Deep-Reinforcement-Learning This repository provides implementations of deep reinforcement learning algorithms. The codes are mainly written in python3 using Ipython Notebook. Chapter 01: Behavior Cloning (Supervised Learning) Chapter 02: Value Iteration and Policy Iteration Chapter 03: SARSA and Q Learning Chapter 04: Deep Q Learning Chapter 05: Policy Gradient Chapter 06: Actor Critic Methods Chapter 07: Model based RL and Learning from Demonstrations Chapter 08: Inverse Reinforcement Learning Doker files for environment settings https://github.com/SKYnSPACE/DockerFiles/tree/master/py3-gym-tf1.6