t; will lead to minimize the mean squared error.
>
> Cheers,
> Arnaud
>
>
> On 24 Feb 2015, at 01:53, Pierre-Luc Bacon wrote:
>
> In the original Extra-Tree papers, the authors use the "relative variance
> reduction" (appendix A) for regression.
>
> The i
In the original Extra-Tree papers, the authors use the "relative variance
reduction" (appendix A) for regression.
The implementation in Scikit-Learn however suggests a different criterion:
https://github.com/scikit-learn/scikit-learn/blob/master/sklearn/tree/_tree.pyx#L836
What was the rational b
le ends up in.
> > Then you can update your class estimates or learn something else on top
> of
> > that.
> >
> >
> >
> > On 02/18/2015 01:31 PM, Pierre-Luc Bacon wrote:
> >
> > In the field of reinforcement learning (RL), the Fitted-Q algorithm of
> Ern
In the field of reinforcement learning (RL), the Fitted-Q algorithm of
Ernst 2005 (http://www.jmlr.org/papers/volume6/ernst05a/ernst05a.pdf)
relies on the ability to fix the tree structure to ensure convergence (see
p. 515 of the JMLR paper).
The warm_start option is useful, but does not fully al
