Coding Exercise

In the following Workspace, you will explore implementations of two different policy-based methods.

## Exercise #1

In this exercise, you'll explore an implementation of a cross-entropy method. To begin, open the Workspace in the next concept, and open CEM.ipynb (in the cross-entropy folder).

## Exercise #2

In this exercise, you'll explore an implementation of hill-climbing with adaptive noise scaling. To begin, open the Workspace in the next concept, and open Hill_Climbing.ipynb (in the hill-climbing folder).

## Note

In the Workspace, you will have the option to ENABLE GPU to accelerate training. After training, you can use the provided code in the Jupyter notebook to watch your agent's performance. Note that if visualizing the trained agent in the Workspace, GPU should be disabled -- otherwise the notebook will return an error.

Thus, you are encouraged to follow the following workflow:

1. train the agent with GPU enabled, and save the trained model weights,
2. disable GPU, load the trained weights from file, and watch the trained agent.