Algorithm helps computers beat humans at Go

TalkBack 1 of 2:

Next »

• Thread View
• Flat View

Gambler's fallacy

"Punters will find that certain one-armed bandits in a casino appear to pay more on average than others, but an intelligent player should also try machines that have so far paid less, in case they are hiding a jackpot, Kocsis said."

Kocsis should retake his statistics and logic classes.

What we have here is what's called the "gambler's fallacy." When you flip a coin, or roll a dice, or any other totally random action, the odds of the next action are never based on the previous action. Just because the previous outcome has been favorable or unfavorable doesn't mean the next outcome is more or less likely.

The truth is, there are no "two sorts of machines." Every machine is the same.

If you flip a coin and it comes up heads ten times, the chances are still 50% that you will get heads on the next flip.

In Go, this may be different, as it's a strategy game and not a chance game, so the algorithm may actually work in Go. But it definitely won't work against the slots.

He should've picked a better illustration.

Posted by: CobraA1   Posted on: 02/21/07 You are currently: a Guest | Members login | Terms of Use

Alert moderator to an offensive message

Subscribe to this discussion via Email or RSS

SponsoredWhite Papers, Webcasts, and Downloads

• IBM Smart Business Time Savings Test IBM If time is money - is your organization in need of a way to save both? ... Download Now
• Why Isn't Server Virtualization Saving Us More? A Few Small Changes May Dramatically Increase Your Efficiency VMware Companies have rapidly adopted server virtualization over the past few ... Download Now
• Three Steps You Need to Know to Stop Data Loss Varonis Sensitive data exposed to misuse or loss... it is the stuff of nightmares ... Download Now