Grokking Deep Reinforcement Learning

8 Introduction to value-based deep reinforcement learning

In this chapter

• You will understand the inherent challenges of training reinforcement learning agents with non-linear function approximators.
• You will create a deep reinforcement learning agent that, when trained from scratch with minimal adjustments to hyperparameters, can solve different kinds of problems.
• You will identify the advantages and disadvantages of using value-based methods when solving reinforcement learning problems.

Human behavior flows from three main sources: desire, emotion, and knowledge.

— Plato A philosopher in Classical Greece and founder of the Academy in Athens

We’ve made a great deal of progress so far, and you’re ready to truly grok deep reinforcement learning. ...