Hello Abhijeet, thanks for your interest in the project.
> Please guide me and provide me relevant links. Some starter level bugs would > be > helpful so that I can get familiar with the codebase. I just opened some network related issues on Github, I'll see if I can add some more in the next days; maybe you can find one of those interesting? https://github.com/mlpack/mlpack/issues Maybe these pages are also helpful: http://www.mlpack.org/involved.html http://www.mlpack.org/gsoc.html There are also other issues open on the Github issue tracker, and any contributions of new techniques or efficiency improvements for existing implementations are always welcome. About the project, to be successful at this project, you should have a good knowledge of reinforcement learning; i.e., you should be familiar with the way agents are typically built and trained, and certainly, you should be familiar with the individual components that you plan to implement. Besides that, I think I said this before somewhere, there are some ways to work with the code, e.g. by implementing an agent that is capable of solving some tasks. Normally I recommend taking a look at Policy Gradients, which are powerful but also really intuitive when it comes to the implementation. Since you said you already worked on an agent that can play carrom, which sounds really interesting, maybe you can rewrite the code using mlpack? Don't feel obligated, it's just an idea, we know it's often not that easy to find the time to work on a project if you have a trillion other things to do. I hope this is helpful, let us know if you have any more questions. Thanks, Marcus > On 28 Feb 2017, at 11:55, Abhijeet Dubey <[email protected]> wrote: > > Hi, > > I'm Abhijeet Dubey, I'm pursuing my Masters in Computer Science with focus in > Machine Learning & Artificial Intelligence from Indian Institute of > Technology, Bombay. I'm interested in participating in GSoC 2017 with mlpack. > > I've gone through the project page and particularly I'm interested in > "Reinforcement Learning" project. I'm proficient in C++ and python and I've > experience in applying machine learning and general reinforcement learning. > I've also done a project involving reinforcement learning... so basically my > project was to design an intelligent agent that can play carrom. > > Please guide me and provide me relevant links. Some starter level bugs would > be helpful so that I can get familiar with the codebase. > > Thanks & Regards, > Abhijeet Dubey > https://github.com/dracarys09/ > <https://github.com/dracarys09/>_______________________________________________ > 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
