Özgür Şimşek

Professor of Artificial Intelligence, University of Bath, UK

Professor of Artificial Intelligence, Deputy Head of Department, Department of Computer Science

 

Vita

Özgür Simsek is a Professor of Artificial Intelligence and Deputy Head of the Department of Computer Science at the University of Bath. Her research is on solving complex problems through autonomous search, learning, and development, spanning a number of different fields, including artificial intelligence, machine learning, network science, and decision heuristics. She is particularly interested in achieving open-ended developmental learning in large, complex environments.

 

Department of Computer Science

UKRI CDT in Accountable, Responsible and Transparent AI

Centre for Autonomous Robotics (CENTAUR)

Centre for Mathematics and Algorithms for Data (MAD)

Artificial Intelligence

EPSRC Centre for Doctoral Training in Statistical Applied Mathematics (SAMBa)

Max Planck Institute for Human Development, Berlin

https://orcid.org/0000-0001-5449-0437

 

  • Since 2022: Professor, Department of Computer Science, University of Bath, Bath, United Kingdom
  • 2017 – 2022: Senior Lecturer, Department of Computer Science, University of Bath, Bath, United Kingdom
  • 2018 – Present: Deputy Director, Institute for Mathematical Innovation, University of Bath, Bath, United Kingdom
  • 2011 - 2017: Research Scientist, Center for Adaptive Behavior and Cognition, Max Planck Institute for Human Development, Berlin, Germany
  • 2008 - 2011: Postdoctoral research fellow, Center for Adaptive Behavior and Cognition, Max Planck Institute for Human Development, Berlin, Germany
  • 2008: PhD in Computer Science, University of Massachusetts, Amherst, Massachusetts
  • 2004: MSc in Computer Science, University of Massachusetts, Amherst, Massachusetts
  • 1997-2000: Research Scientist, Human Factors Transportation Research Center, Battelle Memorial Institute, Seattle, Washington
  • 1997: MSc in Industrial Engineering and Operations Research, University of Massachusetts, Amherst, USA
  • 1995: BSc in Industrial Engineering, Boğaziçi Universitesi, Istanbul, Turkey

 

Selected publications

Lichtenberg, J. M. , & Şimşek, Ö. (2019). Regularization in directable environments with application to Tetris. In Proceedings of the Thirty-Sixth International Conference on Machine Learning (ICML).

Şimşek, Ö., Algorta, S., & Kothiyal, A. (2016). Why Most Decisions Are Easy in Tetris—And Perhaps in Other Sequential Decision Problems, As Well. In Proceedings of the Thirty-Third International Conference on Machine Learning (ICML).

Şimşek, Ö., & Buckmann, M. (2015). Learning from small samples: An analysis of simple decision heuristics. In Advances in Neural Information Processing Systems (NIPS) 28.

Şimşek, Ö. (2013). Linear decision rule as aspiration for simple decision heuristics. In Advances in Neural Information Processing Systems (NIPS) 26.

Şimşek, Ö., & Jensen, D. (2008). Navigating networks by using homophily and degree. Proceedings of the National Academy of Sciences (PNAS), 105(35), pp. 12758–12762.

Şimşek, Ö., & Barto, A. G. (2008). Skill characterization based on betweenness. In Advances in Neural Information Processing Systems (NIPS) 21.

Şimşek, Ö., & Barto, A. G. (2006). An intrinsic reward mechanism for efficient exploration. In Proceedings of the Twenty-Third International Conference on Machine Learning (ICML).

Şimşek, Ö., Wolfe, A. P., & Barto, A. G. (2005) Identifying useful subgoals in reinforcement learning by local graph partitioning. In Proceedings of the Twenty-Second International Conference on Machine Learning (ICML).

Neville, J., Şimşek, Ö., Jensen, D., Komoroske, J., Palmer, K., & Goldberg, H. (2005). Using relational knowledge discovery to prevent securities fraud. In Proceedings of the Eleventh International Conference on Knowledge Discovery and Data Mining (KDD).

Katsikopoulos, K. V., & Şimşek, Ö. (2005). Optimal doubling strategy against a suboptimal opponent. Journal of Applied Probability, 42, 867–872.

Şimşek, Ö., & Barto, A. G. (2004). Using relative novelty to identify useful temporal abstractions in reinforcement learning. In Proceedings of the Twenty-First International Conference on Machine Learning (ICML). ACM, New York, NY, USA.