[mlpack] Reinforcement learning (GSOC 2018)

Marcus Edel marcus.edel at fu-berlin.de
Sun Mar 11 13:37:12 EDT 2018


Hello Madhav,

thanks for getting in touch.

> Would a project  which involves implementing  Double DQN along with prioritized
> experience relay be a suitable addition to the current library?
> 
> Would the above mentioned project goals fit in well with the duration of the
> program?

Yes, that would fit into the current project scope.

Let me know if I should clarify anything.

> On 9. Mar 2018, at 23:03, archit wagle <architwagle at gmail.com> wrote:
> 
> Hi everyone,
> 
> I am very much interested in contributing to the reinforcement learning project(GSOC).
> 
> Would a project  which involves implementing  Double DQN along with prioritized experience relay be a suitable addition to the current library?
> 
> Would the above mentioned project goals fit in well with the duration of the program?
> 
> Thank you for your time.
> 
> Madhav Wagle.
> _______________________________________________
> mlpack mailing list
> mlpack at lists.mlpack.org
> http://knife.lugatgt.org/cgi-bin/mailman/listinfo/mlpack

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://knife.lugatgt.org/pipermail/mlpack/attachments/20180311/b56a83d3/attachment.html>


More information about the mlpack mailing list