An artificially intelligent (AI) virtual gamer coded by University of Texas at Austin scientists recently won the prestigious BotPrize after impressing judges with its human-like abilities in Unreal Tournament 2004.
"The idea is to evaluate how we can make game bots, which are nonplayer characters (NPCs) controlled by AI algorithms, appear as human as possible," explained Professor Risto Miikkulainen, who created the UT^2 game bot with doctoral students Jacob Schrum and Igor Karpov.
As you can see in the video above, the bots face off in a tournament against one another and about an equal number of humans, with each player trying to score points by eliminating its opponents. Each player also carries a "judging gun" in addition to its usual complement of weapons which is used to tag opponents as human or bot.
The bot that scores as most human-like by the human judges is named the winner. UT^2, which clinched a warm-up competition last month, shared the honors with MirrorBot, which was programmed by Romanian computer scientist Mihai Polceanu. Interestingly, the winning bots both achieved a humanness rating of 52 percent, while human players received an average humanness rating of only 40 percent.
"When this 'Turing test for game bots' competition was started, the goal was 50 percent humanness. It took us five years to get there, but that level was finally reached last week, and it's not a fluke," said Miikkulainen.
Indeed, the complex gameplay and 3D environments require that bots mimic humans in a number of ways, including moving around in 3-D space, engaging in chaotic combat against multiple opponents and reasoning about the best strategy at any given point in the game. Even displays of distinctively human irrational behavior can, in some cases, be emulated.
According to doctoral student Jacob Schrum, human players tend to tenaciously pursue specific opponents without regard for optimality.
"When humans have a grudge, they'll chase after an enemy even when it's not in their interests. We can mimic that behavior. In order to most convincingly mimic as much of the range of human behavior as possible, the team takes a two-pronged approach," he explained.
"Some behavior is modeled directly on previously observed human behavior, while the central battle behaviors are developed through a process called neuroevolution, which runs artificially intelligent neural networks through a survival-of-the-fittest gauntlet that is modeled on the biological process of evolution."
The "Turing test" stands as one of the foundational definitions of what constitutes true machine intelligence. Turing argued that we will never be able to see inside a machine's hypothetical consciousness, so the best measure of machine sentience is whether it can fool us into believing it is human.