9. Nb5
{+2.60/21 22} Qb6 {+0.03/5 7} 10. a4 {+2.39/22 22} Be6 {+0.03/5 15} 11. d4
{+3.15/21 22} Bxd4 {+0.22/5 11} 12. Nf3 {+2.47/21 22} Bc5 {+0.22/5 8} 13.
a5 {+2.45/21 22} Qc6 {+0.22/5 9} 14. Ne5 {+1.97/22 22} Qd5+ {+0.29/5 10}
15. Ke1 {+1.57/22 22} Bd6 {+0.29/5 11} 16. Bf4 {+1.78/21 22} Qe4
{+0.17/5 11} 17. Qxe4 {+1.49/21 22} Nxe4 {+0.09/5 4} 18. Bd3 {+1.31/22 22}
Nc5 {+0.16/6 5} 19. Rf1 {+0.83/21 23} f6 {+0.90/6 7} 20. Nc4 {+0.70/21 23}
Bxf4 {+0.96/6 6} 21. Rxf4 {-0.09/21 23} Nba6 {+0.17/7 59} 22. Rd1
{-0.38/22 23} b6 {+1.01/6 7} 23. Rd4 {+0.70/21 23} c6 {+1.16/6 6} 24. Nc3
{-0.38/21 23} Nb4 {+0.97/7 37} 25. axb6 {+0.19/21 23} Ncxd3+ {+1.27/7 32}
26. Kd2 {-3.37/21 23} Nc5 {+2.13/7 15} 27. Ra1 {-1.72/21 23} Nb7
{+1.96/7 35} 28. Rxa7 {+0.05/21 23} Rd8 {+1.04/7 15} 29. Rxd8+
{+3.50/20 23} Nxd8 {+0.13/8 18} 30. Nd6 {+3.37/22 23} c5 {+0.22/7 23} 31.
Rc7 {+3.18/21 23} Nbc6 {+0.63/7 13} 32. h4 {+3.50/21 23} Rg8 {+0.97/7 24}
33. b7 {+3.95/20 23} c4 {+0.14/7 44} 34. Ke3 {+4.20/20 23} f5 {+0.20/7 30}
35. Kf4 {+5.01/20 23} h6 {+0.91/7 15} 36. Ncb5 {+4.15/20 23} g5+
{+0.45/8 19} 37. hxg5 {+3.54/20 22} hxg5+ {+0.45/8 18} 38. Kf3
{+3.33/21 22} Rg7 {+0.95/8 19} 39. Kf2 {+1.79/20 23} Rxc7 {+1.27/9 1:20}
40. Nxc7 {-0.53/20 25} Ke7 {+1.19/10 1:25} 41. Ncb5 {-1.74/21 45} Nb8
{+1.25/8 8} 42. Nc8+ {-0.77/21 43} Kd7 {+1.88/8 6} 43. Ncd6 {-1.64/21 41}
Nf7 {+1.94/8 4} 44. Nxf7 {-1.89/21 40} Bxf7 {+1.82/9 7} 45. Nd4
{-1.93/21 38} Bg6 {+1.15/9 15} 46. Nf3 {-1.62/21 36} Bf7 {+1.13/9 21} 47.
Ne5+ {+0.71/20 35} Ke7 {+1.33/9 4} 48. Nxf7 {+0.97/22 33} Kxf7 {+1.12/10 7}
49. Ke3 {+0.84/23 32} Ke7 {+1.99/9 11} 50. Kd4 {+0.55/23 31} Kd6
{+1.27/10 6} 51. Kxc4 {+0.52/23 29} Kc6 {+2.01/9 6} 52. Kd4 {+0.48/24 28}
Kd6 {+1.97/9 18} 53. c3 {+2.46/20 27} Nc6+ {+2.03/10 11} 54. Kd3
{-0.42/20 26} Kc7 {+2.07/10 8} 55. Kc4 {-0.40/21 25} Kd6 {+1.35/9 7} 56. b4
{+0.92/20 24} f4 {+1.17/9 5} 57. Kd3 {+1.92/20 23} Kc7 {+1.11/9 7} 58. Ke4
{+1.52/21 22} Na7 {+1.03/10 9} 59. Kf5 {+4.98/20 21} Nb5 {+1.17/11 7} 60.
Kxg5 {+5.20/21 20} Nxc3 {+2.06/11 5} 61. Kxf4 {+5.64/20 19} Nd5+
{+2.04/11 9} 62. Ke5 {+5.17/20 19} Nxb4 {+2.04/12 7} 63. g4 {+6.41/20 18}
Nd3+ {+1.89/12 50} 64. Kf5 {+6.93/20 17} Kxb7 {+2.13/11 10} 65. g5
{+6.68/20 16} Nb4 {+0.52/10 16} 66. Ke6 {+6.74/21 16} Nd3 {+0.31/10 14} 67.
Kf5 {+5.62/21 15} Nb4 {+0.52/10 16} 68. g6 {+5.28/22 15} Nd5 {+0.31/10 24}
69. g7 {+5.28/22 14} Ne7+ {+0.52/10 19} 70. Ke6 {+5.00/22 14} Ng8
{+0.44/10 11} 71. Kf7 {+4.81/22 13} Nh6+ {+0.23/12 51} 72. Kf6
{+4.70/22 13} Ka7 {+0.44/10 11} 73. Kg6 {+4.46/21 12} Ng8 {+0.31/12 16} 74.
Kf5 {+4.45/23 12} Ka8 {+0.65/11 28}
{User adjudication} 1/2-1/2[/pgn]
https://rwbc-chess.de

trollwatch:
Chessqueen + chessica + AlexChess + Eduard + Sylwy
Nay Lin Tun
Posts: 708
Joined: Mon Jan 16, 2012 6:34 am

Re: LCZero update

Post by Nay Lin Tun »

Thank you! I got it !! :lol: :)
User avatar
CMCanavessi
Posts: 1142
Joined: Thu Dec 28, 2017 4:06 pm
Location: Argentina

Re: LCZero update

Post by CMCanavessi »

Guenther wrote:With 5 times slower tc there was already an epic battle with the same opponent:

[pgn][Event "RWBC"]
[Site "CAPPUCCINO"]
[Date "2018.03.21"]
[Round "-"]
[White "LCZero_Gen13"]
[Black "Cassandre_024"]
[Result "1/2-1/2"]
[TimeControl "40/900"]
[Annotator "1. -0.04 1... -0.09"]

1. e4 {-0.04/20} e5 {-0.09/6 3} 2. Nf3 {-0.15/21 21} Nf6 {-0.04/6 7} 3. d3
{-0.13/21 21} d5 {-0.05/6 7} 4. exd5 {+0.25/21 21} Bc5 {-0.09/6 12} 5. Nxe5
{+1.11/21 21} Qxd5 {-0.09/5 3} 6. Qe2 {+1.73/21 21} Kf8 {-0.08/5 6} 7. Nc3
{+2.11/21 21} Bxf2+ {-0.09/5 4} 8. Kd1 {+2.58/21 22} Qd4 {+0.01/5 7} 9. Nb5
{+2.60/21 22} Qb6 {+0.03/5 7} 10. a4 {+2.39/22 22} Be6 {+0.03/5 15} 11. d4
{+3.15/21 22} Bxd4 {+0.22/5 11} 12. Nf3 {+2.47/21 22} Bc5 {+0.22/5 8} 13.
a5 {+2.45/21 22} Qc6 {+0.22/5 9} 14. Ne5 {+1.97/22 22} Qd5+ {+0.29/5 10}
15. Ke1 {+1.57/22 22} Bd6 {+0.29/5 11} 16. Bf4 {+1.78/21 22} Qe4
{+0.17/5 11} 17. Qxe4 {+1.49/21 22} Nxe4 {+0.09/5 4} 18. Bd3 {+1.31/22 22}
Nc5 {+0.16/6 5} 19. Rf1 {+0.83/21 23} f6 {+0.90/6 7} 20. Nc4 {+0.70/21 23}
Bxf4 {+0.96/6 6} 21. Rxf4 {-0.09/21 23} Nba6 {+0.17/7 59} 22. Rd1
{-0.38/22 23} b6 {+1.01/6 7} 23. Rd4 {+0.70/21 23} c6 {+1.16/6 6} 24. Nc3
{-0.38/21 23} Nb4 {+0.97/7 37} 25. axb6 {+0.19/21 23} Ncxd3+ {+1.27/7 32}
26. Kd2 {-3.37/21 23} Nc5 {+2.13/7 15} 27. Ra1 {-1.72/21 23} Nb7
{+1.96/7 35} 28. Rxa7 {+0.05/21 23} Rd8 {+1.04/7 15} 29. Rxd8+
{+3.50/20 23} Nxd8 {+0.13/8 18} 30. Nd6 {+3.37/22 23} c5 {+0.22/7 23} 31.
Rc7 {+3.18/21 23} Nbc6 {+0.63/7 13} 32. h4 {+3.50/21 23} Rg8 {+0.97/7 24}
33. b7 {+3.95/20 23} c4 {+0.14/7 44} 34. Ke3 {+4.20/20 23} f5 {+0.20/7 30}
35. Kf4 {+5.01/20 23} h6 {+0.91/7 15} 36. Ncb5 {+4.15/20 23} g5+
{+0.45/8 19} 37. hxg5 {+3.54/20 22} hxg5+ {+0.45/8 18} 38. Kf3
{+3.33/21 22} Rg7 {+0.95/8 19} 39. Kf2 {+1.79/20 23} Rxc7 {+1.27/9 1:20}
40. Nxc7 {-0.53/20 25} Ke7 {+1.19/10 1:25} 41. Ncb5 {-1.74/21 45} Nb8
{+1.25/8 8} 42. Nc8+ {-0.77/21 43} Kd7 {+1.88/8 6} 43. Ncd6 {-1.64/21 41}
Nf7 {+1.94/8 4} 44. Nxf7 {-1.89/21 40} Bxf7 {+1.82/9 7} 45. Nd4
{-1.93/21 38} Bg6 {+1.15/9 15} 46. Nf3 {-1.62/21 36} Bf7 {+1.13/9 21} 47.
Ne5+ {+0.71/20 35} Ke7 {+1.33/9 4} 48. Nxf7 {+0.97/22 33} Kxf7 {+1.12/10 7}
49. Ke3 {+0.84/23 32} Ke7 {+1.99/9 11} 50. Kd4 {+0.55/23 31} Kd6
{+1.27/10 6} 51. Kxc4 {+0.52/23 29} Kc6 {+2.01/9 6} 52. Kd4 {+0.48/24 28}
Kd6 {+1.97/9 18} 53. c3 {+2.46/20 27} Nc6+ {+2.03/10 11} 54. Kd3
{-0.42/20 26} Kc7 {+2.07/10 8} 55. Kc4 {-0.40/21 25} Kd6 {+1.35/9 7} 56. b4
{+0.92/20 24} f4 {+1.17/9 5} 57. Kd3 {+1.92/20 23} Kc7 {+1.11/9 7} 58. Ke4
{+1.52/21 22} Na7 {+1.03/10 9} 59. Kf5 {+4.98/20 21} Nb5 {+1.17/11 7} 60.
Kxg5 {+5.20/21 20} Nxc3 {+2.06/11 5} 61. Kxf4 {+5.64/20 19} Nd5+
{+2.04/11 9} 62. Ke5 {+5.17/20 19} Nxb4 {+2.04/12 7} 63. g4 {+6.41/20 18}
Nd3+ {+1.89/12 50} 64. Kf5 {+6.93/20 17} Kxb7 {+2.13/11 10} 65. g5
{+6.68/20 16} Nb4 {+0.52/10 16} 66. Ke6 {+6.74/21 16} Nd3 {+0.31/10 14} 67.
Kf5 {+5.62/21 15} Nb4 {+0.52/10 16} 68. g6 {+5.28/22 15} Nd5 {+0.31/10 24}
69. g7 {+5.28/22 14} Ne7+ {+0.52/10 19} 70. Ke6 {+5.00/22 14} Ng8
{+0.44/10 11} 71. Kf7 {+4.81/22 13} Nh6+ {+0.23/12 51} 72. Kf6
{+4.70/22 13} Ka7 {+0.44/10 11} 73. Kg6 {+4.46/21 12} Ng8 {+0.31/12 16} 74.
Kf5 {+4.45/23 12} Ka8 {+0.65/11 28}
{User adjudication} 1/2-1/2[/pgn]
Great game!
Follow my tournament and some Leela gauntlets live at http://twitch.tv/ccls
Nay Lin Tun
Posts: 708
Joined: Mon Jan 16, 2012 6:34 am

Re: LCZero update

Post by Nay Lin Tun »

My games vs Leela zero.

Got 1-1 in 5 mins blitz. Here is the second game I won, I kept pushing without knowing that leela resigned already. lol ( I lost my first game by dropping pieces). My 5 mins blitz rating is 2000+ in chess.com.
https://www.chess.com/member/drmrboss

My guess is that Leela is around 1600-1800 in blitz now.

[pgn][Event "Computer chess game"]
[Site "DESKTOP-U9VVTOA"]
[Date "2018.03.22"]
[Round "?"]
[White "Nay Lin Tun"]
[Black "Play"]
[Result "1/2-1/2"]
[BlackElo "2000"]
[ECO "A07"]
[Opening "Reti Opening"]
[Time "00:13:07"]
[Variation "KIA, 2.g3"]
[WhiteElo "2400"]
[TimeControl "300"]
[Termination "normal"]
[PlyCount "129"]
[WhiteType "human"]
[BlackType "program"]

1. Nf3 d5 {(d7-d5 h2-h3 Ng8-f6 a2-a4 a7-a5 Nb1-c3) +0.16/21 6} 2. g3 e5
{(e7-e5 Nf3xe5 f7-f6 Ne5-f3 Nb8-c6 a2-a4 Ng8-h6 Nb1-c3) +0.30/22 6} 3. Nxe5
f6 {(f7-f6 Ne5-f3 Nb8-c6 a2-a4 Ng8-h6 Nb1-c3 d5-d4 Nc3-b5) +0.17/22 6} 4.
Nf3 Nc6 {(Nb8-c6 a2-a4 Ng8-h6 Nb1-c3 d5-d4 Nc3-b5 a7-a6 Nb5xd4) 0.00/22 6}
5. d4 Bd7 {(Bc8-d7 c2-c4 d5xc4 d4-d5 Nc6-b4 a2-a3 Nb4xd5 e2-e4 Nd5-b6)
-0.01/22 5} 6. Bg2 Qc8 {(Qd8-c8 Nb1-c3 Bd7-e6 Nf3-h4 g7-g5 Nh4-f3 g5-g4
Nf3-h4 Nc6xd4) +0.62/22 5} 7. O-O Nge7 {(Ng8-e7 c2-c4 d5xc4 Nb1-c3 b7-b5
d4-d5 a7-a6 d5xc6) +0.54/22 5} 8. Nbd2 Be6 {(Bd7-e6 c2-c4 d5xc4 e2-e4 b7-b5
d4-d5 Ne7xd5 e4xd5 Be6xd5 a2-a4 b5-b4 Nd2xc4) +0.33/21 5} 9. e4 dxe4
{(d5xe4 Nd2xe4 Be6-g4 d4-d5 Ne7xd5 Qd1xd5 Bg4-e6 Qd5-d1 Be6-g4 h2-h3)
-0.23/22 5} 10. Nxe4 Bc4 {(Be6-c4 Nf3-h4 Bc4xf1 Kg1xf1 Ne7-g6 d4-d5 Nc6-e5
Nh4xg6 h7xg6 f2-f4 Ne5-g4 h2-h3) -0.68/22 5} 11. Re1 Bd5 {(Bc4-d5 Nf3-h4
Bd5-f7 Ne4-c5 g7-g5 Nc5-e6 Bf7xe6) -0.99/22 5} 12. b3 Bxe4 {(Bd5xe4 Re1xe4
Ra8-b8 Nf3-h4 g7-g5 Qd1-h5+ Ke8-d7) -0.65/22 5} 13. Rxe4 Nb4 {(Nc6-b4
Bc1-a3 Nb4-d5 Nf3-h4 Nd5-c3 Re4xe7+ Bf8xe7 Ba3xe7 Nc3xd1) -1.91/22 5} 14.
Ba3 Nd5 {(Nb4-d5 Qd1-e1 a7-a5 c2-c4 Nd5-b4 Ba3xb4 a5xb4 Nf3-h4 g7-g5 Nh4-f5
Qc8xf5) -2.38/22 5} 15. c4 Nc3 {(Nd5-c3 Qd1-d3 Nc3xe4 Qd3xe4 a7-a6 d4-d5
c7-c6 d5-d6 c6-c5 d6xe7 Bf8xe7 Ra1-e1 Ke8-f7 Qe4xe7+ Kf7-g6) -1.95/22 5}
16. Rxe7+ Bxe7 {(Bf8xe7 Qd1-e1 c7-c5 d4xc5 Ke8-f7 b3-b4 a7-a5 Qe1xc3 a5xb4
Ba3xb4 Be7xc5 Bb4xc5 Qc8xc5 Ra1-d1 Rh8-e8 Nf3-d4) -3.85/22 5} 17. Qe1 c5
{(c7-c5 d4xc5 Ke8-f7 b3-b4 a7-a5 Nf3-d4 a5xb4 Ba3xb4 Nc3xa2 Ra1xa2 Ra8xa2
Bg2-d5+ Kf7-g6 Qe1xe7) -3.96/23 5} 18. Bxc5 Qd7 {(Qc8-d7 Qe1xc3 Be7xc5
d4xc5 Qd7-c6 Nf3-d4 Qc6xc5 b3-b4 Qc5-b6 c4-c5 Qb6-c7 Nd4-e6 Qc7-c6)
-4.16/22 5} 19. Bxe7 Qxe7 {(Qd7xe7 Qe1xc3 Qe7-c7 d4-d5 a7-a6 Nf3-d4 Ke8-f7
a2-a4 Rh8-d8 Nd4-e6) -4.28/22 5} 20. Qxc3 Qc7 {(Qe7-c7 d4-d5 Ke8-f7 a2-a4
Ra8-c8 Nf3-d4 a7-a5 Nd4-e6 Qc7-d7) -4.36/23 5} 21. Re1+ Kf7 {(Ke8-f7 d4-d5
Ra8-d8 Nf3-d4 Qc7-b6 Nd4-e6 Rd8-c8 c4-c5 Qb6-a6 c5-c6 b7xc6) -4.44/22 5}
22. d5 Qd8 {(Qc7-d8 Re1-e6 Ra8-c8 Nf3-d4 Rh8-e8 Re6xe8 Qd8xe8 a2-a4 Qe8-d8
Nd4-e6) -4.73/23 5} 23. Nd4 a5 {(a7-a5 Re1-e6 Rh8-e8 h2-h4 Re8xe6 d5xe6+
Kf7-f8 Bg2xb7 Ra8-b8) -5.77/22 5} 24. Ne6 Qd7 {(Qd8-d7 Qc3-f3 Rh8-c8 c4-c5
Qd7-e8 Qf3-h5+ g7-g6 Qh5xh7+) -5.95/22 5} 25. Bh3 Qe8 {(Qd7-e8 Ne6-c7
Qe8-d8 Nc7xa8 h7-h6 Bh3-e6+ Kf7-g6 Na8-b6 Qd8xb6 c4-c5) -5.69/22 5} 26.
Ng5+ fxg5 {(f6xg5 Re1xe8 Rh8xe8 Qc3-f3+ Kf7-g6 Bh3-g4 Re8-e5 Bg4-e6 Ra8-e8
Qf3-f7+ Kg6-h6 Qf7xe8) -8.56/21 5} 27. Rxe8 Rhxe8 {(Rh8xe8 Qc3-f3+ Kf7-g6
Bh3-f5+ Kg6-f6 Bf5-d7+ Kf6-e7 Bd7xe8 Ra8xe8 Qf3-h5 g7-g6 Qh5xh7+ Ke7-d6
Qh7xg6+) -8.93/22 5} 28. Be6+ Kg6 {(Kf7-g6 Qc3-d3+ Kg6-h6 Kg1-g2 g7-g6
Qd3-d4 Re8-e7 c4-c5 Re7-e8 d5-d6) -8.77/21 5} 29. Qd3+ Kh6 {(Kg6-h6 Kg1-g2
Ra8-d8 Qd3-c2 g7-g6 Qc2-c3 Re8-e7 Qc3xa5 Rd8-b8 d5-d6 Re7xe6) -8.99/22 5}
30. Qf5 Rf8 {(Re8-f8 Qf5-e4 Rf8-f6 c4-c5 g7-g6 d5-d6 Ra8-d8 Qe4xb7 Rf6xe6
c5-c6 Re6xd6) -8.47/21 5} 31. Qh3+ Kg6 {(Kh6-g6 f2-f4 h7-h6 f4-f5+ Kg6-f6
Qh3-h5 Ra8-e8 Qh5-g6+ Kf6-e5 Qg6xg7+ Ke5-d6 Qg7xh6 Rf8-h8 Qh6xh8) -7.74/21
5} 32. g4 h6 {(h7-h6 Qh3-c3 b7-b6 Be6-f5+ Kg6-f7 d5-d6 Rf8-d8 Qc3-e5 Rd8-f8
d6-d7) -6.98/21 5} 33. Qd3+ Kf6 {(Kg6-f6 Qd3-d4+ Kf6-g6 Qd4-e4+ Kg6-f6
Be6-d7 g7-g6 Qe4-e6+ Kf6-g7 c4-c5 Ra8-d8 c5-c6 b7xc6 Bd7xc6 Rf8-f6)
-7.86/21 4} 34. Qf5+ Ke7 {(Kf6-e7 Qf5-g6 Ke7-d6 Qg6xg7 Rf8-h8 Qg7-d7+
Kd6-c5 Qd7xb7 Ra8-b8 Qb7xb8 Rh8xb8 f2-f4 g5xf4) -8.76/21 4} 35. Qg6 Kd6
{(Ke7-d6 Qg6xg7 b7-b6 Kg1-f1 Rf8-h8 Qg7-d7+ Kd6-c5 Qd7-f7 Rh8-f8 Qf7xf8+
Ra8xf8 Kf1-e1) -9.10/22 4} 36. Qxg7 b6 {(b7-b6 Kg1-f1 Rf8-h8 Qg7-d7+ Kd6-e5
Qd7-f7 Rh8-f8 Qf7xf8 Ra8xf8 Kf1-e1 Ke5-d6) -9.18/22 4} 37. Qxh6 Kc7
{(Kd6-c7 Qh6xg5 Kc7-d6 Qg5-h6 Rf8-h8 Qh6xh8 Ra8xh8 g4-g5 Kd6-e7) -9.34/21
4} 38. Qxg5 Kd6 {(Kc7-d6 Kg1-g2 Kd6-c5 Qg5-h6 Rf8-e8 g4-g5 Re8-e7)
-10.23/21 4} 39. h4 Rh8 {(Rf8-h8 Kg1-g2 Ra8-f8 f2-f3 Rf8-e8 Qg5-g6 Re8-e7
h4-h5) -10.26/21 4 Black resigns} 40. h5 Kc7 {(Kd6-c7 Qg5-g6 Kc7-d6 Qg6-g7
Rh8-e8 h5-h6 Re8-g8 Qg7xg8) -10.89/21 3 Black resigns} 41. Qg7+ Kd6
{(Kc7-d6 Kg1-g2 Ra8-b8 h5-h6 Rb8-e8 g4-g5 Rh8-g8 Qg7xg8) -11.99/21 3 Black
resigns} 42. h6 Kc5 {(Kd6-c5 h6-h7 Kc5-b4 d5-d6 a5-a4 b3xa4 Ra8xa4)
-12.13/21 3 Black resigns} 43. h7 Kb4 {(Kc5-b4 f2-f4 Kb4-a3 f4-f5 Ka3xa2
d5-d6 Ka2xb3 Qg7xh8 Ra8xh8 d6-d7) -12.61/20 3 Black resigns} 44. g5 Ka3
{(Kb4-a3 d5-d6 Ka3xa2 d6-d7 Ra8-d8 Qg7xh8 Rd8xh8 d7-d8Q Rh8xh7 g5-g6)
-11.92/20 3 Black resigns} 45. g6 Kxa2 {(Ka3xa2 d5-d6 Ka2xb3 Be6-d5 Ra8-d8
Qg7-f7 Kb3-b4 g6-g7) -12.40/20 3 Black resigns} 46. Qf6 Kxb3 {(Ka2xb3 d5-d6
a5-a4 c4-c5+ Kb3-c2 c5xb6 a4-a3 b6-b7 Ra8-b8 g6-g7 Rh8xh7) -11.77/20 2
Black resigns} 47. Bg8 Raxg8 {(Ra8xg8 h7xg8N Rh8xg8 Qf6-f7 Rg8xg6+ Qf7xg6
Kb3xc4 d5-d6 b6-b5 d6-d7 b5-b4 d7-d8Q b4-b3 Qd8xa5) -11.07/20 2 Black
resigns} 48. hxg8=Q Rxg8 {(Rh8xg8 Qf6-f7 Rg8-d8 g6-g7 a5-a4 g7-g8Q Rd8xg8+
Qf7xg8 a4-a3 d5-d6 a3-a2 d6-d7 a2-a1Q+ Kg1-g2) -11.27/20 2 Black resigns}
49. g7 a4 {(a5-a4 Qf6-f7 Rg8-d8 Qf7-b7 Rd8-g8 d5-d6 Kb3xc4 d6-d7 Rg8xg7+
Kg1-h2 Rg7xd7 Qb7xd7 a4-a3) -10.89/20 2 Black resigns} 50. d6 a3 {(a4-a3
Qf6-f7 a3-a2 Qf7xg8 a2-a1Q+ Kg1-g2 Qa1-f6 Qg8-h7 Qf6xd6 g7-g8Q Qd6-c6+
Kg2-g3 b6-b5 c4xb5+) -10.46/20 2 Black resigns} 51. d7 a2 {(a3-a2 Kg1-h2
Rg8-b8 Qf6-a1 Rb8-d8 Kh2-g3 Rd8xd7 g7-g8Q Rd7-d2 c4-c5+ Kb3-c2 c5xb6
Kc2-d3) -10.44/19 2 Black resigns} 52. d8=Q Rxd8 {(Rg8xd8 Qf6xb6+ Kb3-c2
Qb6xd8 a2-a1Q+ Kg1-h2 Qa1xg7 c4-c5 Qg7-c3 Qd8-e7 Qc3-d3 c5-c6 Qd3-d2 c6-c7)
-5.11/19 2} 53. Qxd8 a1=Q+ {(a2-a1Q+ Kg1-h2 Qa1xg7 Qd8xb6+ Kb3xc4 Qb6-a6+
Kc4-b3 Qa6-b5+ Kb3-c3 Qb5-a6 Qg7-d4 Kh2-g3 Qd4-d2) -2.00/19 2} 54. Kh2 Qxg7
{(Qa1xg7 Qd8xb6+ Kb3xc4 Qb6-e6+ Kc4-d3 Qe6-a6+ Kd3-d2 Kh2-h3 Kd2-c3 Kh3-h2
Qg7-d4) -1.86/21 2} 55. Qh4 Qg6 {(Qg7-g6 Qh4-d4 Kb3-c2 c4-c5 b6xc5 Qd4xc5+
Kc2-d3 Qc5-d5+ Kd3-c3 Qd5-e5+) +0.54/19 1} 56. Qg3+ Qxg3+ {(Qg6xg3+ f2xg3
Kb3xc4 g3-g4 Kc4-d4 Kh2-g3 Kd4-e4 Kg3-h4 b6-b5 g4-g5 Ke4-f5 Kh4-h5 b5-b4
g5-g6 b4-b3 g6-g7 b3-b2 g7-g8Q b2-b1Q Qg8-f7+ Kf5-e5) +1.88/18 1} 57. fxg3
Kxc4 {(Kb3xc4 g3-g4 Kc4-d4 Kh2-g3 Kd4-e4 Kg3-h4 b6-b5 g4-g5 Ke4-f5 Kh4-h5
b5-b4 Kh5-h6 b4-b3 g5-g6 b3-b2 g6-g7 b2-b1Q g7-g8Q Qb1-b7 Qg8-f8+ Kf5-e6
Kh6-g6 Qb7-d7) +1.88/19 1} 58. g4 Kd5 {(Kc4-d5 Kh2-g3 b6-b5 g4-g5 Kd5-e5
g5-g6 Ke5-f6 Kg3-f4 Kf6xg6 Kf4-e5 b5-b4 Ke5-d4 b4-b3 Kd4-c3) +2.08/20 1}
59. Kg3 b5 {(b6-b5 Kg3-f4 b5-b4 Kf4-e3 Kd5-e5 Ke3-d3 Ke5-f4 Kd3-c4 Kf4xg4
Kc4xb4) +1.27/20 1} 60. Kf4 b4 {(b5-b4 Kf4-e3 Kd5-e5 Ke3-d3 Ke5-f4 Kd3-c4
Kf4xg4 Kc4xb4) +0.15/19 1} 61. Ke3 Ke5 {(Kd5-e5 Ke3-d3 Ke5-f4 Kd3-c4 Kf4xg4
Kc4xb4) 0.00/19 1} 62. Kd2 Kf4 {(Ke5-f4 Kd2-d3 Kf4xg4 Kd3-c4 Kg4-f4 Kc4xb4)
+0.14/19 1} 63. Kc2 Kxg4 {(Kf4xg4 Kc2-b3 Kg4-f4 Kb3xb4) +0.06/19 1} 64. Kb3
Kf4 {(Kg4-f4 Kb3xb4) +0.04/18 1} 65. Kxb4 {Insufficient material} 1/2-1/2
[/pgn][/url]
Nay Lin Tun
Posts: 708
Joined: Mon Jan 16, 2012 6:34 am

Re: LCZero update

Post by Nay Lin Tun »

In both games, Leela chose the same opening! :(
User avatar
Ovyron
Posts: 4556
Joined: Tue Jul 03, 2007 4:30 am

Re: LCZero update

Post by Ovyron »

lucasart wrote:At least one advantage of this approach is that you can create human-like weak levels, which is not really possible with alpha beta. Snapshots of the NN weights along the way would give you that.

Although you may end up with unhuman play in the opposite direction: reasonably good positional play but horrendous tactics. Basically too human like to be credible.
The thing with humans is that they play with an erratic strength, you may have some 1200 rating player that plays like a 2900 elo entity 30% of its moves, 2500 20% of its moves, 1800 40% of its moves and ???? 10% of its moves. This unknown rating can make this player give up their queen or miss a mate in 1, or basically just be completely random now and then, and it's a question of time when the blunder will be played and would allow it to lose a game against anybody else, making the strength of the rest of the moves irrelevant.

This explains why the weaker the players the more erractic the strength, and you see more often huge swings of evaluation, while they get rarer the stronger the players (but even GMs will have some chance of making those ???? elo moves that you'd not see an engine with the same elo to make.)

So I believe the best shot at emulating weak human play by NNs is to mix them up and use different ones for each move. Adversarial Networks could work for this, as you have a NN trying to emulate human play by switching the elo per move as humans do, while another NN is feed those games and gets better at identifying the ones player by real humans.

Eventually you have a NN that can tell if a side was played by a human most of the time, and another that can produce moves that can trick the former. My claim is this latter one would be able to fool most humans into thinking it's a human playing, since the other NN would already be better at identifying computer play than humans.
Your beliefs create your reality, so be careful what you wish for.
Damir
Posts: 2801
Joined: Mon Feb 11, 2008 3:53 pm
Location: Denmark
Full name: Damir Desevac

Re: LCZero update

Post by Damir »

LCZero is drinking a lot of Vodka..... :lol: :lol: