# Deep Q-learning

You've toured the foundations of deep learning, and you already know Q-learning; since deep Q-learning consists of combining Q-learning and deep learning, you're ready to get an intuitive grasp of deep Q-learning and crush it.

Before we start, try to guess some of how this is going to work. I would like you to take a moment and think about how you could integrate Q-learning into an ANN.

First things first, you might have guessed what the inputs and outputs of the neural network are going to be. The input of the artificial neural network is of course going to be the input state, which could be a 1-dimensional vector encoding what is happening in the environment, or an image (like the ones seen by a self-driving car). And the output is going to be the set of Q-values for each action, meaning it is going to be a 1-dimensional vector of several Q-values, one for each action that can be performed. Then, just like before, the AI takes the action...