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

BGonline.org Forums

Another XG ROLLOUT

Posted By: Petter Bengtsson
Date: Wednesday, 9 December 2009, at 2:51 a.m.

In Response To: LA -- JLee vs. Bill Riles #1 (XG ROLLOUT) (Jason Lee)

Can anyone explain why the confidence intervals in Jason's rollout (46656 games) are about five time bigger than in my rollout (12960 games)?

Is it because Jason didn't use variance reduction in his rollout?





is Player 2

score: 3
pip: 96
13 point match
pip: 76
score: 4

is Player 1
XGID=-B-ECcC-----A----A-bb-bbd-:2:1:1:D:4:3:0:13:8
double to 8 take ?


Analyzed in Rollout
No Double
Player Winning Chances: 74,34% (G: 5,87% B: 0,12%)
Opponent Winning Chances: 25,66% (G: 1,50% B: 0,03%)
Double/Take
Player Winning Chances: 74,11% (G: 6,58% B: 0,21%)
Opponent Winning Chances: 25,89% (G: 1,59% B: 0,02%)
Cubeless Equities
No Redouble:+0,522
Redouble:+0,860
Cubeful Equities
No Redouble:+0,774
Redouble/Take:+0,769 (-0,005)
Redouble/Drop:+1,000 (+0,226)
Best Cube action: No Redouble / Take
Rollout details
12960 Games rolled with Variance Reduction.
Dice Seed: 84745752
Moves and cube decisions: 3 ply
Search interval: Huge
Confidence No Redouble: ± 0,002 (+0,772...+0,776)
Confidence Redouble: ± 0,003 (+0,766...+0,771)
Double Decision confidence: 99,9%
Take Decision confidence: 100,0%
Duration: 5 hours 54 minutes 46 seconds

eXtreme Gammon Version: 1.10, MET: GnuBG 11 point

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.