AI Playing Games
As we mentioned last episode, one of the best test spaces for building new AI systems are games. This is because games provide a great framework for an AI to learn an objective and slowly improve. In recent years, AI has made huge strides in games from beating Jeopardy! champions to crushing a five-person team in DOTA 2. Today, we’re going to walk you through creating a Tic Tac Toe bot that uses the minimax algorithm to become undefeatable and we’ll talk about evolutionary neural networks like in SethBling’s MarI/O project. Next week we’ll create our very own game and create an AI to master it!
Tags
Comments
Leave a Comment
Comments are loading... If you don't see any, be the first to comment!
Related Videos

Crash Course: Artificial Intelligence | AI Playing Games #12 | PBS
Owner - Crash Course Artificial Intelligence - Powered By PBS

Crash Course Computer Science | 3D Graphics: Crash Course Computer Science #27 | PBS
Owner - Crash Course Computer Science - Powered By PBS
3D Graphics: Crash Course Computer Science
Crash Course Computer Science

Crash Course: Artificial Intelligence | Cats vs Dogs? Let's Make an AI to Settle This (LAB) #19 | PBS
Owner - Crash Course Artificial Intelligence - Powered By PBS
Cats Vs Dogs? Let's make an AI to settle this (LAB)
Crash Course Artificial Intelligence
Introduce the Instructor and AI
Fun Robotics

How To Turn Your SMART Goals Into Habits and Actually ACHIEVE Them
Owner - Develop Good Habits
Deepfake AI
Learning Mole
This AI Doesn’t Need Any Help from Humans
SciShow
Engineering Ethics: Crash Course Engineering #27
Crash Course Engineering
