Hands-On Reinforcement Learning for Games

Going Deeper with DDQN

Deep learning is the evolution of raw computational learning and it is quickly evolving and starting to dominate all areas of data science, machine learning (ML), and artificial intelligence (AI) in general. In turn, these enhancements have brought about incredible innovation in deep reinforcement learning (DRL) that have allowed it to play games, previously thought to be impossible. DRL is now able to tackle game environments such as the classic Atari 2600 series and play them better than a human. In this chapter, we'll look at what new features in DL allow DRL to play visual state games, such as Atari games. First, we'll look at how a game screen can be used as a visual state. Then, we'll understand how DL can consume ...