Hands-On Reinforcement Learning with Python

Basic Doom game

Before diving in, let us familiarize ourselves with a vizdoom environment by seeing a basic example:

1. Let's load the necessary libraries:

from vizdoom import *import randomimport time

2. Create an instance to the DoomGame:

game = DoomGame() 

3. As we know ViZDoom provides a lot of Doom scenarios, let us load the basic scenario:

game.load_config("basic.cfg")

4. The init() method initializes the game with the scenario:

game.init()

5. Now, let's define the one with hot encoded actions:

shoot = [0, 0, 1]left = [1, 0, 0]right = [0, 1, 0]actions = [shoot, left, right]

6. Now, let us start playing the game:

no_of_episodes = 10for i in range(no_of_episodes):         # for each episode start the game    game.new_episode()     # loop until the episode ...