UTCS Artificial Intelligence
Matthew de Wet
Matt worked on neuroevolution in games, and completed an honors thesis on automatic techniques for avoiding premature convergence. He went on to work at Microsoft Game Studios.
Avoiding Premature Convergence in NeuroEvolution by Broadening the Evolutionary Search
Matthew de Wet, Technical Report HR-11-02, Department of Computer Science, The University of Texas at Austin.
Learning Strategic Behavior in Sequential Decision Tasks
2009 - 2014
Areas of Interest
Formerly affiliated with