Over the past several years, one of the most notable applications of Artificial Intelligence (AI) has been in the game-playing space. Especially with the recent success of AlphaGo and AlphaGo Zero, game-playing AIs have been a topic of great public interest. In this chapter, we'll implement two basic versions of game-playing AIs; one for a video game and one for a board game. We'll primarily be utilizing reinforcement learning methods as our workhorse. We'll also touch upon the methods behind some of the most advanced game-playing AIs in existence at the moment.
In this chapter, the following topics will be covered:
- Game Trees and Fundamental Game Theory
- Constructing an AI agent to play tic-tac-toe
- Constructing an AI agent to play a simple Atari game
