Excelling at games

In the remainder of this chapter, we will use Q-games with the gym package. It offers a standard API for playing different types of games, so it's the perfect test case for what we want to show you.

A small example

Anaconda doesn't ship this package, so it has to be installed though pip:

>>> pip install gym[atari]

Note

We won't use the Atari part of the gym, but it will be required for the breakout game.

From this package, we can create an environment for different games, like this:

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

This creates a new environment for the text game FrozenLake. It consists of four four-character strings, starting with S and ending up at G, the goal. But there are holes (H) on the way to this goal, and ending up there makes you lose the game:

• SFFF
• FHFH
• FFFH
• HFFG

From the environment, we can get the size of the observation space, env.observation_space.n, which is 16 here (where the player is located) and the size of the action space env.action_space.n, which is...