[Computer-go] On proper naming

"Ingo Althöfer" 3-Hirn-Verlag at gmx.de
Thu Mar 8 07:08:58 PST 2018


Hi Darren,

> > but then it does not make sense to call that algorithm "rollout".
> > ...
> 
> Speaking of which, why did people start calling them rollouts 
> instead of playouts?

it comes from the Backgammon scene, where for instance
rungames in the endgame were estimated by dozens or
hundreds of rollouts in the 1970's in the New York
scene.

Even further back, already Emanuel Lasker proposed
rollouts (in Backgammon) in his classic book "Brettspiele
der Voelker" from 1931. However, on p.239 Lasker does not
call it "rollouts" but "Versuche machen" ("making experiments").

To my knowledge, this is the oldest proposal to use
rollouts in 2-person game play.

**************************************

In 1988, Bruce Abramson proposed Monte-Carlo runs in
2-person games without chance. However, he could his
approach "expected outcome". He even tried to apply
it to chess.
https://chessprogramming.wikispaces.com/Bruce+Abramson

Ingo.


More information about the Computer-go mailing list