Not sure where to start?

If you're not sure where to start, here are some suggestions for how to make some progress with the project. You need not follow this advice; these are only suggestions, and you should follow whatever path works best for you!

## Step 1: Master the details of Deep Q-Networks (DQN).

Read the DQN paper to master all of the details. Refer to the lesson on Deep Q-Networks to cement your understanding. If you have any questions, post them in Slack or Knowledge!

## Step 2: Study the coding exercise from the lesson.

In the Deep Q-Networks lesson, you applied a DQN implementation to an OpenAI Gym task. Take the time to understand this code in great detail. Tweak the various hyperparameters and settings to build your intuition for what should work well (and what doesn't!).

## Step 3: Adapt the code from the lesson to the project.

Adapt the code from the exercise to the project, while making as few modifications as possible. (Remember that the code that you use to interact with the Unity environment is different from the OpenAI gym interface.) Don't worry about efficiency, and just make sure the code runs. Don't worry about modifying hyperparameters, optimizers, or anything else of that nature just yet.

For this step, you do not need to run your code on a GPU. In particular, if working in the Udacity Workspace, GPU should not be enabled. Save your GPU hours (if needed) for the next step!

## Step 4: Optimize the hyperparameters.

After you have verified that your DQN code runs, try a few long training sessions while running your code on CPU. If your agent fails to learn, try out a few potential solutions by modifying your code. Once you're feeling confident (or impatient :)) try out your implementation with GPU support! (Note that you may not need GPU at all. For instance, we found that our implementation trained quickly enough on CPU.)