Hi Dan, hi friends,
> There is actually no randomness in the algorithm, just like AlphaZero's...
but then it does not make sense to call that algorithm "rollout".
**
In general: when introducing a new name, care should
be taken that the name
> but then it does not make sense to call that algorithm "rollout".
>
> In general: when introducing a new name, care should
> be taken that the name describes properly what is going on.
Speaking of which, why did people start calling them rollouts instead of
playouts?
Darren
P.S. And don't
In the AGZ paper, there is a formula for what they call “a variant of the PUCT
algorithm”, and they cite a paper from Christopher Rosin:
http://gauss.ececs.uc.edu/Workshops/isaim2010/papers/rosin.pdf
But that paper has a formula that he calls the PUCB formula, which incorporates
the priors
The technique originated with backgammon players in the late 1970's, who would
roll out positions manually. Ron Tiekert (Scrabble champion) also applied the
technique to Scrabble, and I took that idea for Maven. It seemed like people
were using the terms interchangeably.
-Original
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
