Hi Stefan, --- In [email protected], "Stefan Pochmann" <[EMAIL PROTECTED]> wrote: > Results so far > You have won 9, lost 3, and tied 4 games > Statistics for 16 games > winning percentage*: 37.50% > won : 56.25% > lost: 18.75% > tied: 25.00%
I wouldn't be too surprised if you /can/ beat this program consistently, but you don't have much evidence here. Suppose we start from the hypothesis (1) that those win/lose/tie percentages really are an accurate reflection of what you would get in a very long run of games. Now compare the probability of getting the result (9,3,4) under that assumption (1) with the probability of getting (9,3,4) in purely random play: Ratio = (.5625)^9 * (.1875)^3 * (.25)^4 / (.3333)^16 = 6.2 This is not strong evidence in favour of (1), as compared with random play, and it will be weakened further if you were to make allowance for other hypotheses -- as we should: I deliberately chose (1) to be maximally favourable to /you/ -- i.e., to give the maximum possible value for the relative likelihoods of the 2 hypotheses. > That program is sooo bad. And my strategy was actually quite > repetitive. It was a short run. Try playing several hundred games to see if the program will pick up on your strategy. Yeah, it would be boring to do a proper test. ;) Mike ------------------------ Yahoo! Groups Sponsor --------------------~--> Get fast access to your favorite Yahoo! Groups. Make Yahoo! your home page http://us.click.yahoo.com/dpRU5A/wUILAA/yQLSAA/MXMplB/TM --------------------------------------------------------------------~-> Yahoo! Groups Links <*> To visit your group on the web, go to: http://groups.yahoo.com/group/speedsolvingrubikscube/ <*> To unsubscribe from this group, send an email to: [EMAIL PROTECTED] <*> Your use of Yahoo! Groups is subject to: http://docs.yahoo.com/info/terms/
