PyTorch 1.x Reinforcement Learning Cookbook

How to do it...

Let's solve the Pong environment using a CNN-based DQN as follows:

1. Import the necessary modules and create a Pong environment:

 >>> import gym >>> import torch >>> import random >>> from collections import deque >>> import copy >>> from torch.autograd import Variable >>> import torch.nn as nn >>> import torch.nn.functional as F >>> env = gym.envs.make("PongDeterministic-v4")

2. Then, we specify three actions:

 >>> ACTIONS = [0, 2, 3] >>> n_action = 3

These actions are not moving, moving up, and moving down.

3. Now, we develop an image processing function to downsize the image:

 >>> import torchvision.transforms as T >>> from PIL import Image >>> image_size = 84 >>> transform = T.Compose([T.ToPILImage(), ... T.Resize((image_size, ...