Playing blasterball 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 blasterball. 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.
My robot doesn't use:
planning programs/heuristic searches (used by MIT and
Stanford University), Bayesian's probability theories
for decision making, Bayesian's equation for
induction and deduction, semantic networks for
natural language understanding, predicate calculus,
common sense systems, first-order logic, rule-based
systems, genetic programming, or MACHINE LEARNING.
In the video, the
robot is trying to do multiple tasks at the same
time. The game has rules and objectives to follow,
there's a weapon management system, and there are
blocks that need to be eliminated. The player (the
robot) needs to do all 3 tasks at the same time. The
robot is considering all 3 tasks when making
decisions. He makes decisions based on what benefits
him in the future. The robot's goal is to beat the
entire game and he will make decisions (every second)
that would lead him to accomplishing his goal/s.
In one of the scenes,
the robot is deciding wither to bounce the ball
around or get the L option. The L option is the most
important weapon that you can use to win the game, so
the robot decides to get the L option. However, at
the same time, the robot has to bounce the ball
around. One of the rules of the game is to not allow
the ball to pass the player (represented by a stick).
The robot has to weigh the 2 options and decide on
which option to select and commit to. After using
logic and common sense, the robot determined that the
ball will bounce on the stick in 2 seconds and the L
option will reach the stick in 4 seconds. He makes a
decision to bounce the ball first, and use the
remaining 2 seconds to get the L option. Thus, the
robot is able to accomplish both tasks by
prioritizing which task to do first and second.