Can a bot play like a human? The Turing test adjusted to games

Are you human or are you a bot? Turing test!

Until recently, research on videogames was mainly focused on having more realistic games by improving graphics and sound. However, in recent years, hardware components have experienced exponential growth and players demand higher quality opponents controlled by better articial intelligences (AI). In this context AI plays an important role in the success or failure of a game and some major AI techniques have already been used in existing videogames (e.g., evolutionary computation and neural networks are beginning to be considered with moderate success).

In First Person Shooters (FPS) games, requiring higher quality opponents means obtaining enemies exhibiting intelligent behavior; however, it is not easy to evaluate what a `human-like intelligence’ means for a bot in these games. Generally speaking, it is well known that the Turing Test is a procedure proposed by Alan Turing to corroborate the existence of intelligence in a machine (more information in  [1] . The basic fundament is that a machine that behaves intelligently might be considered as intelligent in the human sense (this sounds to Terminator 🙂 

 

2k games

In this context, the “2k bot prize” is a competition that proposes an interesting adaptation of the Turing test in the context of the well-nown FPS game Unreal Tournament 2004 (UT2004), a multi-player online FPS game in which enemy bots are controlled by some kind of game AI.

UT2004

The 2k bot prize have been  sponsored by 2K Australia since 2008, and the goal is  to create a computer game bot (a.k.a. non-player character or NPC) which is indistinguishable from a human player. In other words, based on the reasoning (and fact) that computers are fast and accurate at playing games, they wonder if bots (i.e., non-human players) can play like a human player? As it is written in the web page of the Bot Prize 2014:

 People like to play against opponents who are like themselves – opponents with personality, who can surprise, who sometimes make mistakes, yet don’t blindly make the same mistakes over and over. The BotPrize competition challenges programmers/researchers/hobbyists to create a bot for UT2004 (a first-person shooter) that can fool opponents into thinking it is another human player.

This competition was created and is usually organised by Associate Professor Philip Hingston, of Edith Cowan University, in Perth, Western Australia. The competition has been sponsored by 2K games since 2008, with up to $7000 prize money.

Dou you accept the challenge? Do you dare to try implementing a human-like bot for a FPS game? Try it…..Let’s try…

(Note: In the past, I worked on this issue and you can find a paper of mine in [2]. I will insist more on this issue in further posts)

References:

[1] Turing, A.: Computing machinery and intelligence. Mind 59 (1950) 433-460.

[2] Antonio José Fernández Leiva, Jorge L. O’Valle Barragán: Decision Tree-Based Algorithms for Implementing Bot AI in UT2004. IWINAC (1) 2011: 383-392