I'm a Ph.D. student at the University of Texas at Austin
in the Department of Computer Science.
I've already received a Master of Science in Computer Sciences (MSCS) degree from the department as a stepping stone
on the way to my Ph.D. I made my dissertation proposal on Evolving Multimodal Behavior
in the Fall of 2009, and am currently in candidacy. I received my B.S.
from Southwestern University in Georgetown, Texas, where I
triple-majored in Computer Science, Math, and German.
My dissertation advisor is Risto Miikkulainen of the
Neural Networks Research Group.
I'm interested in automatic discovery of complex multi-modal behavior, particularly in the domain of video games.
Agents that can behave in different manners in response to different situations are crucial for games because
they are so complex, and human players adapt so quickly. I'm particularly interested in the use of multiobjective
evolution and neuroevolution in these domains. Furthermore, because I believe in the power of evolution via
natural selection, I think it should be possible to find domain-independent methods to solve these tasks.
Therefore I also study and develop domain-independent shaping methods to help evolution.
The less expert knowledge, the better.
So far this research has primarily used the BREVE simulation environment.
My source code is available here.
This code is offered freely without guarantee, but feel free to ask me for help
if you are interested. If you are unfamiliar with BREVE,
then I recommend you try out some of the BREVE example code first. The control
class for the simulation is Simulation.tz. Though the file
extension is tz, all files are text files. To get a list of all command line parameters, type: breve -ux Simulation.tz io off help
Lately I've moved on to working in the domain of Ms. Pac-Man using the
Java implementation available here.
I've also done some work in the domain of
Unreal Tournament 2004 using
the programming API Pogamut,
which communicates with the game according to the Gamebots
message protocol. Along with Igor Karpov,
I have participated in the annual Botprize and Humanlike Bots Competitions
every year, and at the 2012 Botprize competition our team finally won the grand prize by attaining
a humanness rating of 51.9%. We also won the year's preceding
Humanlike Bots Competition.
Information about our work in Unreal Tournament is available on our
Humanlike Bots Project Page.
There are also some movies from the 2012 competition here.
The source code for our bot is available here.
Jacob Schrum and Risto Miikkulainen (2012).
Evolving Multimodal Networks for Multitask Games,
IEEE Transactions on Computational Intelligence and AI in Games (TCIAIG 2012).
June. Volume 4, Issue 2, pages 94 - 111.
Editor: Simon M. Lucas. IEEE.
(movies)
Jacob Schrum and Risto Miikkulainen (2009).
Evolving Multi-modal Behavior in NPCs,
Proceedings of the IEEE Conference on Computational Intelligence and Games (CIG 2009).
(slides,
movies)
Best Student Paper Award
