You may have noticed that computers can now automatically learn to play ATARI games (from raw game pixels!), they are beating world champions at Go, simulated quadrupeds are learning to run and leap, and robots are learning how to perform complex manipulation tasks that defy explicit programming. It turns out that all of these advances fall under the umbrella of RL research.
This tutorial will review Deep Reinforcement Learning using Tensorflow & Keras throughout learning to beat Flappy bird and other games!
Chapter 1: Supervised learning and decision making Chapter 2: RL definitions, value iteration, policy iteration Chapter 3: Review section: autodiff, backpropagation, optimization Chapter 4: Learning dynamical system models from data Chapter 5: Deep Q-learning, SARSA, and others Chapter 6: Deep Q-learning improvmenet - DDQN Chapter 7: Advanced model learning: predicting images and videos