| |
BGonline.org Forums
Rollout
Posted By: Timothy Chow In Response To: 15 checkers against 1 at DMP (Timothy Chow)
Date: Thursday, 12 November 2009, at 9:24 p.m.
I didn't say so in my original message, but my real question here, as lenny surmised, is (a) whether playing 8/3(2) 7/2*(2) has any merit, and (b) whether the bots can be trusted to roll primes a short distance.
GNU 0-ply thinks that 8/3(2) 7/2*(2) is 42nd best (!), but a rollout puts it within striking distance of 22/12 19/9 (which I picked for no better reason than that it happens to be GNU 2-ply's top choice). Can these numbers be trusted?
The score is: gnubg 0, tchow 0 (match to 1 point, post-Crawford play)
gnubg 23
tchow 140 Position ID: AABAYNsWGCIAAA Match ID: cIk2AAAAAAAA
# Ply Move Equity • 1 R 22/12 19/9 -0.851
0.074 0.000 0.000 - 0.926 0.062 0.048 -0.851 -0.851 0.002 0.000 0.000 - 0.002 0.001 0.001 0.003 0.003 Full cubeful rollout with var.redn. 5184 games, Mersenne Twister dice gen. with seed 869873060 and quasi-random dice Play: supremo 2-ply cubeful prune [world class] keep the first 0 0-ply moves and up to 16 more moves within equity 0.32 Skip pruning for 1-ply moves. Cube: 2-ply cubeful prune [world class] 2 R 8/3(2) 7/2*(2) -0.861 ( -0.010)
0.069 0.000 0.000 - 0.931 0.101 0.088 -0.861 -0.861 0.001 0.000 0.000 - 0.001 0.001 0.001 0.003 0.003 Full cubeful rollout with var.redn. 5184 games, Mersenne Twister dice gen. with seed 869873060 and quasi-random dice Play: supremo 2-ply cubeful prune [world class] keep the first 0 0-ply moves and up to 16 more moves within equity 0.32 Skip pruning for 1-ply moves. Cube: 2-ply cubeful prune [world class]
| |
BGonline.org Forums is maintained by Stick with WebBBS 5.12.