Playing monopoly 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 a board game called Monopoly. 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 this game, the
robot's goal is to beat the opponent. Monopoly is a
game that can be really simple or really complex. The
really complex stuff is when players start buying
houses and hotels. The robot playing the game has a
basic understanding of monopoly and had the intention
of playing the game for a short period of time. He
doesn't overwelm himself with complex rules or
procedures.
When the robot plays
the game, he is constantly looking at the monopoly
board. When this happens, the robot is reminded of
facts and rules about the game. In particular, when
the robot focuses on specific things like the
community chest slot, he will activate specific rules
and facts about community chest. For example, when
the robot lands on the community chest slot, he will
activate the thought: "pick up the community chest
card and follow the instructions". When the robot
lands on the space that says he has to go to jail,
facts and procedures activate in his mind. The
thought activates in the robot's mind: pick up your
game piece and put it on the jail space. Other facts
and rules activate when the robot focuses on the jail
space. For example, rules start to activate: when you
are in jail, you have to pay $50 or roll a double to
get out.
Other rules of the
game activate in the background. The robot does
things in the game without consciously thinking.
Things like, move the game pieces clockwise or start
at go, are just some rules the robot follows
automatically, without thinking. The reason for this
is because the robot has played board games in the
past and his intelligent pathways in memory are
conditioned strongly. Because of experience, the
instructions in the pathways does repeated things
automatically, without consciously thinking.
Unfortunately there
are no good strategies to use to play monopoly. The
rolling of the dices and the places you land are
based on randomness. And because some features in the
game are absent, such as auctions and negotiations,
the robot has limited strategies to use in the game.
Unfortunately, this video simply shows a player (the
robot) rolling the dices, moving, and buying
property. The opponent and player takes turns doing
this over and over and over again.
The robot was able to
exact intelligent pathways from memory and these
intelligent pathways was able to form a computer
program to play monopoly. This computer program will
manage tasks, rules, and procedures when playing
monopoly. Remember, this computer program is formed
inside the robot's mind. It has adaptive behavior and
changes as the game changes.