Computer game bot Turing test: Difference between revisions

Revision as of 05:06, 18 November 2022

Revision as of 05:09, 18 November 2022

Line 1:

{{Cleanup bare URLs|date=August 2022}}

{{primary sources|date=August 2017}}

The '''Computercomputer Gamegame Botbot Turing Testtest''' is a variant of the [[Turing test]], where a human judge viewing and interacting with a [[virtual world]] must distinguish between other humans and [[video game bot]]s, both interacting with the same virtual world. This variant was first proposed in 2008 by Associate Professor Philip Hingston<ref>{{Cite web|url=http://philiphingston.com/Homepage/Homepage.html|title=Philip Hingston &#124; Home}}</ref><ref name="turing">{{Cite journal|last=Hingston | publisher=IEEE Transactions on Computational Intelligence and AI in Games|first=Philip | title=A Turing Test for Game Bots | date=September 2009|url=http://www.cs.ucf.edu/~gitars/cap6671-2010/Presentations/turing.pdf}}</ref> of [[Edith Cowan University]], and implemented through a tournament called the 2K BotPrize.<ref name="BotPrize">http://botprize.org</ref>

[[File:UT^2 bot combats an opponent in the BotPrize.jpg|thumb|alt=The UT^2 bot combats an opponent in the BotPrize.|A bot combats a human opponent in the game ''[[Unreal Tournament 2004]]'']]

==History==

The Computercomputer Gamegame Botbot Turing Testtest was proposed to advance the fields of [[artificial intelligence]] (AI) and [[computational intelligence]] with respect to video games. It was considered that a poorly implemented bot implied a subpar game, so a bot that would be capable of passing this test, and therefore might be indistinguishable from a human player, would directly improve the quality of a game. It also served to debunk a flawed notion that "game AI is a solved problem."<ref name="turing"/>

Emphasis is placed on a game bot that interacts with other players in a [[Multiplayer video game|multiplayer]] environment. Unlike a bot that simply needs to make optimal human-like decisions to play or beat a game, this bot must make the same decisions while also convincing another in-game player of its human-likeness.{cn}}

==Implementation==

The Computercomputer Gamegame Botbot Turing Testtest was designed to test a bot's ability to interact with a game environment in comparison with a human player, simply 'winning' was insufficient. This evolved into a contest with a few important goals in mind:<ref name="turing"/>

* There are three participants: a human player, a computer-game bot, and a judge.

Line 29:

==Successful bots==

To date, there have been two successfully programmed bots that passed the Computercomputer Gamegame Botbot Turing Testtest:

* UT^2, a team from the [[University of Texas at Austin]], emphasized a bot that adjusted its behaviour based on previously observed human behaviour and [[neuroevolution]]. The team has made their bot available,<ref>{{Cite web|url=http://nn.cs.utexas.edu/?ut2|title = NNRG Software - UT^2: Winning Botprize 2012 Entry}}</ref> although a copy of ''[[Unreal Tournament 2004]]'' is required.<ref>Archived at [https://ghostarchive.org/varchive/youtube/20211209/VwIrZ3X4b6c Ghostarchive]{{cbignore}} and the [https://web.archive.org/web/20140421193458/http://www.youtube.com/watch?v=VwIrZ3X4b6c Wayback Machine]{{cbignore}}: {{cite AV media| url = https://www.youtube.com/watch?v=VwIrZ3X4b6c| title = UT bot kills human judge | website=[[YouTube]]}}{{cbignore}}</ref>

Line 37:

The outcome of a bot that appears more human-like than a human player is possibly overstated, since in the tournament in which the bots succeeded, the average 'humanness' rating of the human players was only 41.4%.<ref>{{Cite web |url=http://botprize.org/result.html |title=Botprize 2012 : Result |access-date=2013-02-04 |archive-url=https://web.archive.org/web/20130225095906/http://botprize.org/result.html |archive-date=2013-02-25 |url-status=dead }}</ref> This showcases some limits of this Turing test, since the results demonstrate that human behaviour is more complicated and quantitative than was accounted for.<ref>{{Cite news|title=How did this game bot score higher than humans on a Turing Test?|date=October 1, 2012|last=Dvorsky|first=George|url=http://io9.com/5947796/how-can-a-game-bot-score-higher-than-humans-on-a-turing-test}}</ref> In light of this, the BotPrize competition organizers will increase the difficulty in upcoming years with new challenges, forcing competitors to improve their bots.<ref>{{Cite news|title=More human than human: AI game bots pass Turing Test|date=September 26, 2012|first=Darren|last=Quick|url=http://www.gizmag.com/turing-test-ut2004-botprize/24308/}}</ref>

It is also believed that methods and techniques developed for the Computercomputer Gamegame Botbot Turing Testtest will be useful in fields other than video games, such as [[virtual training]] environments and in improving [[Human–robot interaction]].<ref>{{Cite news|title=Artificially Intelligent Game Bots Pass the Turing Test on Turing's Centenary|date=September 26, 2012|url=https://www.sciencedaily.com/releases/2012/09/120926133235.htm}}</ref>

==Contrasts to the Turing test==

The Computercomputer Gamegame Botbot Turing test differs from the traditional or generic [[Turing test]] in a number of ways:<ref name="turing"/>

* Unlike the traditional Turing test, for example the [[Chatterbot]]-style contest held annually by the [[Loebner Prize]] competition, the humans who played against the Computer Game Bots are not trying to convince judges they are the human; rather, they want to win the game (i.e., by achieving the highest kill score).

* Judges are not restricted to awarding only one participant in a match as the 'human' and the other as the 'non-human.' This emphasizes more qualitative rather than polarized findings.

* With regards to a successful video game bot, this is not to be confused with a claim that the bot is 'intelligent,' whereas a machine that 'passed' the Turing Testtest would arguably have some evidence for its Chatterbot's 'intelligence.'

* The game ''[[Unreal Tournament 2004]]'' was chosen for its commercial availability and its interface for creating bots, GameBots. This limitation on medium is a sharp contrast to the Turing Testtest, which emphasizes a conversation, where possible questions are vastly more numerous than the set of possible actions available in any specific video game.

* The available information to the participants, humans and bots, is not equal. Humans interact through vision and sound, whereas bots interact with data and events.

* The judges cannot introduce new events (e.g., a lava pit) to aid in differentiating between human and bot, whereas in a Chatterbot designed system, judges may theoretically ask any question in any manner.