Playing zelda (pt 3) 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).
A robot with human level
artificial intelligence is a robot that can do any
human task. It can drive a car, fly a plane, cook in
a restaurant, play videogames, play boardgames, etc.
Building a robot that can do any human task is the
holy grail of Artificial Intelligence.
This video is silent
because I wanted the viewers to see the thoughts of
the robot while playing the game. The robot's
conscious is the voice in his head that gives
instructions or information. This conscious allows
the robot to play the game in an intelligent manner.
The reason RPG games,
like Zelda is so difficult is because there are no
instructions given to the player. In fact, the rules
of the game and the objectives of the game are not
disclosed. The robot has to discover the rules and
objectives of the game through trial and error.
Playing the entire
game of Zelda takes a very long time. I have broken
up my zelda video into segments and each segment
shows 1 or 2 objectives of the robot during the game.
In this video, the character's main objective is to
find and navigate to level 2. During the gameplay the
character is trying to find where level 2 is located.
The instruction manual doesn't say where level 2-8
are. The robot uses logic to come up with a plan to
find level 2. His plan is to search west and east
from the starting point. Since level 2 follows level
1, then level 2 must be close by.
During his
exploration, the character accidentally finds level
3. The robot knows that it isn't wise to play level 3
yet because the levels should be completed linearly.
After exploring further he eventually finds level 2.
This example is very
similar to a tourist that is lost in a city and his
goal is to find the nearest Mcdonald. No smartphone
or maps are used here, the tourist has to explore
using logic to find the nearest Mcdonald. After
exploring for several hours, the tourist should find
the closest Mcdonald. The key here is that the
tourist is using logic and common sense to narrow the
searches and to find the nearest Mcdonald in the
fastest time possible.