Playing castlevania lament (pt 2) 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 Castlevania Lament. 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.
I did videos on the
robot playing castlevania for the NES, which is 2-d.
Now, I'm trying to show people how the robot plays
castlevania in a 3-d environment. The robot has to
incorporate what he knows about the real world in
order to understand the environment in a 3-d game. He
has to know about perspective, identify walkable
areas, avoid environment objects, and understand
physical aspects of objects from different angles. He
needs to know this information to navigate the
character in the game from place to place.
The robot is also
doing multiple tasks at the same time: 1. navigate to
level boss. 2. kill enemies. 3. collect hearts. He is
actually making decisions based on all 3 tasks. The
goal is to make decisions that will satisfy all 3
tasks. Some decisions require stopping some tasks or
doing 2 (or more) tasks at the same time.
In addition, the
robot is using trial and error to fight enemies,
finding new strategies to solve a new problem, using
old strategies that are proven to work, etc. Common
sense is also telling the robot what to do next. In
the video, the robot identify a door that is blocked.
He uses logic to determine that the door will only
open if he killed every enemy in the room. This
knowledge is based on common sense. Also, the robot
is using knowledge from similar games, like 2-d
castlevania to play this 3-d game. The rules of 2-d
and 3-d castlevania are very similar. He can also use
knowledge from side-scrolling games like god of war
to play this 3-d game because the rules and
objectives of all side-scrolling action games are
very similar.