Hello Madhuparna, welcome, glad you find the idea interesting; Shangtong Zhang contributed a lot to the existing RL framework (https://github.com/mlpack/mlpack/tree/master/src/m lpack/methods/reinforcement_learning) he wrote about it here: https://www.mlpack.org/gsocblog/ShangtongZhangPage.html. Anyway, I think there are a bunch of opportunities to improve/extend the existing codebase, and we are working on an update for the RL GSoC idea, which should see the light in the next days.
I hope anything I said was helpful, let me know if I should clarify anything. Thanks, Marcus > On 27. Jan 2019, at 17:58, Madhuparna Bhowmik <[email protected]> > wrote: > > Hello everyone, > I am new to mlpack, and I have gone through the ideas for GSoC 2019. However, > there is an idea in the list of ideas of 2018 i.e, based on Reinforcement > Learning. And I see that no one took up that project last year. I am > experienced in Reinforcement Learning and I believe that I can work on that > project. So, my question is whether it is possible to take up that idea for > this year's GSoC since it was not taken up last year? > > Thank you > > Regards, > Madhuparna > _______________________________________________ > mlpack mailing list > [email protected] > http://knife.lugatgt.org/cgi-bin/mailman/listinfo/mlpack _______________________________________________ mlpack mailing list [email protected] http://knife.lugatgt.org/cgi-bin/mailman/listinfo/mlpack
