Özgür Simsek

Assoziierte Wissenschaftlerin
+49 30 82406-688
ozgur [at] mpib-berlin [dot] mpg [dot] de

Akademischer Steckbrief: 

M.S. in Industrial engineering and Operations Research, 1997, Unviersity of Massachusetts Amherst
M.S. in Computer Science, 2004, University of Massachusetts, Amherst
Ph.D., Computer Science, 2008, University of Massachusetts Amherst

  • Maschinelles Lernen
  • Künstliche Intelligenz
  • Komplexe Netzwerke

Ausgewählte Literatur: 
  • Simsek, O. and Barto, A. (2009). Skill characterization based on betweenness. Proceedings of the Twenty-Second Annual Conference on Neural Information Processing Systems (NIPS).
  • Simsek, O. and Jensen D. (2008). Navigating networks by using homophily and degree. Proceedings of the National Academy of Sciences, 105(35), 12758-12762.
  • Simsek, O. and Barto, A. (2006). An intrinsic reward mechanism for efficient exploration. Proceedings of the Twenty-Third International Conference on Machine Learning (ICML).
  • Simsek, O., Wolfe, A.P., Barto, A. (2005) Identifying useful subgoals in reinforcement learning by local graph partitioning. Proceedings of the Twenty-Second International Conference on Machine Learning (ICML).
  • Neville, J., Simsek, O., Jensen D., John Komoroske, Palmer, K., Goldberg, H. (2005). Using relational knowledge discovery to prevent securities fraud. Proceedings of the Eleventh International Conference on Knowledge Discovery and Data Mining (KDD).
  • Simsek, O. and Barto, A. (2004). Using relative novelty to identify useful temporal abstractions in reinforcement learning. Proceedings of the Twenty-First International Conference on Machine Learning (ICML).