[mlpack] Hints for A3C/PPO

Hi Chirag, I think it would be better to also cc the mail list. I assume you are trying to implement A3C or something likes this. Actually this has almost been done. See my PR https://github.com/mlpack/mlpack/pull/934 This is my work last summer. To

[mlpack] Regarding GSoC '18

Hi, my name is Surya Krishnamurthy. I'm interested in contributing to mlpack for GSoC '18. I have a lot experience in C++14, python, nodejs and I'm an also an AI enthusiast(Deep learning specialisation in coursera). I have made some projects - chatbots, image classifiers and participated in a few h

Re: [mlpack] Hints for A3C/PPO

For TRPO you need to read the original paper.. I don’t have better idea. Starting from a vanilla policy gradient is good, however the main concern is that from my experience, you need either experience replay or multi-workers to make a non-linear function approximator work (they can give you unco

Re: [mlpack] Hints for A3C/PPO

Yes. First try the vanilla implementation, if it doesn’t work augment it with experience replay (ER). However I would suggest not to merge your vanilla implementation with ER, because it’s wrong theoretically as I mentioned before. I would also suggest not to merge your vanilla implementation wi

Re: [mlpack] Regarding GSoC '18

Hello Surya, welcome and thanks for getting in touch. If you search for a general starting point please take a look at mlpack.org/gsoc.html and www.mlpack.org/involved.html. I hope this is helpful, let me know if I should clarify anything. Thanks, Marcus > On 19. Feb 2018, at 17:50, Surya Krishn

Re: [mlpack] Introduction to GSOC 2018 : Rohan Rajadhyax

Hello Rohan, welcome and thanks for getting in touch. The video is a really nice introduction, have to keep that in mind. An important step for every project is to get familiar with the codebase (e.g. going through the codebase and run tests), for the RBFN project it's a good idea to take a close

Re: [mlpack] GSOC 2018 [Essential Deep Learning Modules]

Hey Marcus, As i was looking through the stacked GAN papers i came across a few versions of it. Mostly the idea behind all of them is same but a couple of things are different basically the way the whole thing is trained. Can you let me know which version of Stacked GAN do we need. or should it be