This repository contains code for reinforcement learning that I go on learning and implementing as I dwelve further into this field.

This repository contains two major parts as of now -

• Sutton-Book- Implementation of codes from the book by Sutton and Barto.
• CS294-Berkeley- Assignment from the course on Deep Reinforcement learning offered at Berkeley

• Chapter2 ->Armed Bandit Problems
• Chapter3 ->MDP-State/Action Value estimates
• Chapter4 ->DynamicProgramming-Policy/Value iteration,Policy improvement

• Assignment1 ->Imitation Learning algos,Dagger