Reinforcement Learning Algorithms with Python

Atari games

Atari games became a standard testbed for deep RL algorithms since their introduction in the DQN paper. These were first provided in the Arcade Learning Environment (ALE) and subsequently wrapped by OpenAI Gym to provide a standard interface. ALE (and Gym) includes 57 of the most popular Atari 2600 video games, such as Montezuma's Revenge, Pong, Breakout, and Space Invaders, as shown in the following illustration. These games have been widely used in RL research for their high-dimensional state space (210 x 160 pixels) and their task diversity between games:

Figure 5.3 The Montezuma's Revenge, Pong, Breakout, and Space Invaders ...