[computer-go] More statistics and conclusions from CGOS data
Gunnar Farnebäck
gunnar at lysator.liu.se
Wed Feb 13 15:07:45 PST 2008
Don Dailey wrote:
> Here is the entire tree, where I drop nodes if they have less than 500
> samples. These are games between 1700+ players who are within 100 ELO
> of each others rating.
>
>
> E5 49.1% 19630
> | C4 49.6% 5894
> | | C5 49.9% 1558
> | | | B5 54.7% 788
> | | | | C6 48.4% 566
> | | C6 51.3% 1106
> | | D4 53.5% 737
> | | | C5 52.0% 765
> | | E3 50.6% 678
> | | D3 51.9% 620
> | C5 56.0% 4131
> | | D4 48.4% 1226
> | | | C4 52.0% 765
> | | C4 47.6% 710
> | | D3 39.0% 605
> | C3 54.2% 3702
> | | C5 50.1% 1532
> | | E7 50.3% 557
> | D4 50.5% 3634
> | | D5 52.3% 2730
> | | | C5 37.3% 585
> | | | E4 49.0% 582
> | D5 39.3% 1688
> | | D4 63.0% 1253
> | | E4 58.4% 611
> | | | D4 49.0% 582
> D5 47.9% 8405
> | F5 56.1% 2465
> | | F4 47.2% 895
> | | | G4 54.1% 512
> | | E4 39.6% 528
> | F4 52.9% 1516
> | | F5 47.4% 529
> | E5 50.8% 758
> | | D4 45.9% 848
> | | E4 50.4% 544
> | G4 51.9% 698
> | E4 49.1% 696
> | | E5 58.4% 611
> | | | D4 49.0% 582
> | | E6 39.6% 528
> | F3 49.5% 553
> D4 47.4% 7963
> | E6 51.4% 1466
> | E5 55.2% 1355
> | | D5 45.9% 848
> | F6 53.1% 1019
> | F7 51.3% 967
> | D6 58.7% 652
> | G7 58.5% 535
> C4 44.6% 3206
> C5 47.9% 2270
> C3 40.3% 1438
Interesting. If I do the same with MonteGNU's fuseki database, which
is based on online learning from own CGOS games, and cut off at 200
samples I get:
E5 8101
| C3 2950
| | G5 1798
| | | G3 1145 (A)
| | | | C5 403
| | | C7 310
| | E3 622
| | | C7 1145 (transposition of A)
| C4 2249
| | C5 714
| | | B5 459
| | | | C6 403
| | D4 443
| | | C5 277 (B)
| | C6 351
| | D6 286
| | E3 239
| C5 1708
| | D4 612
| | | C4 277 (transposition of B)
| | C4 343
| | C3 297
| D4 864
| | E4 698
| | | D5 205
| D5 295
| | D4 216
D4 1608
| E5 681
| | E4 520
| | | D5 351
| | | | C5 212
| F6 279
| F5 250
D5 1521
| F5 508
| | F4 190
| F4 320
C4 585
C5 391
(C3 149)
/Gunnar
More information about the computer-go
mailing list