Playing Super Street Fighter 4 (Ryo vs
Viper) using Human Level Artificial Intelligence
Note: To make this website free to the public
please click on an ad to support my sponsors or you
can make a tax-deductable donation using Paypal
(click on the donation icon on the left).
This video shows a
robot playing Super Street Fighter 4. There are no
sound in the video because I wanted to show the
viewers what the robot is thinking while playing the
game. The flashing text and freeze frames are the
internal thoughts of the robot and not instruction
text for the viewers. These internal thoughts
describe the details of how the robot produce
intelligence.
In this video the
player is playing an opponent he has never played
before. At the beginning, the robot is using common
knowledge of playing different characters. As he
plays the game, the robot learns the opponent's
moves, strategies, and weaknesses. It is through
trial and error that the robot learns the optimal
skills to beat an unknown opponent.
This is important
because it shows viewers that the robot has the
ability to adapt his fighting style to an unknown
opponent. Not only can he defeat Viper in the game,
but any character in the game (known and unknown). As
stated before, machine learning is not used here. In
fact, if you want to build a robot that has universal
AI, you can't use machine learning. The robot in the
video was able to teach itself how to defeat an
unknown opponent. It was through trial and error the
robot learned the skills to fight and ultimately
defeat the opponent.