The reader will be introduced to more advanced Q-learning problems and will get suggestions on how to take an RL approach to real-world problems. They will become familiar with research in Q-learning and the current problems practitioners are working on solving. They will leave this section with a sense of what is coming up next in RL and how they can apply their skills to those problems moving forward.
The following chapters are included in this section:
- Chapter 7, Decoupling Exploration and Exploitation in Multi-Armed Bandits
- Chapter 8, Further Q-Learning Research and Future Projects
