Igor V. Karpov
I am
a Ph.D.
student in the Department of
Computer Science at
the University of Texas at
Austin. I started at UT in 2004 and switched to the PhD program
after completing
my MSCS
in 2006. Before that, I graduated
from Rice University with a BS in
Computer Science in 2003. I am originally from Pushchino, Moscow
Region, Russia and I have lived in the United States since 1994.
My research centers around agents that can learn from humans. In paritcular
I am studying how machine learning methods, such as neuroevolution, can be extended
to learn effectively from human training modalities such as advice, examples, and
task shaping via environment and reinforcement.
I am a member of the Neural Networks Research
Group, and I am variously involved with the following
projects:
|
OpenNERO
- OpenNERO is an open source software platform
for research and education in Artificial Intelligence. It includes a
growing number of environments and algorithms designed to
demonstrate and compare different approaches. OpenNERO is based on
previous NERO game project
and uses the NEAT/rtNEAT
library for real-time neuroevolution. [Karpov'08].
|
|
Human-Like Behavior
in Games - The 2K BotPrize
competition challenges the participants to design an human-like
artificial player for a first-person action game (Unreal
Tournament). The task of designing a bot capable of passing a
Turing-like (though non-linguistic) test while interacting with
human players has inspired several new research directions. As part
of the UT^2 bot, I am interested in learning from collected
traces of human game behavior.[Karpov'12].
|
|
Human Assisted
Machine Learning We build and experimentally compare different
ways to leverage the complimentary strengths of human input and
machine learning techniques in order to design complex behaviors for
games and other sequential decision tasks. [Karpov'11].
|
| |
GIVE Challenge -
the goal of the GIVE challenge is to measure and improve the state
of the art in Natural Language Generation systems. The systems in
the challenge face the task of guiding human players through an
interactive 3-D environment to solve a puzzle. They are judged on
both on the objective and subjective quality of the instructions
they generate.
|
-
Igor V. Karpov, Leif Johnson, Vinod Valsalam and Risto Miikkulainen. Evaluation Methods for Active Human-Guided Neuroevolution in Games.. In 2012 AAAI Fall Symposium on Robots Learning Interactively from Human Teachers (RLIHT), Arlington, VA, November 2012.
-
Igor V. Karpov, Jacob Schrum, Risto Miikkulainen (2012). Believable Bot Navigation via Playback of Human Traces. To Appear In Philip F. Hingston, editor, Believable Bots, 2012. Springer.
-
Jacob Schrum, Igor V. Karpov and Risto Miikkulainen (2012). Humanlike Combat Behavior via Multiobjective Neuroevolution. To Appear In Philip F. Hingston, editor, Believable Bots, 2012. Springer.
-
Risto Miikkulainen, Eliana Feasley, Leif Johnson, Igor Karpov, Padmini Rajagopalan, Aditya Rawal, and Wesley Tansey (2012). Multiagent Learning through Neuroevolution. In J. Liu et al., editors, Advances in Computational Intelligence, LNCS 7311, 24-46, Berlin, Heidelberg:, 2012. Springer.
-
[workshop] Igor V. Karpov, Vinod K.Valsalam and Risto Miikkulainen (2011). Human-Assisted Machine Learning via Shaping, Advice and Examples. In 2011 IJCAI Workshop on Agents Learning Interactively from Human Teachers (ALIHT). July 2011. Barcelona, Spain.
-
Igor V. Karpov, Vinod K. Valsalam and Risto Miikkulainen (2011). Human-Assisted Neuroevolution Through Shaping, Advice and Examples. Proceedings of the Genetic and Evolutionary Computation Conference (GECCO'11). July, 2011. Dublin, Ireland.
-
[workshop] Jacob Schrum, Igor V. Karpov, Risto Miikkulainen (2011). UT^2: Human-like Behavior via Neuroevolution of Combat Behavior and Replay of Human Traces. New Orleans, LA, June 2011. Extended Abstract for the Human-like Bot Workshop at the IEEE Congress on Evolutionary Computation (CEC 2011).
-
[competition] Jacob Schrum, Igor V. Karpov, Risto Miikkulainen (2011). UT^2: Human-like Behavior via Neuroevolution of Combat Behavior and Replay of Human Traces. To Appear in Proceedings of the IEEE Symposium on Computational Intelligence and Games (CIG 2011). Seoul, South Korea. September 2011. IEEE.
-
[demo] Igor V. Karpov, John Sheblak and Risto Miikkulainen (2008). OpenNERO: a Game Platform for AI Research and Education. Proceedings of the Fourth Artificial Intelligence and Interactive Digital Entertainment Conference (AIIDE'08).
-
Joseph Reisinger, Erkin Bahceci, Igor V. Karpov and Risto Miikkulainen (2007). Coevolving Strategies for General Game Playing. Proceedings of the IEEE Symposium on Computational Intelligence and Games (CIG'07).
-
Igor V. Karpov, Thomas D'Silva, Craig Varrichio, Kenneth O. Stanley and Risto Miikkulainen (2006). Integration and Evaluation of Exploration-Based Learning in Games. Proceedings of the IEEE 2006 Symposium on Computational Intelligence in Games (CIG'06). Reno, NV: IEEE, 2006.
-
Chern Han Yong, Kenneth O. Stanley, Igor V. Karpov and Risto Miikkulainen (2006). Incorporating Advice into Neuroevolution of Adaptive Agents, Proceedings of the Artificial Intelligence and Interactive Digital Entertainment Conference (AIIDE'06). Marina Del Rey, CA: AAAI, 2006.
-
Kenneth O. Stanley, Bobby D. Bryant, Igor V. Karpov, Risto Miikkulainen (2006). Real-Time Evolution of Neural Networks in the NERO Video Game, Proceedings of the Twenty-First National Conference on Artificial Intelligence (AAAI'06). Boston, MA: AAAI, 2006.
Older and off-topic projects
- Eliot Flannery, John Novotny, Igor Karpov, Chendi Zhang, Nazareth Bedrossian. XNsim Extensible Network Simulation. Proceedings of the American Institute of Aeronautics and Astronautics (AIAA) Modeling and Simulation Conference and Exhibit, Austin, TX 2003.
- P. Read Montague, Gregory S. Berns, Jonathan D. Cohen,
Samuel M. McClure, Giuseppe Pagnoni, Mukesh Dhamala, Michael
C. Wiest, Igor Karpov, Richard D. King, Nathan Apple
and Ronald
E. Fisher, Hyperscanning:
Simultaneous fMRI during Linked Social Interactions,
NeuroImage, Volume 16, Issue 4, August 2002, Pages
1159-1164.
- Igor Karpov. Hidden Markov Model classifier for Music Genres. Undergraduate class project: Rice University, Fall 2002.
- UT-CLAMP: Connecting Language Acquisition with Machine Perception Reading Group
- UT-NLL: Natural Language Learning Reading Group
- RLRG: Reinforcement Learning Reading Group
- CPS: Center for Perceptual Systems Seminar Series
- GNOFAI: Good Not Old-Fashioned Artificial Intelligence
- FAI: Forum for Artificial Intelligence
- ALH: Agents that Learn From Humans Reading Group
I have been the Research Educator for several iterations of the
Computational Intelligence in Game Design stream of
the Freshman Research
Initiative. The goal of the two-semester course sequence is to
introduce freshmen and sophomores interested in computer science
research to the area of artificial intelligence in games.
Bookshelf
|
Programming
|
Professional Experience
|
Calendars
Miscellaneous
|
