Coding Exercise

In this exercise, you will use an implementation of REINFORCE to solve OpenAI Gym's CartPole environment.

Note: In the implementation, each trajectory corresponds to a full episode, and we collect m=1 trajectories. You're strongly encouraged to refer to the pseudocode for REINFORCE while perusing the implementation.

Later in the Nanodegree program, you will learn about some modifications that you can use to improve this algorithm. You're strongly encouraged to implement these modifications, to get better performance!