UT^2: Winning Botprize 2012 Entry
Released 2012
The Botprize Competition is an annual competition to program bots that appear human-like to other humans for the commercial videogame Unreal Tournament 2004. The Neural Networks Research Group has had an entry in every competition since its inception in 2008, and in 2012 our entry, UT^2, finally broke the 50% humanness threshold to win the grand prize.

This software package contains a jar file of the UT^2 bot for people that would like to run the bot "out of the box", and also contains the source code for people that want to take a closer look at how the bot works. The source code is written in Java with the help of the Pogamut API. The zip file also includes the version of GameBots used in the 2012 Botprize competition (this is a mod for Unreal 2004 that is required in order for the bot to communicate with the game, and also implements the judging rules of the Botprize competition). The UT2004 game can be most easily purchased from Steam. More information about programming bots for UT2004 is available on both the Botprize and Pogamut websites.
Download:
ZIP
Also show archived content
Igor V. Karpov Ph.D. Student ikarpov [at] gmail com
Jacob Schrum Ph.D. Alumni schrum2 [at] cs utexas edu
Believable Bot Navigation via Playback of Human Traces Igor V. Karpov, Jacob Schrum, Risto Miikkulainen In Philip F. Hingston, editors, Believable Bots, 151--170, 2012. Springer Berlin Heidelberg. 2012

Humanlike Combat Behavior via Multiobjective Neuroevolution Jacob Schrum, Igor V. Karpov and Risto Miikkulainen In Philip F. Hingston, editors, Believable Bots, 119--150, 2012. Springer Berlin Heidelberg. 2012

UT^2: Human-like Behavior via Neuroevolution of Combat Behavior and Replay of Human Traces Jacob Schrum, Igor V. Karpov and Risto Miikkulainen In Proceedings of the IEEE Conference on Computational Intelligence and Games (CIG 2011), 329... 2011