Igor V. Karpov
Ph.D. Student
My research interests are in artificial intelligence, computational linguistics and cognitive science. In particular, I am using simulated environments (such as video games!) to study aspects of evolution, acquisition and grounding of communication and language in multi-agent systems.
Homepage:
http://www.cs.utexas.edu/~ikarpov/
Publications (12)
Believable Bot Navigation via Playback of Human Traces 2012
Igor V. Karpov, Jacob Schrum, Risto Miikkulainen
Evaluation Methods for Active Human-Guided Neuroevolution in Games 2012
Igor Karpov, Leif Johnson, Vinod Valsalam and Risto Miikkulainen
Humanlike Combat Behavior via Multiobjective Neuroevolution 2012
Jacob Schrum, Igor V. Karpov and Risto Miikkulainen
Multiagent Learning through Neuroevolution 2012
Risto Miikkulainen, Eliana Feasley, Leif Johnson, Igor Karpov, Padmini Rajagopalan, Aditya Rawal, and Wesley Tansey
Assisting Machine Learning Through Shaping, Advice and Examples 2011
Igor Karpov, Vinod Valsalam and Risto Miikkulainen
Human-Assisted Neuroevolution Through Shaping, Advice and Examples 2011
Igor V. Karpov, Vinod K. Valsalam and Risto Miikkulainen
UT^2: Human-like Behavior via Neuroevolution of Combat Behavior and Replay of Human Traces 2011
Jacob Schrum, Igor V. Karpov and Risto Miikkulainen
Coevolving Strategies for General Game Playing 2007
Joseph Reisinger, Erkin Bahceci, Igor Karpov and Risto Miikkulainen
Computational Intelligence in Games 2006
Risto Miikkulainen, Bobby D. Bryant, Ryan Cornelius, Igor V. Karpov, Kenneth O. Stanley, and Chern Han Yong
Incorporating Advice into Neuroevolution of Adaptive Agents 2006
Chern Han Yong, Kenneth O. Stanley, Risto Miikkulainen, and Igor V. Karpov
Integration and Evaluation of Exploration-Based Learning in Games 2006
Igor V. Karpov, Thomas D'Silva, Craig Varrichio, Kenneth O. Stanley, Risto Miikkulainen
Real-Time Evolution of Neural Networks in the NERO Video Game 2006
Kenneth O. Stanley, Bobby D. Bryant, Igor Karpov, Risto Miikkulainen
Projects
The OpenNERO AI Research and Education Platform 2009 - Present
Constructing Intelligent Agents in Simulated Worlds 2008 - 2010
Leveraging Human Creativity with Machine Discovery 2008 - 2010
Human-like Bots in Unreal Tournament 2008 - 2012
Neuroevolution in Real Time Games 2005 - Present
NERO: NeuroEvolving Robotic Operatives 2003 - 2009
NEAT: Evolving Increasingly Complex Neural Network Topologies 2000 - 2011
Areas of Interest
Reinforcement Learning Neuroevolution Cognitive Science Other Areas Game Playing Evolutionary Computation
Software/Data
UT^2: Winning Botprize 2012 Entry The Botprize Competition is an annual competition to program bots that appear human-l... 2012
NEAT C++ The NEAT package contains source code implementing the NeuroEvolution of Augmenting Topologies method. The source code i... 2010
OpenNERO OpenNERO is a general research and education platform for artificial intelligence. The platform is based on a simulatio... 2010
rtNEAT C++ The rtNEAT package contains source code implementing the real-time NeuroEvolution of Augmenting Topologies method. In ad... 2006
Demos
UT^2: Winner of 2012 BotPrize in Unreal Tournament 2004Jacob Schrum, Igor Karpov2012
Neuro-Evolving Robotic Operatives (NERO)Kenneth Stanley2007
Labs
Neural Networks