Erkin Bahceci
Ph.D. Student
Erkin's work focuses on understanding how multiple agents search for the same peaks on a common fitness landscape, or Competitive MultiAgent Search (CMAS). This problem is motivated by innovation search in the real world, i.e. how high-tech companies search for new products. Erkin simulates these processes in NK landscapes, uses evolutionary computation to discover optimal strategies, and verifies the discoveries using human subject data. He is currently trying to finish up his dissertation writing while working full-time at Google, Inc.
Competitive Multi-Agent Search 2014
Erkin Bahceci, PhD Thesis, Department of Computer Science, The University of Texas at Austin.
Transfer of Evolved Pattern-Based Heuristics in Games 2008
Erkin Bahceci and Risto Miikkulainen, In IEEE Symposium On Computational Intelligence and Games (CIG 2008), pp. 220-227, Perth, Australia, December 2008.
Coevolving Strategies for General Game Playing 2007
Joseph Reisinger, Erkin Bahceci, Igor Karpov and Risto Miikkulainen, In Proceedings of the {IEEE} Symposium on Computational Intelligence and Games, pp. 320-327, Piscataway, NJ 2007. IEEE.
NKVis This package contains a 3D visualization tool for NK fitness landscapes. Two types of visualizations are provided: a 2011

NEAT C++ The NEAT package contains source code implementing the NeuroEvolution of Augmenting Topologies method. The source code i... 2010

rtNEAT C++ The rtNEAT package contains source code implementing the real-time NeuroEvolution of Augmenting Topologies method. In ad... 2006

Currently affiliated with Neural Networks