10. Playing an Atari Game with Deep Recurrent Q-Networks

Activity 10.01: Training a DQN with CNNs to Play Breakout

Solution

1. Open a new Jupyter Notebook and import the relevant packages: gym, random, tensorflow, numpy, and collections:

   import gym
   import random
   import numpy as np
   from collections import deque
   import tensorflow as tf
   from tensorflow.keras.models import Sequential
   from tensorflow.keras.layers import Dense, Conv2D, \
   MaxPooling2D, Flatten
   from tensorflow.keras.optimizers import RMSprop
   import datetime

2. Set the seed for NumPy and TensorFlow to 168:

   np.random.seed(168)
   tf.random.set_seed(168)

3. Create the DQN class with the following methods: the build_model() method to instantiate a CNN, the get_action() method to apply the epsilon-greedy algorithm to choose the action to be played, the add_experience() method to store in memory the experience acquired by playing the game, the replay() method, which will perform experience replay by sampling experiences from...