In this chapter, you will be introduced to deep learning (DL) in order to handle newer, more challenging infinite Markov decision process (MDP) problems. We will cover some basics about DL that are relevant to reinforcement learning (RL), and then look at how we can solve a Q-learning. After that, we will look at how to build a Deep Q-learning or DQN agent in order to solve some Gym environments.
Here is a summary of the topics we will cover in this chapter:
- DL for RL
- Using PyTorch for DL
- Building neural networks with PyTorch
- Understanding DQN in PyTorch
- Exercising DQN
In this chapter, we introduce DL with respect to RL. Applying DL to deep reinforcement learning (DRL) is quite specific and is not covered in detail here.
