Codex Gamicus
Explore
Main Page
Discuss
All Pages
Interactive Maps
navigation
Main page
Community portal
Recent changes
Random page
Admin noticeboard
Forums
Company Index
Character Index
Hardware Index
In-Game Index
Ratings Index
Video Game Index
Fandom
Gamepedia support
Report a bad ad
Help Wiki
Contact us
FANDOM
Fan Central
BETA
Games
Anime
Movies
TV
Video
Wikis
Explore Wikis
Community Central
Start a Wiki
Don't have an account?
Register
Sign In
Sign In
Register
Fandom's centric source of video game knowledge
42,423
pages
Explore
Main Page
Discuss
All Pages
Interactive Maps
navigation
Main page
Community portal
Recent changes
Random page
Admin noticeboard
Forums
Company Index
Character Index
Hardware Index
In-Game Index
Ratings Index
Video Game Index
Fandom
Gamepedia support
Report a bad ad
Help Wiki
Contact us
Editing
Game artificial intelligence
(section)
Back to page
Edit
VisualEditor
View history
Talk (0)
Edit Page
Game artificial intelligence
Warning:
You are not logged in. Your IP address will be publicly visible if you make any edits. If you
log in
or
create an account
, your edits will be attributed to your username, along with other benefits.
Anti-spam check. Do
not
fill this in!
==History== Game playing was an area of research in AI from its inception. In 1951, using the [http://en.wikipedia.org/wiki/Ferranti_Mark_1 Ferranti Mark 1] machine of the [http://en.wikipedia.org/wiki/University_of_Manchester University of Manchester], [http://en.wikipedia.org/wiki/Christopher_Strachey Christopher Strachey] wrote a checkers program and Dietrich Prinz wrote one for chess.<sup class="reference" id="cite_ref-0">[http://en.wikipedia.org/wiki/Artificial_intelligence_%28video_games%29#cite_note-0 [1]]</sup> These were among the first computer programs ever written. [http://en.wikipedia.org/wiki/Arthur_Samuel Arthur Samuel]'s checkers program, developed in the middle 50s and early 60s, eventually achieved sufficient skill to challenge a respectable amateur.<sup class="reference" id="cite_ref-1">[http://en.wikipedia.org/wiki/Artificial_intelligence_%28video_games%29#cite_note-1 [2]]</sup> Work on checkers and chess would culminate in the defeat of [http://en.wikipedia.org/wiki/Garry_Kasparov Garry Kasparov] by [http://en.wikipedia.org/wiki/IBM IBM]'s [http://en.wikipedia.org/wiki/Deep_Blue_%28chess_computer%29 Deep Blue] computer in 1997.<sup class="reference" id="cite_ref-2">[http://en.wikipedia.org/wiki/Artificial_intelligence_%28video_games%29#cite_note-2 [3]]</sup> The first [http://en.wikipedia.org/wiki/Video_game video games] developed in the 1960s and early 1970s, like ''[http://en.wikipedia.org/wiki/Spacewar%21 Spacewar!]'', ''[http://en.wikipedia.org/wiki/Pong Pong]'' and ''[http://en.wikipedia.org/wiki/Gotcha_%28arcade_game%29 Gotcha]'' ([http://en.wikipedia.org/wiki/1973_in_video_gaming 1973]), were games implemented on [http://en.wikipedia.org/wiki/Discrete_logic discrete logic] and strictly based on the competition of two players, without AI. Games that featured a [http://en.wikipedia.org/wiki/Single_player single player] mode with enemies started appearing in the 1970s. The first notable ones for the [http://en.wikipedia.org/wiki/Arcade_game arcade] included the [http://en.wikipedia.org/wiki/1974_in_video_gaming 1974] [http://en.wikipedia.org/wiki/Atari Atari] games ''[http://en.wikipedia.org/wiki/Qwak%21_%28arcade_game%29 Qwak]'' (duck hunting) and ''[http://en.wikipedia.org/wiki/Pursuit_%28arcade_game%29 Pursuit]'' (fighter aircraft dogfighting simulator). Two text-based computer games from [http://en.wikipedia.org/wiki/1972_in_video_gaming 1972], ''[http://en.wikipedia.org/wiki/Hunt_the_Wumpus Hunt the Wumpus]'' and ''[http://en.wikipedia.org/wiki/Star_Trek_%28script_game%29 Star Trek]'', also had enemies. Enemy movement was based on stored patterns. The incorporation of [http://en.wikipedia.org/wiki/Microprocessor microprocessors] would allow more computation and random elements overlaid into movement patterns. The idea was used by ''[http://en.wikipedia.org/wiki/Space_Invaders Space Invaders]'' ([http://en.wikipedia.org/wiki/1978_in_video_gaming 1978]), sporting an increasing difficulty level, distinct movement patterns, and in-game events dependent on [http://en.wikipedia.org/wiki/Hash_function hash functions] based on the player's input. ''[http://en.wikipedia.org/wiki/Galaxian Galaxian]'' ([http://en.wikipedia.org/wiki/1979_in_video_gaming 1979]) added more complex and varied enemy movements. ''[http://en.wikipedia.org/wiki/Pac-Man Pac-Man]'' ([http://en.wikipedia.org/wiki/1980_in_video_gaming 1980]) applied these patterns to maze games, with the added quirk of different personalities for each enemy, and ''[http://en.wikipedia.org/wiki/Karate_Champ Karate Champ]'' ([http://en.wikipedia.org/wiki/1984_in_video_gaming 1984]) to fighting games, although the poor AI prompted the release of a second version. Games like ''[http://en.wikipedia.org/wiki/Madden_NFL Madden Football]'', ''[http://en.wikipedia.org/wiki/Earl_Weaver_Baseball Earl Weaver Baseball]'' and ''[http://en.wikipedia.org/wiki/Tony_La_Russa_Baseball Tony La Russa Baseball]'' all based their AI on an attempt to duplicate on the computer the coaching or managerial style of the selected celebrity. Madden, Weaver and La Russa all did extensive work with these game development teams to maximize the accuracy of the games.Later sports titles allowed users to "tune" variables in the AI to produce a player-defined managerial or coaching strategy. The emergence of new game genres in the 1990s prompted the use of formal AI tools like [http://en.wikipedia.org/wiki/Finite_state_machines finite state machines]. [http://en.wikipedia.org/wiki/Real-time_strategy Real-time strategy] games taxed the AI with many objects, incomplete information, pathfinding problems, real-time decisions and economic planning, among other things. The first games of the genre had notorious problems. ''[http://en.wikipedia.org/wiki/Herzog_Zwei Herzog Zwei]'' (1989), for example, had almost broken pathfinding and very basic three-state state machines for unit control, and ''[http://en.wikipedia.org/wiki/Dune_II Dune II]'' (1992) attacked the players' base in a beeline and used numerous cheats Later games in the genre exhibited more sophisticated AI. Later games have used bottom-up AI methods, such as the [http://en.wikipedia.org/wiki/Emergent_behaviour emergent behaviour] and evaluation of player actions in games like ''[http://en.wikipedia.org/wiki/Creatures_%28artificial_life_program%29 Creatures]'' or ''[http://en.wikipedia.org/wiki/Black_%26_White_%28video_game%29 Black & White]''. [http://en.wikipedia.org/wiki/Fa%C3%A7ade_%28interactive_story%29 Façade (interactive story)] was released in 2005 and used interacitve multiple way dialogs and AI as the main aspect of game. Games have provided an environment for developing artificial intelligence with potential applications beyond gameplay. Examples include [http://en.wikipedia.org/wiki/Watson_%28artificial_intelligence_software%29 Watson], a [http://en.wikipedia.org/wiki/Jeopardy Jeopardy]-playing computer; and the [http://en.wikipedia.org/wiki/RoboCup RoboCup] tournament, where robots are trained to compete in soccer.
Summary:
Please note that all contributions to the Codex Gamicus are considered to be released under the CC BY-SA 3.0
Cancel
Editing help
(opens in new window)
Follow on IG
TikTok
Join Fan Lab