Fluctuations in Stockfish evaluation

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

Moderators: hgm, Rebel, chrisw

Javier Ros
Posts: 200
Joined: Fri Oct 12, 2012 12:48 pm
Location: Seville (SPAIN)
Full name: Javier Ros

Fluctuations in Stockfish evaluation

Post by Javier Ros »

Stockfish's progress is impressive, especially after nnue.

However, the fluctuations in the evaluation are still there.
For example at initial position with one thread, discarding the first two minutes, we have with version Stockfish_13_win_x64_bmi2 with 1 Gb RAM in a i7 7700HQ after 30 minutes variations from +0.14 to +0.42 and alternating best moves between d4, c4 and e4, final best move e4 +0.21 ply 44/54-

and version Stockfish_13_win_x64_avx2 with 1 Gb RAM in a Ryzen 7 2700x after 30 minutes variations from +0.14 to +0.34 and alternating best moves between e4, d4 and c4, final best move c4 +0.26 ply 43/59

I wonder what is the origin of these unpleasant fluctuations and if there is a solution.
On the other hand, I don't understand the discrepancy between the results of the bmi2 and avx versions.

i7 7700HQ
FEN: rnbqkbnr/pppppppp/8/8/8/8/PPPPPPPP/RNBQKBNR w KQkq - 0 1

Stockfish_13_win_x64_bmi2:
NNUE evaluation using nn-62ef826d1a6d.nnue enabled

33/42 02:01 112.723.623 927.033 +0,23 1.d2-d4 Ng8-f6 2.c2-c4 e7-e6 3.Ng1-f3 d7-d5 4.Nb1-c3 Bf8-e7 5.g2-g3 O-O 6.Bf1-g2 d5xc4 7.Qd1-a4 c7-c6 8.Qa4xc4 b7-b5 9.Qc4-b3 a7-a5 10.O-O Bc8-b7 11.Bc1-g5 Nb8-d7 12.Nf3-e5 a5-a4 13.Qb3-c2 Nd7xe5 14.d4xe5 Nf6-d7 15.Bg5xe7 Qd8xe7 16.f2-f4 Qe7-c5+ 17.Rf1-f2 b5-b4
34/46+ 02:40 148.577.172 925.662 +0,31 1.c2-c4
34/46- 02:58 164.495.839 921.122 +0,14 1.c2-c4 e7-e5
34/46+ 04:09 228.962.917 919.356 +0,26 1.e2-e4
34/46 04:30 248.303.538 919.019 +0,25 1.e2-e4 e7-e6 2.d2-d4 d7-d5 3.Nb1-c3 Ng8-f6 4.e4-e5 Nf6-d7 5.Nc3-e2 c7-c5 6.c2-c3 Qd8-b6 7.Ng1-f3 Nb8-c6 8.g2-g3 c5xd4 9.c3xd4 Bf8-b4+ 10.Bc1-d2 a7-a5 11.Bf1-h3 Bb4xd2+ 12.Qd1xd2 Qb6-b4 13.Qd2xb4 a5xb4 14.Ke1-d2 Nd7-b6 15.b2-b3 Ke8-e7 16.Rh1-c1 Bc8-d7 17.Ne2-f4
35/43+ 04:48 264.801.996 918.080 +0,34 1.e2-e4
35/43+ 04:52 268.629.346 918.193 +0,42 1.e2-e4
35/43- 05:03 278.267.739 916.632 +0,17 1.e2-e4 e7-e6
35/46+ 05:36 305.839.963 909.550 +0,36 1.e2-e4
35/46 05:40 309.541.736 909.820 +0,37 1.e2-e4 e7-e6 2.d2-d4 d7-d5 3.Nb1-c3 Ng8-f6 4.Bc1-g5 Bf8-e7 5.e4-e5 Nf6-d7 6.Bg5xe7 Qd8xe7 7.Qd1-d2 O-O 8.f2-f4 c7-c5 9.Ng1-f3 Nb8-c6 10.O-O-O a7-a6 11.g2-g4 b7-b5 12.h2-h4 f7-f6 13.e5xf6 Nd7xf6 14.d4xc5 Qe7xc5 15.Bf1-d3 Nf6xg4 16.Rh1-g1 Ng4-f2 17.Bd3xh7+ Kg8xh7 18.Rd1-f1
36/44- 06:02 329.768.348 910.212 +0,29 1.e2-e4 e7-e6
36/44- 06:30 355.266.460 910.750 +0,21 1.e2-e4 e7-e5
36/44+ 06:41 365.553.131 910.908 +0,29 1.e2-e4
36/44 06:46 370.216.738 910.798 +0,26 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 a7-a6 4.Bb5-a4 Ng8-f6 5.O-O Nf6xe4 6.d2-d4 b7-b5 7.Ba4-b3 d7-d5 8.d4xe5 Bc8-e6 9.c2-c3 Bf8-c5 10.Qd1-d3 O-O 11.Bc1-e3 Bc5xe3 12.Qd3xe3 Nc6-e7 13.Bb3-c2 Be6-f5 14.Nb1-d2 Ne4xd2 15.Qe3xd2 Bf5xc2 16.Qd2xc2 h7-h6 17.a2-a4 c7-c5 18.a4xb5 a6xb5 19.Ra1xa8
37/48+ 07:07 389.903.701 911.222 +0,34 1.e2-e4
37/48- 07:28 408.460.257 911.711 +0,18 1.e2-e4 e7-e5
37/48+ 07:48 427.277.778 911.950 +0,30 1.e2-e4
37/48 07:58 436.138.449 912.173 +0,32 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.Bc1-f4 Re8xe1 12.Qd1xe1 Nd6-e8 13.c2-c3 a7-a5 14.Nb1-d2 d7-d5 15.Bf1-d3 a5-a4 16.Nd2-f3 a4-a3 17.b2-b4 Ne8-d6 18.Qe1-e2 Bc8-f5 19.Bd3xf5 Nd6xf5 20.Qe2-b5 b7-b6
38/44- 09:17 507.342.185 910.604 +0,24 1.e2-e4 e7-e5
38/45+ 09:30 519.454.524 910.142 +0,32 1.e2-e4
38/45 09:33 521.726.724 910.236 +0,26 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.Bc1-f4 Re8xe1 12.Qd1xe1 Nd6-e8 13.Bf1-d3 Bf6xd4 14.Bd3xh7+ Kg8xh7 15.Qe1-e4+ Kh7-g8 16.Qe4xd4 d7-d5 17.Nb1-d2 c7-c6 18.c2-c4 Ne8-f6 19.h2-h3 Bc8-f5 20.g2-g4
39/48- 10:57 597.679.603 908.516 +0,18 1.e2-e4 c7-c5
39/48+ 11:17 614.270.423 907.292 +0,26 1.e2-e4
39/48 11:39 634.154.420 906.100 +0,31 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.Bc1-f4 Re8xe1 12.Qd1xe1 Nd6-e8 13.c2-c3 a7-a5 14.Nb1-d2 d7-d5 15.Bf1-d3 a5-a4 16.Qe1-e3 Qd8-e7 17.Qe3-g3 Ne8-d6 18.a2-a3 Bc8-d7 19.Bf4xd6 Qe7xd6 20.Qg3xd6 c7xd6
40/47 13:38 739.243.466 903.525 +0,25 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.Bc1-f4 Re8xe1 12.Qd1xe1 Nd6-e8 13.c2-c3 a7-a5 14.a2-a4 d7-d6 15.Nb1-d2 Bc8-e6 16.h2-h3 g7-g6 17.Qe1-e4 c7-c6 18.Qe4-e3 Bf6-e7 19.c3-c4 Ne8-g7 20.Bf1-d3 Ng7-f5 21.Bd3xf5 Be6xf5 22.d4-d5
41/53- 15:28 838.052.070 902.356 +0,17 1.e2-e4 e7-e5
41/53+ 15:58 864.887.871 902.063 +0,25 1.e2-e4
41/53 16:05 870.885.354 902.053 +0,25 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.Bc1-f4 Re8xe1 12.Qd1xe1 Nd6-e8 13.c2-c3 d7-d5 14.a2-a4 Ne8-d6 15.Nb1-d2 a7-a5 16.Bf1-d3 Bc8-f5 17.Qe1-e3 Bf5xd3 18.Qe3xd3 Qd8-d7 19.g2-g3 Ra8-e8 20.Bf4xd6 Qd7xd6 21.Kg1-g2 Qd6-d7 22.Nd2-f3 c7-c6 23.h2-h3
42/51- 18:39 1.009.321.730 901.979 +0,17 1.e2-e4 e7-e5
42/51+ 19:19 1.045.305.608 901.815 +0,25 1.e2-e4
42/51 19:32 1.057.554.324 901.762 +0,21 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.Bc1-f4 Re8xe1 12.Qd1xe1 Nd6-e8 13.c2-c3 d7-d5 14.a2-a4 a7-a5 15.Bf1-d3 g7-g6 16.Nb1-d2 Ne8-g7 17.Nd2-f3 Bc8-f5 18.Bd3xf5 Ng7xf5 19.g2-g3 Qd8-d7 20.Qe1-e2 c7-c6 21.Qe2-d2 Ra8-e8 22.h2-h4 Nf5-g7
43/46- 22:50 1.234.101.899 900.226 +0,13 1.e2-e4 e7-e5
43/55+ 24:21 1.314.457.234 899.644 +0,21 1.e2-e4
43/55 24:56 1.346.285.181 899.530 +0,21 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.Bc1-f4 Re8xe1 12.Qd1xe1 Nd6-e8 13.c2-c3 d7-d5 14.Bf1-d3 g7-g6 15.Nb1-d2 Ne8-g7 16.Nd2-f3 c7-c6 17.Bf4-h6 a7-a5 18.Qe1-e3 Bc8-g4 19.Nf3-e5 Ng7-f5 20.Bd3xf5 Bg4xf5 21.Ra1-e1 a5-a4 22.h2-h3
44/54- 31:57 1.722.138.757 897.971 +0,12 1.e2-e4 e7-e5

Ryzen 7 2700x
FEN: rnbqkbnr/pppppppp/8/8/8/8/PPPPPPPP/RNBQKBNR w KQkq - 0 1

Stockfish_13_win_x64_avx2:
NNUE evaluation using nn-62ef826d1a6d.nnue enabled

36/50- 02:22 145.261.236 1.017.891 +0,28 1.e2-e4 e7-e5
36/50 02:47 170.761.372 1.017.605 +0,25 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.c2-c3 Re8xe1 12.Qd1xe1 Nd6-e8 13.Bc1-f4 d7-d5 14.Bf1-d3 g7-g6 15.Nb1-d2 Ne8-g7 16.Nd2-f3 Bc8-f5 17.Bd3xf5 Ng7xf5 18.h2-h3 c7-c6 19.Qe1-d2 Nf5-d6 20.Ra1-e1 Nd6-e4 21.Qd2-e3 Qd8-d7 22.Nf3-e5
37/47- 03:17 200.367.178 1.015.823 +0,17 1.e2-e4 e7-e5
37/49 03:41 224.491.256 1.015.420 +0,17 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.c2-c3 Re8xe1 12.Qd1xe1 Nd6-e8 13.a2-a4 a7-a5 14.Bc1-f4 d7-d5 15.Qe1-e3 Bc8-f5 16.Nb1-d2 h7-h6 17.Nd2-f3 c7-c6 18.Ra1-e1 Ne8-c7 19.Bf4-e5 Nc7-e6 20.Be5xf6 Qd8xf6
38/51 04:17 261.164.439 1.014.439 +0,17 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.c2-c3 Re8xe1 12.Qd1xe1 Nd6-e8 13.a2-a4 a7-a5 14.Bc1-f4 d7-d5 15.Bf1-d3 g7-g6 16.Qe1-e2 Ne8-d6 17.Nb1-d2 c7-c6 18.Ra1-e1 Bc8-f5 19.g2-g3 Bf5xd3 20.Qe2xd3 Bf6-g5 21.Bf4xd6 Bg5xd2 22.Qd3xd2 Qd8xd6
39/49+ 06:18 382.983.236 1.011.764 +0,25 1.d2-d4
39/50+ 06:24 388.872.084 1.012.155 +0,34 1.d2-d4
39/51 07:13 438.409.469 1.011.329 +0,15 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.c2-c3 Re8xe1 12.Qd1xe1 Nd6-e8 13.Bc1-f4 d7-d5 14.Bf1-d3 g7-g6 15.h2-h3 Ne8-g7 16.Nb1-d2 Bc8-f5 17.Bd3xf5 Ng7xf5 18.Nd2-f3 c7-c6 19.g2-g3 Qd8-d7 20.Kg1-g2 Ra8-e8 21.Qe1-d2 Nf5-d6 22.Ra1-e1 Re8xe1 23.Qd2xe1 Bf6-g7
40/54+ 07:37 463.026.188 1.011.042 +0,23 1.e2-e4
40/54 08:49 535.027.657 1.009.886 +0,21 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.c2-c3 Re8xe1 12.Qd1xe1 Nd6-e8 13.Bc1-f4 d7-d5 14.Nb1-d2 Bc8-f5 15.Qe1-e3 c7-c6 16.Ra1-e1 h7-h6 17.Qe3-g3 Bf6-g5 18.Bf4xg5 h6xg5 19.Bf1-e2 Bf5-g6 20.f2-f4 g5xf4 21.Qg3xf4 f7-f6
41/54+ 17:48 1.078.531.366 1.009.298 +0,29 1.c2-c4
41/54 19:09 1.160.542.452 1.009.212 +0,14 1.c2-c4 Ng8-f6 2.Ng1-f3 e7-e6 3.g2-g3 d7-d5 4.Bf1-g2 d5xc4 5.Qd1-a4+ Bc8-d7 6.Qa4xc4 c7-c5 7.d2-d4 Nb8-c6 8.O-O c5xd4 9.Nf3xd4 Ra8-c8 10.Nb1-c3 Nc6xd4 11.Qc4xd4 Bf8-c5 12.Qd4-f4 Bd7-c6 13.Bg2xc6+ Rc8xc6 14.Rf1-d1 Qd8-c8 15.b2-b4 Bc5-b6 16.Nc3-a4 Bb6-c7 17.Qf4-e3 O-O 18.Bc1-b2 Nf6-g4 19.Qe3-b3 Bc7-e5 20.Ra1-c1 b7-b6 21.Rc1xc6 Qc8xc6 22.Bb2xe5 Ng4xe5 23.b4-b5
42/51+ 20:30 1.242.678.825 1.009.545 +0,23 1.c2-c4
42/51+ 20:47 1.259.308.192 1.009.454 +0,31 1.c2-c4
42/51 21:46 1.318.280.276 1.009.331 +0,13 1.c2-c4 Ng8-f6 2.Ng1-f3 e7-e6 3.d2-d4 d7-d5 4.Nb1-c3 d5xc4 5.e2-e4 Bf8-b4 6.Bc1-g5 c7-c5 7.Bf1xc4 c5xd4 8.Nf3xd4 Bb4xc3+ 9.b2xc3 Qd8-a5 10.Nd4-b5 Nf6xe4 11.Qd1-d4 O-O 12.Qd4xe4 a7-a6 13.Bc4-d3 f7-f5 14.Qe4-b4 a6xb5 15.Qb4xa5 Ra8xa5 16.Bg5-e7 Rf8-e8 17.Be7-b4 Ra5-a8 18.Bd3xb5 Bc8-d7 19.Bb5-c4 Bd7-c6 20.O-O Kg8-f7 21.Bc4-b3 Ra8-a6 22.Rf1-d1 Nb8-d7 23.a2-a4
43/59+ 24:31 1.486.668.887 1.010.557 +0,22 1.c2-c4
43/59+ 28:17 1.715.530.258 1.010.397 +0,30 1.c2-c4
43/59 29:13 1.771.801.468 1.010.411 +0,26 1.c2-c4 Ng8-f6 2.Ng1-f3 e7-e6 3.g2-g3 d7-d5 4.Bf1-g2 d5xc4 5.Qd1-a4+ c7-c6 6.Qa4xc4 b7-b5 7.Qc4-b3 Bc8-b7 8.O-O Nb8-d7 9.d2-d4 a7-a6 10.Nf3-e5 Nd7xe5 11.d4xe5 Nf6-d5 12.a2-a4 Bf8-e7 13.Nb1-c3 O-O 14.Nc3xd5 c6xd5 15.Bc1-e3 b5-b4 16.a4-a5 Bb7-c6 17.Be3-b6 Qd8-e8 18.Rf1-d1 Ra8-c8 19.Ra1-c1 Bc6-a4 20.Rc1xc8 Ba4xb3 21.Rc8xe8
Top
Javier Ros
Posts: 200
Joined: Fri Oct 12, 2012 12:48 pm
Location: Seville (SPAIN)
Full name: Javier Ros

Re: Fluctuations in Stockfish evaluation

Post by Javier Ros »

I have repeated the experiment with the latest dev versions obtaining similar results.

version Stockfish_21061411_x64_modern with 1 Gb RAM in a i7 7700HQ after 30 minutes variations from +0.16 to +0.45 and alternating best moves between d4, c4 and e4, final best move d4

and version Stockfish_21061411_x64_avx2 with 1 Gb RAM in a Ryzen 7 2700x after 30 minutes variations from +0.16 to +0.45 and alternating best moves between e4, d4 and c4, final best move d4

i7 7700HQ
FEN: rnbqkbnr/pppppppp/8/8/8/8/PPPPPPPP/RNBQKBNR w KQkq - 0 1

Stockfish_21061411_x64_modern:
NNUE evaluation using nn-8e47cf062333.nnue enabled

33/45 02:05 82.680.871 657.601 +0,31 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.c2-c3 Re8xe1 12.Qd1xe1 Nd6-e8 13.d4-d5 c7-c6 14.d5xc6 d7xc6 15.Nb1-d2 Bc8-e6 16.Nd2-e4 Qd8-b6 17.b2-b3 Ra8-d8 18.Bc1-f4 Kg8-h8 19.Ne4xf6 Ne8xf6
34/45 02:37 103.535.926 656.429 +0,30 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.c2-c3 Re8xe1 12.Qd1xe1 Nd6-e8 13.Bc1-f4 d7-d5 14.Nb1-d2 Bc8-f5 15.Qe1-e3 Bf6-e7 16.Ra1-e1 Be7-d6 17.Bf4-e5 Bf5-g6 18.h2-h3 f7-f6 19.Be5-g3 c7-c6 20.c3-c4 Ne8-c7 21.c4xd5 Bd6xg3
35/46+ 03:00 118.127.316 655.800 +0,38 1.e2-e4
35/46 03:04 120.741.259 655.571 +0,35 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.c2-c3 Re8xe1 12.Qd1xe1 Nd6-e8 13.Bc1-f4 d7-d5 14.Nb1-d2 Bc8-f5 15.a2-a4 c7-c6 16.a4-a5 Ne8-c7 17.Bf4-g3 Nc7-e6 18.Qe1-e3 a7-a6 19.Nd2-b3 Bf6-e7 20.Qe3-e2 Kg8-h8 21.f2-f3
36/45+ 03:35 141.373.473 655.019 +0,43 1.e2-e4
36/47 03:46 148.569.488 654.984 +0,32 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.c2-c3 Re8xe1 12.Qd1xe1 Nd6-e8 13.a2-a4 a7-a5 14.Bc1-f4 d7-d5 15.Nb1-d2 c7-c6 16.Bf1-d3 g7-g6 17.Nd2-f3 Ne8-g7 18.Qe1-d2 Bc8-f5 19.Bd3xf5 Ng7xf5 20.h2-h3 Bf6-e7 21.g2-g4 Nf5-h4 22.Nf3xh4 Be7xh4 23.Bf4-e3 Bh4-e7
37/49+ 03:54 153.631.483 655.094 +0,40 1.e2-e4
37/49 04:08 162.942.710 654.724 +0,32 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.c2-c3 Re8xe1 12.Qd1xe1 Nd6-e8 13.Bc1-f4 d7-d5 14.a2-a4 a7-a5 15.Nb1-d2 c7-c6 16.Bf1-d3 g7-g6 17.Nd2-f3 Ne8-g7 18.Qe1-d2 Bc8-f5 19.Bd3xf5 Ng7xf5 20.h2-h3 Nf5-g7 21.Ra1-e1 Bf6-e7 22.g2-g3 Ng7-e6
38/48+ 04:22 171.675.985 653.941 +0,40 1.e2-e4
38/48 05:53 229.944.860 649.721 +0,45 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.c2-c3 Re8xe1 12.Qd1xe1 Nd6-e8 13.Bc1-f4 d7-d5 14.Nb1-d2 Bc8-f5 15.a2-a4 c7-c6 16.a4-a5 Ne8-c7 17.Nd2-f3 Nc7-e6 18.Bf4-g3 c6-c5 19.d4xc5 Ne6xc5 20.Bg3-e5 Ra8-c8 21.Be5xf6 Qd8xf6
39/48- 06:52 267.384.017 648.376 +0,37 1.e2-e4 e7-e5
39/48- 07:18 284.387.367 648.935 +0,28 1.e2-e4 e7-e5
39/49 13:42 533.012.165 647.678 +0,28 1.c2-c4 e7-e5 2.g2-g3 Ng8-f6 3.Bf1-g2 c7-c6 4.d2-d4 e5xd4 5.Qd1xd4 d7-d5 6.Ng1-f3 Bf8-e7 7.c4xd5 Qd8xd5 8.Nb1-c3 Qd5-a5 9.O-O O-O 10.Bc1-f4 Rf8-d8 11.Qd4-e3 Rd8-e8 12.Qe3-c1 Nb8-d7 13.Rf1-d1 Nd7-f8 14.h2-h3 Bc8-f5 15.Nf3-d4 Nf8-e6 16.e2-e4 Ne6xd4 17.Rd1xd4 Bf5-e6 18.Qc1-c2 Nf6-d7 19.a2-a3 Qa5-b6 20.Rd4-d2
40/50- 16:28 641.183.369 648.434 +0,20 1.c2-c4 e7-e5
40/50+ 17:26 678.376.182 648.009 +0,28 1.e2-e4
40/50 17:31 681.298.432 647.968 +0,26 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.c2-c3 Re8xe1 12.Qd1xe1 Nd6-e8 13.Bc1-f4 d7-d5 14.Bf1-d3 g7-g6 15.Nb1-d2 Ne8-g7 16.h2-h3 Bc8-f5 17.Bd3xf5 Ng7xf5 18.Nd2-f3 c7-c6 19.Qe1-e2 Nf5-g7 20.Ra1-e1 h7-h5 21.Nf3-e5 Bf6xe5 22.Qe2xe5 Qd8-a5
41/54+ 22:57 880.344.233 639.285 +0,34 1.e2-e4
41/54 23:19 894.915.487 639.455 +0,33 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.c2-c3 Re8xe1 12.Qd1xe1 Nd6-e8 13.Bc1-f4 d7-d5 14.Bf1-d3 g7-g6 15.Nb1-d2 Ne8-g7 16.h2-h3 Bc8-f5 17.Bd3xf5 Ng7xf5 18.Nd2-f3 c7-c6 19.Qe1-e2 Qd8-e7 20.Ra1-e1 Qe7xe2 21.Re1xe2 Kg8-h8 22.a2-a4 Kh8-g7 23.g2-g3
42/50- 26:40 1.020.929.672 637.984 +0,25 1.e2-e4 e7-e5
42/50+ 30:11 1.154.713.752 637.535 +0,33 1.d2-d4
42/50- 32:23 1.237.216.078 636.734 +0,16 1.d2-d4 Ng8-f6


Ryzen 7 2700x
Stockfish_21061411_x64_avx2:
NNUE evaluation using nn-8e47cf062333.nnue enabled

35/46+ 02:11 118.127.316 896.683 +0,38 1.e2-e4
35/46 02:14 120.741.259 896.684 +0,35 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.c2-c3 Re8xe1 12.Qd1xe1 Nd6-e8 13.Bc1-f4 d7-d5 14.Nb1-d2 Bc8-f5 15.a2-a4 c7-c6 16.a4-a5 Ne8-c7 17.Bf4-g3 Nc7-e6 18.Qe1-e3 a7-a6 19.Nd2-b3 Bf6-e7 20.Qe3-e2 Kg8-h8 21.f2-f3
36/45+ 02:37 141.373.473 895.846 +0,43 1.e2-e4
36/47 02:45 148.569.488 895.698 +0,32 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.c2-c3 Re8xe1 12.Qd1xe1 Nd6-e8 13.a2-a4 a7-a5 14.Bc1-f4 d7-d5 15.Nb1-d2 c7-c6 16.Bf1-d3 g7-g6 17.Nd2-f3 Ne8-g7 18.Qe1-d2 Bc8-f5 19.Bd3xf5 Ng7xf5 20.h2-h3 Bf6-e7 21.g2-g4 Nf5-h4 22.Nf3xh4 Be7xh4 23.Bf4-e3 Bh4-e7
37/49+ 02:51 153.631.483 895.789 +0,40 1.e2-e4
37/49 03:02 162.942.710 895.092 +0,32 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.c2-c3 Re8xe1 12.Qd1xe1 Nd6-e8 13.Bc1-f4 d7-d5 14.a2-a4 a7-a5 15.Nb1-d2 c7-c6 16.Bf1-d3 g7-g6 17.Nd2-f3 Ne8-g7 18.Qe1-d2 Bc8-f5 19.Bd3xf5 Ng7xf5 20.h2-h3 Nf5-g7 21.Ra1-e1 Bf6-e7 22.g2-g3 Ng7-e6
38/48+ 03:11 171.675.985 894.448 +0,40 1.e2-e4
38/48 04:18 229.944.860 890.820 +0,45 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.c2-c3 Re8xe1 12.Qd1xe1 Nd6-e8 13.Bc1-f4 d7-d5 14.Nb1-d2 Bc8-f5 15.a2-a4 c7-c6 16.a4-a5 Ne8-c7 17.Nd2-f3 Nc7-e6 18.Bf4-g3 c6-c5 19.d4xc5 Ne6xc5 20.Bg3-e5 Ra8-c8 21.Be5xf6 Qd8xf6
39/48- 05:00 267.384.017 889.651 +0,37 1.e2-e4 e7-e5
39/48- 05:19 284.387.367 890.508 +0,28 1.e2-e4 e7-e5
39/49 09:59 533.012.165 888.569 +0,28 1.c2-c4 e7-e5 2.g2-g3 Ng8-f6 3.Bf1-g2 c7-c6 4.d2-d4 e5xd4 5.Qd1xd4 d7-d5 6.Ng1-f3 Bf8-e7 7.c4xd5 Qd8xd5 8.Nb1-c3 Qd5-a5 9.O-O O-O 10.Bc1-f4 Rf8-d8 11.Qd4-e3 Rd8-e8 12.Qe3-c1 Nb8-d7 13.Rf1-d1 Nd7-f8 14.h2-h3 Bc8-f5 15.Nf3-d4 Nf8-e6 16.e2-e4 Ne6xd4 17.Rd1xd4 Bf5-e6 18.Qc1-c2 Nf6-d7 19.a2-a3 Qa5-b6 20.Rd4-d2
40/50- 12:01 641.183.369 888.407 +0,20 1.c2-c4 e7-e5
40/50+ 12:43 678.376.182 888.164 +0,28 1.e2-e4
40/50 12:47 681.298.432 888.187 +0,26 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.c2-c3 Re8xe1 12.Qd1xe1 Nd6-e8 13.Bc1-f4 d7-d5 14.Bf1-d3 g7-g6 15.Nb1-d2 Ne8-g7 16.h2-h3 Bc8-f5 17.Bd3xf5 Ng7xf5 18.Nd2-f3 c7-c6 19.Qe1-e2 Nf5-g7 20.Ra1-e1 h7-h5 21.Nf3-e5 Bf6xe5 22.Qe2xe5 Qd8-a5
41/54+ 16:32 880.344.233 887.039 +0,34 1.e2-e4
41/54 16:48 894.915.487 887.079 +0,33 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.c2-c3 Re8xe1 12.Qd1xe1 Nd6-e8 13.Bc1-f4 d7-d5 14.Bf1-d3 g7-g6 15.Nb1-d2 Ne8-g7 16.h2-h3 Bc8-f5 17.Bd3xf5 Ng7xf5 18.Nd2-f3 c7-c6 19.Qe1-e2 Qd8-e7 20.Ra1-e1 Qe7xe2 21.Re1xe2 Kg8-h8 22.a2-a4 Kh8-g7 23.g2-g3
42/50- 19:11 1.020.929.672 886.930 +0,25 1.e2-e4 e7-e5
42/50+ 21:41 1.154.713.752 887.461 +0,33 1.d2-d4
42/50- 23:14 1.237.216.078 887.362 +0,16 1.d2-d4 Ng8-f6
42/52 28:24 1.512.795.138 887.788 +0,17 1.d2-d4 Ng8-f6 2.c2-c4 e7-e6 3.Ng1-f3 d7-d5 4.g2-g3 Bf8-b4+ 5.Bc1-d2 Bb4-e7 6.Bf1-g2 O-O 7.O-O c7-c6 8.Qd1-c2 b7-b6 9.Rf1-d1 Nb8-d7 10.b2-b3 Nf6-e4 11.Nb1-c3 Ne4xd2 12.Nf3xd2 Bc8-a6 13.e2-e4 Ra8-c8 14.Nd2-f1 d5xe4 15.Nc3xe4 Qd8-c7 16.Nf1-e3 Rf8-d8 17.Ra1-b1 Ba6-b7 18.c4-c5 f7-f5 19.Ne4-c3 b6xc5
43/49+ 30:01 1.599.056.233 887.803 +0,25 1.d2-d4
43/49+ 30:20 1.617.008.157 888.049 +0,34 1.d2-d4
43/53 33:06 1.764.287.565 888.177 +0,36 1.d2-d4 Ng8-f6 2.c2-c4 c7-c6 3.Ng1-f3 d7-d5 4.Nb1-c3 e7-e6 5.Bc1-g5 Nb8-d7 6.e2-e3 Bf8-e7 7.Qd1-c2 O-O 8.a2-a3 h7-h6 9.Bg5-h4 b7-b6 10.c4xd5 c6xd5 11.Bf1-d3 Bc8-b7 12.O-O Ra8-c8 13.Rf1-c1 g7-g5 14.Bh4-g3 Nf6-e4 15.Qc2-e2 Ne4xc3 16.b2xc3 Nd7-f6 17.Nf3-e5 Nf6-e4 18.c3-c4 d5xc4 19.Bd3xc4 Bb7-d5 20.Bc4-d3 Ne4xg3 21.h2xg3 Rc8xc1+ 22.Ra1xc1 Be7xa3
44/52- 39:11 2.089.695.367 888.666 +0,28 1.d2-d4 Ng8-f6
Top
Cornfed
Posts: 511
Joined: Sun Apr 26, 2020 11:40 pm
Full name: Brian D. Smith

Re: Fluctuations in Stockfish evaluation

Post by Cornfed »

I wonder if setting contempt to zero would help? I only ever use zero.
Top
syzygy
Posts: 5557
Joined: Tue Feb 28, 2012 11:56 pm

Re: Fluctuations in Stockfish evaluation

Post by syzygy »

Javier Ros wrote: ↑Mon Jun 14, 2021 6:45 pm I wonder what is the origin of these unpleasant fluctuations and if there is a solution.
What would be the point of searching longer/deeper if fluctuations did not exist? If you don't want fluctuations, search to depth 1.
On the other hand, I don't understand the discrepancy between the results of the bmi2 and avx versions.
Search with 1 thread. (Or never repeat your search. Or accept that multi-threaded search is not determinisitc.)
Top
Javier Ros
Posts: 200
Joined: Fri Oct 12, 2012 12:48 pm
Location: Seville (SPAIN)
Full name: Javier Ros

Re: Fluctuations in Stockfish evaluation

Post by Javier Ros »

Cornfed wrote: ↑Tue Jun 15, 2021 12:22 am I wonder if setting contempt to zero would help? I only ever use zero.
Thank you for the advice. I will repeat the experiment with contemp equal to zero.
Top
Raphexon
Posts: 476
Joined: Sun Mar 17, 2019 12:00 pm
Full name: Henk Drost

Re: Fluctuations in Stockfish evaluation

Post by Raphexon »

Contempt is mostly non-functional with nnue.

It only works in positions where classical is used, so its effect is very marginal.

Also, SF13 is already outdated.
https://abrok.eu/stockfish/
Top
Javier Ros
Posts: 200
Joined: Fri Oct 12, 2012 12:48 pm
Location: Seville (SPAIN)
Full name: Javier Ros

Re: Fluctuations in Stockfish evaluation

Post by Javier Ros »

syzygy wrote: ↑Tue Jun 15, 2021 1:04 am
Javier Ros wrote: ↑Mon Jun 14, 2021 6:45 pm I wonder what is the origin of these unpleasant fluctuations and if there is a solution.
What would be the point of searching longer/deeper if fluctuations did not exist? If you don't want fluctuations, search to depth 1.
On the other hand, I don't understand the discrepancy between the results of the bmi2 and avx versions.
Search with 1 thread. (Or never repeat your search. Or accept that multi-threaded search is not determinisitc.)
Of course I have used 1 thread to avoid non-determination due multiple threads.

After 11 hours fluctuations remain 0.32, 0.24, 0.26, 0.24, 0.22, 0.21, see analysis below.

In iterative mathematical methods, as the iterations progress, the estimated value converges with smaller and smaller fluctuations, but in this case, after a significant volume of calculations, large fluctuations remain.

It is true that this is not a traditional mathematical method looking for an exact solution, but it is desirable that it should be similar.

Stockfish_21061411_x64_avx2:
NNUE evaluation using nn-8e47cf062333.nnue enabled

52/60 3:42:10 10.444.254.743 783.468 +0,32 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.c2-c3 Re8xe1 12.Qd1xe1 Nd6-e8 13.Bf1-d3 d7-d5 14.Bc1-f4 g7-g6 15.Nb1-d2 Ne8-g7 16.Nd2-f3 Bc8-f5 17.Bd3xf5 Ng7xf5 18.Qe1-d2 c7-c6 19.Ra1-e1 Nf5-d6 20.Bf4xd6 Qd8xd6 21.g2-g3 h7-h5 22.h2-h3 Kg8-g7 23.Kg1-g2 Qd6-c7 24.Nf3-e5 Bf6xe5 25.d4xe5 Ra8-e8 26.Qd2-d4 a7-a6
53/60- 5:07:42 14.504.778.512 785.615 +0,24 1.e2-e4 e7-e5
53/62- 9:16:28 27.012.967.291 809.060 +0,16 1.e2-e4 e7-e5
53/71+ 10:20:46 30.111.340.522 808.428 +0,24 1.e2-e4
53/71 10:23:38 30.248.222.322 808.384 +0,22 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.c2-c3 Re8xe1 12.Qd1xe1 Nd6-e8 13.Bf1-d3 d7-d5 14.Bc1-f4 g7-g6 15.Nb1-d2 Ne8-g7 16.Nd2-f3 Bc8-f5 17.Bd3xf5 Ng7xf5 18.Qe1-d2 c7-c6 19.Ra1-e1 Nf5-g7 20.h2-h3 Qd8-d7 21.Nf3-e5 Bf6xe5 22.d4xe5 Ng7-e6 23.Bf4-g5 Ne6xg5 24.Qd2xg5 a7-a5 25.a2-a3 Ra8-e8 26.Qg5-d2 Qd7-e7 27.f2-f4 a5-a4 28.Qd2-d4
54/62 11:30:03 33.441.206.266 807.688 +0,21 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.c2-c3 Re8xe1 12.Qd1xe1 Nd6-e8 13.Nb1-d2 d7-d5 14.Nd2-b3 Ne8-d6 15.Bc1-f4 Bc8-f5 16.Nb3-c5 b7-b6 17.Nc5-d3 Bf6-g5 18.Qe1-e5 Bg5xf4 19.Qe5xf4 Qd8-d7 20.Nd3-b4 c7-c6 21.Ra1-e1 h7-h6 22.h2-h4 a7-a5 23.Nb4-d3 Qd7-c7 24.Re1-e3 Bf5-e4 25.h4-h5 Be4xd3 26.Bf1xd3 Ra8-e8 27.a2-a3 Re8xe3 28.Qf4xe3 Qc7-d7 29.Qe3-f4 Kg8-f8
Top
Javier Ros
Posts: 200
Joined: Fri Oct 12, 2012 12:48 pm
Location: Seville (SPAIN)
Full name: Javier Ros

Re: Fluctuations in Stockfish evaluation

Post by Javier Ros »

Raphexon wrote: ↑Tue Jun 15, 2021 8:34 am Contempt is mostly non-functional with nnue.

It only works in positions where classical is used, so its effect is very marginal.

Also, SF13 is already outdated.
https://abrok.eu/stockfish/
I have repeated the experiment with latest dev version, see above and below.

You are right, with contemp 0 results are similar, evaluations between 2 minutes and 30 minutes: maximum value 0.46, minimum value 0.17

If you remove lines with non complete ply + - the fluctuations are slightly smaller, maximum value 0.43, minimum value 0.20 but not disappearing



FEN: rnbqkbnr/pppppppp/8/8/8/8/PPPPPPPP/RNBQKBNR w KQkq - 0 1

Stockfish_21061411_x64_avx2contemp0:
NNUE evaluation using nn-8e47cf062333.nnue enabled

34/47- 02:01 96.064.636 792.906 +0,32 1.e2-e4 e7-e5
34/47 02:05 99.800.775 794.117 +0,29 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.c2-c3 Re8xe1 12.Qd1xe1 Nd6-f5 13.a2-a4 a7-a5 14.Nb1-d2 d7-d5 15.Nd2-f3 Nf5-d6 16.Bc1-f4 Bc8-f5 17.Qe1-e3 c7-c6 18.Nf3-e5 Bf6-e7 19.Ra1-e1
35/45+ 02:14 106.905.542 793.167 +0,37 1.e2-e4
35/45 02:17 109.411.297 793.186 +0,37 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.c2-c3 Re8xe1 12.Qd1xe1 Nd6-e8 13.Bc1-f4 d7-d5 14.a2-a4 a7-a5 15.Bf1-d3 Bf6-e7 16.Nb1-d2 Bc8-e6 17.Nd2-f3 Be7-d6 18.Bf4-e5 Bd6xe5 19.Qe1xe5 Be6-g4 20.Nf3-d2 Bg4-e6 21.h2-h3 c7-c6 22.Nd2-b3
36/48+ 03:04 145.339.285 789.681 +0,46 1.e2-e4
36/48- 03:18 156.789.654 788.807 +0,29 1.e2-e4 e7-e5
36/48 04:14 200.372.428 786.687 +0,29 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.Bc1-f4 Re8xe1 12.Qd1xe1 Nd6-e8 13.c2-c3 d7-d5 14.a2-a4 a7-a5 15.Bf1-d3 Bf6-e7 16.Nb1-d2 Bc8-e6 17.Nd2-f3 Be7-d6 18.Bf4-e5 Qd8-d7 19.h2-h3 Be6-f5 20.Be5xd6 Ne8xd6 21.Nf3-e5 Qd7-e8
37/49+ 04:25 209.182.592 786.492 +0,37 1.e2-e4
37/49 04:52 230.349.596 786.248 +0,26 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.Bc1-f4 Re8xe1 12.Qd1xe1 Nd6-e8 13.c2-c3 d7-d5 14.Nb1-d2 Bc8-f5 15.Qe1-e3 c7-c6 16.h2-h3 Ne8-c7 17.Ra1-e1 Nc7-e6 18.Bf4-e5 a7-a5 19.Nd2-f3 Bf6xe5 20.Nf3xe5 f7-f6 21.Ne5-f3
38/47+ 07:12 339.562.491 784.941 +0,35 1.c2-c4
38/52 07:48 367.868.756 785.480 +0,39 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.Bc1-f4 Re8xe1 12.Qd1xe1 Nd6-e8 13.c2-c3 d7-d5 14.Nb1-d2 c7-c6 15.Bf1-d3 g7-g6 16.Nd2-f3 Ne8-g7 17.Qe1-d2 Bc8-f5 18.Bd3xf5 Ng7xf5 19.Nf3-e5 Nf5-d6 20.Ne5-d3 Nd6-e4 21.Qd2-e2 b7-b6 22.Ra1-e1 Qd8-d7 23.h2-h3 Ra8-e8
39/49- 08:40 408.410.688 784.686 +0,31 1.e2-e4 e7-e5
39/49+ 09:29 446.238.110 783.295 +0,39 1.e2-e4
39/49 09:36 451.465.251 783.506 +0,40 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.Bc1-f4 Re8xe1 12.Qd1xe1 Nd6-e8 13.c2-c3 d7-d5 14.Bf1-d3 g7-g6 15.Nb1-d2 Ne8-g7 16.Nd2-f3 Bc8-f5 17.Bd3xf5 Ng7xf5 18.Qe1-d2 c7-c6 19.Ra1-e1 Nf5-d6 20.Bf4xd6 Qd8xd6 21.g2-g3 Qd6-d7 22.Qd2-e2
40/48- 12:50 603.397.327 783.215 +0,32 1.e2-e4 c7-c6
40/50 14:10 665.425.771 782.597 +0,34 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.Bc1-f4 Re8xe1 12.Qd1xe1 Nd6-e8 13.c2-c3 d7-d5 14.Bf1-d3 g7-g6 15.Nb1-d2 Ne8-g7 16.Nd2-f3 Bc8-f5 17.Bd3xf5 Ng7xf5 18.Qe1-d2 c7-c6 19.Ra1-e1 Nf5-d6 20.Qd2-c2 Nd6-e4 21.Nf3-d2 Ne4xd2 22.Qc2xd2 Qd8-d7 23.h2-h3 Ra8-e8
41/52- 15:06 709.295.839 782.654 +0,25 1.e2-e4 e7-e5
41/52- 20:42 972.808.348 782.790 +0,17 1.e2-e4 e7-e5
41/53+ 21:10 994.083.826 782.730 +0,25 1.e2-e4
41/53 21:24 1.005.192.046 782.767 +0,20 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.Bc1-f4 Re8xe1 12.Qd1xe1 Nd6-e8 13.c2-c3 d7-d5 14.Bf1-d3 g7-g6 15.Nb1-d2 Ne8-g7 16.Nd2-f3 Bc8-f5 17.Bd3xf5 Ng7xf5 18.Qe1-d2 Nf5-d6 19.Bf4xd6 Qd8xd6 20.Ra1-e1 Qd6-d7 21.h2-h3 c7-c6 22.Nf3-e5 Qd7-f5 23.Qd2-e3 Ra8-e8
42/50+ 22:16 1.046.142.874 782.598 +0,28 1.e2-e4
42/50+ 22:39 1.063.514.679 782.519 +0,37 1.e2-e4
42/53 23:37 1.109.192.365 782.242 +0,43 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.Bc1-f4 Re8xe1 12.Qd1xe1 Nd6-e8 13.c2-c3 d7-d5 14.Bf1-d3 g7-g6 15.Nb1-d2 Ne8-g7 16.Nd2-f3 Bc8-f5 17.Bd3xf5 Ng7xf5 18.Qe1-d2 Nf5-d6 19.Bf4xd6 Qd8xd6 20.Ra1-e1 c7-c6 21.h2-h3 Kg8-g7 22.g2-g3 h7-h5 23.a2-a4 Qd6-d7 24.h3-h4 Ra8-h8
43/44- 24:33 1.152.764.601 782.130 +0,35 1.e2-e4 e7-e5
43/54- 26:30 1.243.960.086 782.231 +0,27 1.e2-e4 e7-e5
43/56+ 29:33 1.385.491.871 781.328 +0,35 1.e2-e4
43/56 32:02 1.522.819.840 792.286 +0,37 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Nc6xe5 7.Re1xe5+ Bf8-e7 8.Bb5-f1 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.Bc1-f4 Re8xe1 12.Qd1xe1 Nd6-e8 13.c2-c3 d7-d5 14.Bf1-d3 g7-g6 15.Nb1-d2 Ne8-g7 16.Qe1-e2 c7-c6 17.Ra1-e1 Bc8-f5 18.Bd3xf5 Ng7xf5 19.Nd2-f3 Nf5-g7 20.Qe2-d2 Qd8-d7 21.h2-h3 Ra8-e8 22.Nf3-e5 Bf6xe5 23.d4xe5

only complete plies

34/47 02:05 99.800.775 794.117 +0,29 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.c2-c3 Re8xe1 12.Qd1xe1 Nd6-f5 13.a2-a4 a7-a5 14.Nb1-d2 d7-d5 15.Nd2-f3 Nf5-d6 16.Bc1-f4 Bc8-f5 17.Qe1-e3 c7-c6 18.Nf3-e5 Bf6-e7 19.Ra1-e1
35/45 02:17 109.411.297 793.186 +0,37 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.c2-c3 Re8xe1 12.Qd1xe1 Nd6-e8 13.Bc1-f4 d7-d5 14.a2-a4 a7-a5 15.Bf1-d3 Bf6-e7 16.Nb1-d2 Bc8-e6 17.Nd2-f3 Be7-d6 18.Bf4-e5 Bd6xe5 19.Qe1xe5 Be6-g4 20.Nf3-d2 Bg4-e6 21.h2-h3 c7-c6 22.Nd2-b3
36/48 04:14 200.372.428 786.687 +0,29 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.Bc1-f4 Re8xe1 12.Qd1xe1 Nd6-e8 13.c2-c3 d7-d5 14.a2-a4 a7-a5 15.Bf1-d3 Bf6-e7 16.Nb1-d2 Bc8-e6 17.Nd2-f3 Be7-d6 18.Bf4-e5 Qd8-d7 19.h2-h3 Be6-f5 20.Be5xd6 Ne8xd6 21.Nf3-e5 Qd7-e8
37/49 04:52 230.349.596 786.248 +0,26 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.Bc1-f4 Re8xe1 12.Qd1xe1 Nd6-e8 13.c2-c3 d7-d5 14.Nb1-d2 Bc8-f5 15.Qe1-e3 c7-c6 16.h2-h3 Ne8-c7 17.Ra1-e1 Nc7-e6 18.Bf4-e5 a7-a5 19.Nd2-f3 Bf6xe5 20.Nf3xe5 f7-f6 21.Ne5-f3
38/52 07:48 367.868.756 785.480 +0,39 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.Bc1-f4 Re8xe1 12.Qd1xe1 Nd6-e8 13.c2-c3 d7-d5 14.Nb1-d2 c7-c6 15.Bf1-d3 g7-g6 16.Nd2-f3 Ne8-g7 17.Qe1-d2 Bc8-f5 18.Bd3xf5 Ng7xf5 19.Nf3-e5 Nf5-d6 20.Ne5-d3 Nd6-e4 21.Qd2-e2 b7-b6 22.Ra1-e1 Qd8-d7 23.h2-h3 Ra8-e8
39/49 09:36 451.465.251 783.506 +0,40 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.Bc1-f4 Re8xe1 12.Qd1xe1 Nd6-e8 13.c2-c3 d7-d5 14.Bf1-d3 g7-g6 15.Nb1-d2 Ne8-g7 16.Nd2-f3 Bc8-f5 17.Bd3xf5 Ng7xf5 18.Qe1-d2 c7-c6 19.Ra1-e1 Nf5-d6 20.Bf4xd6 Qd8xd6 21.g2-g3 Qd6-d7 22.Qd2-e2
40/50 14:10 665.425.771 782.597 +0,34 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.Bc1-f4 Re8xe1 12.Qd1xe1 Nd6-e8 13.c2-c3 d7-d5 14.Bf1-d3 g7-g6 15.Nb1-d2 Ne8-g7 16.Nd2-f3 Bc8-f5 17.Bd3xf5 Ng7xf5 18.Qe1-d2 c7-c6 19.Ra1-e1 Nf5-d6 20.Qd2-c2 Nd6-e4 21.Nf3-d2 Ne4xd2 22.Qc2xd2 Qd8-d7 23.h2-h3 Ra8-e8
41/53 21:24 1.005.192.046 782.767 +0,20 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.Bc1-f4 Re8xe1 12.Qd1xe1 Nd6-e8 13.c2-c3 d7-d5 14.Bf1-d3 g7-g6 15.Nb1-d2 Ne8-g7 16.Nd2-f3 Bc8-f5 17.Bd3xf5 Ng7xf5 18.Qe1-d2 Nf5-d6 19.Bf4xd6 Qd8xd6 20.Ra1-e1 Qd6-d7 21.h2-h3 c7-c6 22.Nf3-e5 Qd7-f5 23.Qd2-e3 Ra8-e8
42/53 23:37 1.109.192.365 782.242 +0,43 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Bf8-e7 7.Bb5-f1 Nc6xe5 8.Re1xe5 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.Bc1-f4 Re8xe1 12.Qd1xe1 Nd6-e8 13.c2-c3 d7-d5 14.Bf1-d3 g7-g6 15.Nb1-d2 Ne8-g7 16.Nd2-f3 Bc8-f5 17.Bd3xf5 Ng7xf5 18.Qe1-d2 Nf5-d6 19.Bf4xd6 Qd8xd6 20.Ra1-e1 c7-c6 21.h2-h3 Kg8-g7 22.g2-g3 h7-h5 23.a2-a4 Qd6-d7 24.h3-h4 Ra8-h8
43/56 32:02 1.522.819.840 792.286 +0,37 1.e2-e4 e7-e5 2.Ng1-f3 Nb8-c6 3.Bf1-b5 Ng8-f6 4.O-O Nf6xe4 5.Rf1-e1 Ne4-d6 6.Nf3xe5 Nc6xe5 7.Re1xe5+ Bf8-e7 8.Bb5-f1 O-O 9.d2-d4 Be7-f6 10.Re5-e1 Rf8-e8 11.Bc1-f4 Re8xe1 12.Qd1xe1 Nd6-e8 13.c2-c3 d7-d5 14.Bf1-d3 g7-g6 15.Nb1-d2 Ne8-g7 16.Qe1-e2 c7-c6 17.Ra1-e1 Bc8-f5 18.Bd3xf5 Ng7xf5 19.Nd2-f3 Nf5-g7 20.Qe2-d2 Qd8-d7 21.h2-h3 Ra8-e8 22.Nf3-e5 Bf6xe5 23.d4xe5
Top
RubiChess
Posts: 584
Joined: Fri Mar 30, 2018 7:20 am
Full name: Andreas Matthies

Re: Fluctuations in Stockfish evaluation

Post by RubiChess »

Javier Ros wrote: ↑Tue Jun 15, 2021 8:42 am After 11 hours fluctuations remain 0.32, 0.24, 0.26, 0.24, 0.22, 0.21, see analysis below.

In iterative mathematical methods, as the iterations progress, the estimated value converges with smaller and smaller fluctuations, but in this case, after a significant volume of calculations, large fluctuations remain.
If eval converges with deeper search and the converged value is even correct, chess would be solved. Good luck!

Edit: I should better say: Eval will converge with deeper search but the number N with |eval(searchdepth_n) - score_of_chess| < epsilon for all n>N is too big to be handled by even Stockfish.
Top
Cornfed
Posts: 511
Joined: Sun Apr 26, 2020 11:40 pm
Full name: Brian D. Smith

Re: Fluctuations in Stockfish evaluation

Post by Cornfed »

RubiChess wrote: ↑Tue Jun 15, 2021 9:40 am
Javier Ros wrote: ↑Tue Jun 15, 2021 8:42 am After 11 hours fluctuations remain 0.32, 0.24, 0.26, 0.24, 0.22, 0.21, see analysis below.

In iterative mathematical methods, as the iterations progress, the estimated value converges with smaller and smaller fluctuations, but in this case, after a significant volume of calculations, large fluctuations remain.
If eval converges with deeper search and the converged value is even correct, chess would be solved. Good luck!

Edit: I should better say: Eval will converge with deeper search but the number N with |eval(searchdepth_n) - score_of_chess| < epsilon for all n>N is too big to be handled by even Stockfish.
I am really not sure what the problem is. Those are just numbers...and pretty darn close at that. Isn't it to be expected that the vary over time/ply? Chess...isn't accounting you know.
Top

Return to “Computer Chess Club: General Topics”