Milestones in the Development of Artificial Intelligence in Games

While discussing the evolution of artificial intelligence in computer games, one definitely should mention the games which have turned out to be milestones in the development of intelligent behavior in games.

One of the most popular games of the 1990's was War Craft – a game developed by the Blizzard studio. It was the first game to employ path-finding algorithms at such a grand scale, for hundreds of units in the game engaged in massive battles. Sim City, created by the company Maxis, was the first game to prove the feasibility of using A-Life technologies in the field of computer games. Another milestone turned out to be the game Black&White, created in 2001 by Lion-head Studios, in which technologies of computer-controlled characters' learning were used for the first time.

Artificial intelligence Introduction

Introduction

Elements of artificial intelligence used in computer games have come a long way. In the beginning, the developed systems were based on sets of rules written directly in the code of the game or on the behavior
scripts interpreted by the code, with the whole thing based most commonly on the appropriate selection of importance of the random factor in the process of choosing the appropriate behavior. That time witnessed the birth of such memorable games as the immortal River-Raid, Donkey-Kong, Boulder-Dash, and many other objects of fascination for users of eight-bit machines, back in the 1970's.

Another step in the development process was introducing simple computer science methods, such as the still popular and frequently used Finite State Machine method, into describing the behavior of the computer-controlled enemies. However, as the demands of the players grew day by day, games grew more and more complicated, thanks to the use of more and more advanced computing algorithms. The dawn of the era of Introduction

Elements of artificial intelligence used in computer games have come a long way. In the beginning, the developed systems were based on sets of rules written directly in the code of the game or on the behaviour scripts interpreted by the code, with the whole thing based most commonly on the appropriate selection of importance of the random factor in the process of choosing the appropriate behaviour. That time witnessed the birth of such memorable games as the immortal River-Raid, Donkey-Kong, Boulder-Dash, and many other objects of fascination for users of eight-bit machines, back in the 1970s.

Another step in the development process was introducing simple computer science methods, such as the still popular and frequently used Finite State Machine method, into describing the behaviour of the computer-controlled enemies. However, as the demands of the players grew day by day, games grew more and more complicated, thanks to the use of more and more advanced computing algorithms. The dawn of the era of RTS-type games (Real Time Strategy) has caused a significant shift of interest (in terms of frequency of use) to algorithms which determine the optimal path between two specified points on a map.

Fast technical progress and rapid increase of processing power of home computers were also a catalyst for the development of applications using artificial intelligence in computer games. The first games and artificial intelligence algorithms had to settle for limited capabilities of machines available at that time, with the processor frequencies no higher than 2 MHz. The first PCs brought in new possibilities and new applications. After PCs with 386/486 processors became the standard for a home computer, programmers were given new possibilities; that led to the start of a race between game development companies. For a long time, the foremost indicator of a computer game's quality was the quality of three-dimensional graphics it featured; however, a realisation soon came that nice graphics, sound, and character animation is not everything. Recently, one of the most important elements of computer games has been identified as artificial intelligence – as the primary factor behind the so-called playability of present-day video games.

The process of production of computer games has undergone significant changes as well. Even though programming the artificial intelligence of a game used to be treated slightly unfairly, and its implementation tended to be pushed to near the end of the production of the game's engine, at present, planning the modules of artificial intelligence and their co-operation with other components of the game is one of the most important elements of the planning process.

More and more frequently, at least one of the members of a programming team is designated to, full-time and ever since the beginning of the project, handle designing and programming the modules of artificial intelligence.

At present, when in most homes, one can find PC-class computers with Pentium IV processors with frequencies in the range of 3 to 4 GHz, it is being considered to let computer games make use of the most advanced and sophisticated methods of artificial intelligence: neural networks, genetic algorithms, and fuzzy logic. In the age of Internet and network games, artificial intelligence systems in games have been given new tasks: a computer player should, in its behavior and strategies of playing, be indistinguishable from a real player on the other side of an Internet connection. type games (Real Time Strategy) has caused a significant shift of interest (in terms of frequency of use) to algorithms which determine the optimal path between two specified points on a map.

Fast technical progress and rapid increase of processing power of home computers were also a catalyst for the development of applications using artificial intelligence in computer games. The first games and artificial intelligence algorithms had to settle for limited capabilities of machines available at that time, with the processor frequencies no higher than 2 MHz. The first PCs brought in new possibilities and new applications. After PCs with 386/486 processors became the standard for a home computer, programmers were given new possibilities; that led to the start of a race between game development companies. For a long time, the foremost indicator of a computer game's quality was the quality of three-dimensional graphics it featured; however, a realization soon came that nice graphics, sound, and character animation is not everything. Recently, one of the most important elements of computer games has been identified as artificial intelligence – as the primary factor behind the so-called pliability of present-day video games.

The process of production of computer games has undergone significant changes as well. Even though programming the artificial intelligence of a game used to be treated slightly unfairly, and its implementation tended to be pushed to near the end of the production of the game's engine, at present, planning the modules of artificial intelligence and their co-operation with other components of the game is one of the most important elements of the planning process.

More and more frequently, at least one of the members of a programming team is designated to, full-time and ever since the beginning of the project, handle designing and programming the modules of artificial intelligence.

At present, when in most homes, one can find PC-class computers with Pentium IV processors with frequencies in the range of 3 to 4 GHz, it is being considered to let computer games make use of the most advanced and sophisticated methods of artificial intelligence: neural networks, genetic algorithms, and fuzzy logic. In the age of Internet and network games, artificial intelligence systems in games have been given new tasks: a computer player should, in its behavior and strategies of playing, be indistinguishable from a real player on the other side of an Internet connection.

Artificial Inteligence

Definition:
                         The branch of computer science concerned with making computers behave like humans.

The term was coined in 1956 by John McCarthy at the Massachusetts Institute of Technology. Artificial intelligence includes

games playing: programming computers to play games such as chess and checkers

expert systems : programming computers to make decisions in real-life situations (for example, some expert systems help doctors diagnose diseases based on symptoms)

natural language : programming computers to understand natural human languages

neural networks : Systems that simulate intelligence by attempting to reproduce the types of physical connections that occur in animal brains

robotics : programming computers to see and hear and react to other sensory stimuli

Currently, no computers exhibit full artificial intelligence (that is, are able to simulate human behavior). The greatest advances have occurred in the field of games playing. The best computer chess programs are now capable of beating humans. In May, 1997, an IBM super-computer called Deep Bluedefeated world chess champion Gary Kasparov in a chess match.

In the area of robotics, computers are now widely used in assembly plants, but they are capable only of very limited tasks. Robots have great difficulty identifying objects based on appearance or feel, and they still move and handle objects clumsily.

Natural-language processing offers the greatest potential rewards because it would allow people to interact with computers without needing any specialized knowledge. You could simply walk up to a computer and talk to it. Unfortunately, programming computers to understand natural languages has proved to be more difficult than originally thought. Some rudimentary translation systems that translate from one human language to another are in existence, but they are not nearly as good as human translators. There are also voice recognition systems that can convert spoken sounds into written words, but they do not understand what they are writing; they simply take dictation. Even these systems are quite limited -- you must speak slowly and distinctly.

In the early 1980s, expert systems were believed to represent the future of artificial intelligence and of computers in general. To date, however, they have not lived up to expectations. Many expert systems help human experts in such fields as medicine and engineering, but they are very expensive to produce and are helpful only in special situations.

Today, the hottest area of artificial intelligence is neural networks, which are proving successful in a number of disciplines such as voice recognition and natural-language processing.

There are several programming languages that are known as AI languages because they are used almost exclusively for AI applications. The two most common are LISP and Prolog.