We will learn how to build more advanced Q-learning models by combining Q-learning with deep learning and giving the agent an existing model of a problem to work from. We will learn the challenges of reinforcement learning in an environment with sparse data and will work with delayed returns. The reader will become familiar with implementing deep Q-networks to solve problems and learn about the different challenges they can be used to address.
The following chapters are included in this section:
- Chapter 5, Building Q-Networks with TensorFlow
- Chapter 6, Digging Deeper into Deep Q-Networks with Keras and TensorFlow
