I was fascinated the first time when Google release its AlphaGo which beat all the pro player and was just amazed by Progress the OPENAI made which Destroyed all the pro player in the history of dota2 and was always curious how these system learns . So ,basically the purpose of this Repo is learning Reinforcement.
I will be updating the repo everytime i learned new things to implement RL algorithems.
So, I will be using python 3 as a coding environment and OpenAI Gym as a RL environments and Tensorflow and Keras for neural Network implementations.