Artificial Intelligence in Video Games

Artificial intelligence (AI) is the intelligence of machines and the branch of computer science that aims to create it. AI textbooks define the field as "the study and design of intelligent agents" where an intelligent agent is a system that perceives its environment and takes actions that maximize its chances of success
Game artificial intelligence refers to techniques used in computer and video games to produce the illusion of intelligence in the behavior of non-player characters (NPCs). The techniques used typically draw upon existing methods from the field of artificial intelligence (AI).Since game AI is centered on appearance of intelligence and good gameplay, its approach is very different from that of traditional AI,the computer abilities must be toned down to give human players a sense of fairness. This, for example, is true in first-person shooter games, where NPCs' otherwise perfect aiming would be beyond human skill.

There are many types of computer programs that use AI. Market
simulators, logic systems, and economic planners are some of the different fields
of computer software that rely heavily on elements of artificial intelligence. These
elements include situation calculus, tree searching, problem solving, and
decision-making. But one genre of software programming has been slowly
borrowing more and more from the field of AI is video gaming.
Video games have gone through drastic improvements in the past ten
years. It seems as if Moore’s law applies to video games as well as processor
speed. Video games seem to get twice as complex in some ways every eighteen
months. As these games get more complex they also get more interesting and
engaging. Video games are no longer just a distraction from work or a thirtyminute
escape from reality. They are becoming an artistic form of expression for
the programmers and developers and a serious hobby and undertaking for the
players.
Physicist Willy Higinbotham created the first video game in 1958. It was
called “Tennis For Two” and was played on an oscilloscope. The first game to
run on a computer was “Spacewar” by Steve Russell from MIT. The graphics
were ASCII characters and it ran on a Digital PDP-1 mainframe.
The history of artificial intelligence in video games dates back to the midsixties.
Before that, games were either two-player (meaning that there was no
computer opponent) or any non-human objects were hard-coded. An example of
hard-coded video game objects are the little aliens in “Space Invaders” that
swoop down at the human player. The human player must shoot the aliens
before they reach the bottom of the screen. The manner in which these aliens
move is explicitly coded into the game and is not determined at runtime by any
precepts. The earliest real artificial intelligence in gaming was the computer
opponent in “Pong” or variations thereof (of which there were many). The
computer paddle would do its best to block the ball from scoring by hitting it back
at the user. Determining where to move the paddle was accomplished by a
simple equation that would calculate at exactly what height the ball would cross
the goal line and move the paddle to that spot as fast as allowed. Depending on
the difficulty setting, the computer might not move fast enough to get to the spot
or may just move to the wrong spot with some probability

For a long time no video game AI was not much more intelligent the
“Pong” AI. This was because the games were relatively simple and most often
played with a second player instead of a computer opponent. Atari sports games
AI agents were basically goal-oriented towards scoring points and governed by
simple rules that controlled when to pass, shoot, or move. The advent of fighting
games such as “Kung Foo” for Nintendo or “Mortal Kombat” for Sega Genesis
saw only a slight improvement in AI. The moves of the computer opponents
were determined by what each player was currently doing and where they were
standing. In the most basic games, there was simply a lookup table for what was
currently happening and the appropriate best action. In the most complex cases,
the computer would perform a short minimax search of the possible state space
and return the best action. The minimax search had to be of short depth since
the game was occurring in real-time. Real-time game play has always been
major setback for AI in video games. There is very little time to compute actions
and possible future states when the action never stops.


Chinook is a computer program that plays English draughts (also known as checkers), developed around 1989 at the University of Alberta, led by Jonathan Schaeffer. Other developers are Rob Lake, Paul Lu, Martin Bryant, and Norman Treloar. In July 2007, Chinook's developers announced that the program has been improved to the point where it cannot lose a game.
Chinook's program algorithm includes an opening book, a library of opening moves from games played by grandmasters; a deep search algorithm; a good move evaluation function; and an end-game database for all positions with eight pieces or fewer. The linear handcrafted evaluation function considers several features of the game board, including piece count, kings count, trapped kings, turn, runaway checkers (unimpeded path to be kinged) and other minor factors. All of Chinook's knowledge was programmed by its creators, rather than learned with artificial intelligence
The best games adapt to the player to provide an entertaining experience. But handling adaptation in immersive 3D worlds isn’t trivial! In terms of AI, the challenge is to build a system that:
1. Requires little work to script each possible adaptation,
2. Allows you to control the outcome to prevent unrealistic situations


-
N.HARDEV
CH09B066