neural networks research group
areas • people • projects • demos • publications • software/data •
Nate Kohl
Ph.D. Alumni
Nate's dissertation focused on methods for dealing with fractured problems in neuroevolution, i.e. those where small changes in the input may cause large required changes in the output. More broadly, Nate worked on complexification in evolution, and on machine learning in real-world tasks like automobile collision warning and robotic soccer.
Homepage:
http://natekohl.net/
Also show archived content
Projects
Learning Strategic Behavior in Sequential Decision Tasks 2009 - 2014
NEAT: Evolving Increasingly Complex Neural Network Topologies 2000 - 2011
Constructing Intelligent Agents in Simulated Worlds 2008 - 2010
Cooperative Coevolution of Multi-Agent Systems 2000 - 2007
NEAT: Evolving Vehicle Warning Systems 2004 - 2006
Demos
Learning in Fractured DomainsNate Kohl2009
Evolving Vehicle Warning SystemsNate Kohl2006
Publications
     [Expand to show all 17][Minimize]
An Integrated Neuroevolutionary Approach to Reactive Control and High-level Strategy Nate Kohl, Risto Miikkulainen IEEE Transactions on Evolutionary Computation, 2011. 2011
Evolving Neural Networks for Strategic Decision-Making Problems Nate Kohl and Risto Miikkulainen In Neural Networks, Special issue on Goal-Directed Neural Systems, 2009. 2009
Learning in Fractured Problems for Constructive Neural Network Algorithms Nate Kohl PhD Thesis, Department of Computer Sciences, University of Texas at Austin, Austin, TX, 2009. 2009
Evolving Neural Networks for Fractured Domains Nate Kohl and Risto Miikkulainen In Proceedings of the Genetic and Evolutionary Computation Conference, 1405-1412, July 2008. 2008
Autonomous Learning of Stable Quadruped Locomotion Manish Saggar and Thomas D'Silva and Nate Kohl and Peter Stone In Gerhard Lakemeyer and Elizabeth Sklar and Domenico Sorenti and Tomoichi Takahashi, editors, Ro... 2007
Evolving a Real-World Vehicle Warning System Nate Kohl, Kenneth Stanley, Risto Miikkulainen, Michael Samples, and Rini Sherony In Proceedings of the Genetic and Evolutionary Computation Conference, 2006. 2006
From Pixels to Multi-Robot Decision-Making: A Study in Uncertainty Peter Stone and Mohan Sridharan and Daniel Stronger and Gregory Kuhlmann and Nate Kohl and Peggy Fid... Robotics and Autonomous Systems, 54(11):933-43, November 2006. Special issue on Planning Unde... 2006
The UT Austin Villa 2006 RoboCup Four-Legged Team Peter Stone and Peggy Fidelman and Nate Kohl and Gregory Kuhlmann and Tekin Mericli and Mohan Sridha... Technical Report UT-AI-TR-06-337, The University of Texas at Austin, Department of Computer Sciences... 2006
Neuroevolution of an Automobile Crash Warning System Kenneth Stanley, Nate Kohl, Rini Sherony, and Risto Miikkulainen In Proceedings of the Genetic and Evolutionary Computation Conference, 2005. 2005
Evolving Keepaway Soccer Players through Task Decomposition Shimon Whiteson and Nate Kohl and Risto Miikkulainen and Peter Stone Machine Learning, 59(1):5-30, May 2005. 2005
Automatic Feature Selection via Neuroevolution Shimon Whiteson and Peter Stone and Kenneth O. Stanley and Risto Miikkulainen and Nate Kohl In Proceedings of the Genetic and Evolutionary Computation Conference, June 2005. 2005
The UT Austin Villa 2005 RoboCup Four-Legged Team Peter Stone and Kurt Dresner and Peggy Fidelman and Nate Kohl and Gregory Kuhlmann and Mohan Sridhar... Technical Report UT-AI-TR-05-325, The University of Texas at Austin, Department of Computer Sciences... 2005
Machine Learning for Fast Quadrupedal Locomotion Nate Kohl and Peter Stone In Nineteenth National Conference on Artificial Intelligence, 611-616, July 2004. 2004
Policy Gradient Reinforcement Learning for Fast Quadrupedal Locomotion Nate Kohl and Peter Stone In Proceedings of the {IEEE} International Conference on Robotics and Automation, 2619-2624,... 2004
The UT Austin Villa 2004 RoboCup Four-Legged Team: Coming of Age Peter Stone and Kurt Dresner and Peggy Fidelman and Nicholas K. Jong and Nate Kohl and Gregory Kuhlm... Technical Report UT-AI-TR-04-313, The University of Texas at Austin, Department of Computer Sciences... 2004
The UT Austin Villa 2003 Four-Legged Team Peter Stone and Kurt Dresner and Selim T. Erdougan and Peggy Fidelman and Nicholas K. Jong and Nate ... In Daniel Polani and Brett Browning and Andrea Bonarini and Kazuo Yoshida, editors, RoboCup-2003:... 2004
UT Austin Villa 2003: A New RoboCup Four-Legged Team Peter Stone and Kurt Dresner and Selim T. Erdougan and Peggy Fidelman and Nicholas K. Jong and Nate ... %RefShort% 2003
Areas of Interest
Evolutionary Computation Neuroevolution Reinforcement Learning Control Robotics Game Playing Applications
UT Only: Advice • Calendar • Admin