As human beings, we learn from experiences. We have not become so charming overnight or by accident. Years of compliments as well as criticism have all helped shape who we are today. We learn how to ride a bike by trying out different muscle movements until it just clicks. When you perform actions, you are sometimes rewarded immediately, and this is known as reinforcement learning (RL).
This chapter is all about designing a machine learning system driven by criticisms and rewards. We will see how to develop a demo GridWorld game using Deeplearning4j (DL4J), reinforcement learning 4j (RL4J), and Neural Q-learning that acts as the Q function. We will start from reinforcement learning and its theoretical background so that the concept is easier to grasp. In summary, the following topics will be covered in this chapter:
- Notation...