Deep Q-Learning Algorithm

Please take the time now to read the research paper that introduces the Deep Q-Learning algorithm.

## Reading Scientific Papers

As part of this nanodegree, you will learn about many of the most recent, cutting-edge algorithms! Because of this, it will prove useful to learn how to read the original research papers. Here are some excellent tips. Some of the best advice is:

• Take notes.

• Read the paper multiple times. On the first couple readings, try to focus on the main points:

1. What kind of tasks are the authors using deep reinforcement learning (RL) to solve? What are the states, actions, and rewards?
2. What neural network architecture is used to approximate the action-value function?
3. How are experience replay and fixed Q-targets used to stabilize the learning algorithm?
4. What are the results?

• Understanding the paper will probably take you longer than you think. Be patient, and reach out to the Udacity community with any questions.

## Check Your Understanding

After you have read the paper, use the video below to check your understanding.