[ View Thread ] [ Post Response ] [ Return to Index ] [ Read Prev Msg ] [ Read Next Msg ]

BGonline.org Forums

GNU Move Filter Test

Posted By: Stick
Date: Thursday, 11 September 2008, at 7:22 a.m.

I was wondering what kind of an effect, if any, would a larger filter have. I don't know if anyone has looked at this sort of stuff and I don't plan on lingering on it. I wanted to know if it'd be worth it to do any rollouts with a larger filter is all.

Below are two identical rollouts except one is 12 moves within' .16 and the other is 16 moves within' .32. Only one example but doesn't interest me in upping my settings any. (though to get a full grasp I'd also have to clock what the time difference in the rollouts is)

gnubg164


2O ' ' '1X4X '3X ' '1X5O

2X ' ' ' '5O '3O ' ' '4X

user167

Position ID: 0HPkATDgc/ABMA Match ID: cIkFAAAAAAAA

# Ply Move Equity
R 8/5 6/5 +0.0099
0.50100.14970.0076-0.49900.15160.0069 +0.0009 +0.0099
0.00170.00180.0004-0.00170.00180.0004 0.0044 0.0106
Full cubeful rollout with var.redn.
1296 games, Mersenne Twister dice gen. with seed 1030848064 and quasi-random dice
Play: 2-ply cubeful prune [world class]
keep the first 0 0-ply moves and up to 12 more moves within equity 0.16
Skip pruning for 1-ply moves.
Cube: 2-ply cubeful prune [world class]

# Ply Move Equity
R 8/5 6/5 +0.0090
0.50130.14990.0074-0.49870.15280.0072 -0.0001 +0.0090
0.00170.00180.0003-0.00170.00190.0004 0.0043 0.0104
Full cubeful rollout with var.redn.
1296 games, Mersenne Twister dice gen. with seed 1030848064 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]

Messages In This Thread

 

Post Response

Your Name:
Your E-Mail Address:
Subject:
Message:

If necessary, enter your password below:

Password:

 

 

[ View Thread ] [ Post Response ] [ Return to Index ] [ Read Prev Msg ] [ Read Next Msg ]

BGonline.org Forums is maintained by Stick with WebBBS 5.12.