9. What Is Deep Q-Learning?

Activity 9.01: Implementing a Double Deep Q Network in PyTorch for the CartPole Environment

1. Open a new Jupyter notebook and import all of the required libraries:

   import gym
   import matplotlib.pyplot as plt
   import torch
   import torch.nn as nn
   from torch import optim
   import numpy as np
   import random
   import math

2. Write code that will create a device based on the availability of a GPU environment:

   use_cuda = torch.cuda.is_available()
   device = torch.device("cuda:0" if use_cuda else "cpu")
   print(device)

3. Create a gym environment using the 'CartPole-v0' environment:

   env = gym.make('CartPole-v0')

4. Set the seed for torch and the environment for reproducibility:

   seed = 100
   env.seed(seed)
   torch.manual_seed(seed)
   random.seed(seed)

5. Fetch the number of states and actions from the environment:

   number_of_states = env.observation_space.shape[0]
   number_of_actions = env.action_space.n
   print('Total number of States...