Playing Atari games with a DQN and its variants

Now, let's learn how to create a DQN to play Atari games with Stable Baselines. First, let's import the necessary modules:

from stable_baselines import DQN

Since we are dealing with Atari games, we can use a convolutional neural network instead of a vanilla neural network. So, we use CnnPolicy:

from stable_baselines.deepq.policies import CnnPolicy

We learned that we preprocess the game screen before feeding it to the agent. With Stable Baselines, we don't have to preprocess manually; instead, we can make use of the make_atari module, which takes care of preprocessing the game screen:

from stable_baselines.common.atari_wrappers import make_atari

Now, let's create an Atari game environment. Let's create the Ice Hockey game environment:

env = make_atari('IceHockeyNoFrameskip-v4')

Instantiate the agent:

agent = DQN(CnnPolicy, env, verbose=1)

Train the agent...