In this chapter, we learned the basic concepts of artificial neural networks. We also learned how to apply neural network methods to our data, and how neural network algorithms work. We learned about the basic concepts that deep neural networks use to approximate reinforcement learning components.
Then, we looked at the basics of the Keras neural network model, as well as a practical example of the Keras neural network model. Then, we moved on to explore the Deep Q-learning concepts. The term "Deep Q-learning" refers to a reinforcement learning method that adopts a neural network as a function approximation. It therefore represents an evolution of the basic Q-learning method, as the state–action table is replaced by a neural network, with the aim of approximating the optimal value function. This network have the current state as input, and the corresponding...
