[mlpack] [mlpack/mlpack] NEAT algorithm (#752)

[Excalibur]

Hi Marcus,

I am so sorry for reply so late! I am in China and didn't check this email
quite often, and also cannot receive the notifications from it due to the
Internet condition. Sorry for that! I check the bang3 at ualberta.ca emails
more frequently.

The last change I made to the NEAT algorithm is mainly the changes of
activation calculation in the Genome class. There are some bugs previously.
I test all the testing cases except Mario. I will try to test it when I
have got a free time, as these days I am quite busy with a lot stuffs.

Best wishes,
Bang

2016-11-08 23:55 GMT+08:00 Marcus Edel <notifications at github.com>:

> I've written a command line client and server to run the NEAT method,
> actually any mlpack classifier, against the OpenAI Gym toolkit. Which
> enables us to easily test the NEAT method against a variety of environments.
>
> I've tried to reproduce the result for the Mario task, but it looks like
> the method doesn't converge as it did the last time I tested it. I'm not
> sure if the last change that effected the Evaluation process could be a
> reason for that. Maybe @BangLiu <https://github.com/BangLiu> can provide
> some insights?
>
> —
> You are receiving this because you were mentioned.
> Reply to this email directly, view it on GitHub
> <https://github.com/mlpack/mlpack/pull/752#issuecomment-259175388>, or mute
> the thread
> <https://github.com/notifications/unsubscribe-auth/AD9tIU9uN-Cp2qN5oCgX0jJfExmrJi65ks5q8Jt8gaJpZM4JeA4o>
> .
>


-- 
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/pull/752#issuecomment-264831977
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://knife.lugatgt.org/pipermail/mlpack/attachments/20161205/fe9e09e8/attachment.html>