Deep Reinforcement Learning with Python - Second Edition

9

Deep Q Network and Its Variants

In this chapter, let's get started with one of the most popular Deep Reinforcement Learning (DRL) algorithms called Deep Q Network (DQN). Understanding DQN is very important as many of the state-of-the-art DRL algorithms are based on DQN. The DQN algorithm was first proposed by researchers at Google's DeepMind in 2013 in the paper Playing Atari with Deep Reinforcement Learning. They described the DQN architecture and explained why it was so effective at playing Atari games with human-level accuracy. We begin the chapter by learning what exactly a deep Q network is, and how it is used in reinforcement learning. Next, we will deep dive into the algorithm of DQN. Then we will learn how to implement DQN to play Atari ...