Hello everyone, I’m Shangtong Zhang. It has been two years since last time I coded in mlpack for mean shift and CNN. Now I’m a MSc student in University of Alberta supervised by Prof Richard Sutton. My primary interest is reinforcement learning. I wrote python code <https://github.com/ShangtongZhang/reinforcement-learning-an-introduction> for the book Reinforcement Learning: An Introduction(2nd Edition). However I don’t have much experience with DeepRL, so this project interests me.
To warm up, I proposed a framework for Q-Learning with an implementation of DQN with experience replay and target network. The pull request is here <https://github.com/mlpack/mlpack/pull/934> I test it in Mountain Car task. The PR is just to show my design, it’s not ready to merge. I think we need to support batch update for our network component to make deep RL more efficient. Looking forward to any feedback. Thanks, Shangtong Zhang, First year graduate student, Department of Computing Science, University of Alberta Github <https://github.com/ShangtongZhang> | Stackoverflow <http://stackoverflow.com/users/3650053/slardar-zhang>
_______________________________________________ mlpack mailing list [email protected] http://knife.lugatgt.org/cgi-bin/mailman/listinfo/mlpack
