In the last few chapters, we have learned how Deep Q learning works by approximating the q function with a neural network. Following this, we have seen various improvements to Deep Q Network (DQN) such as Double Q learning, dueling network architectures, and the Deep Recurrent Q Network. We have seen how DQN makes use of a replay buffer to store the agent's experience and trains the network with the mini-batch of samples from the buffer. We have also implemented DQNs for playing Atari games and a Deep Recurrent Q Network (DRQN) for playing the Doom game. In this chapter, let's get into the detailed implementation of a dueling DQN, which is essentially the same as a regular DQN, except the final fully connected layer will be broken down into two streams, namely a value stream and an advantage stream, and these two streams will be clubbed together to compute the Q function. We will see how to train an agent for winning the car racing game with a dueling DQN. 

In this chapter, you will learn how to implement the following:

• Environment wrapper functions
• A dueling network
• Replay buffer
• Training the network
• Car racing