Özgür Şimşek
Postdoctoral Research Fellow
Center for Adaptive Behavior and Cognition
Max Planck Institute for Human Development
ozgur [at] mpib-berlin [dot] mpg [dot] de
PUBLICATIONS [chronological]
Refereed Journals
Özgür Şimşek and David Jensen Navigating networks by using homophily and degree Proceedings of the National Academy of Sciences, 105(35), 12758–12762, 2008 [pdf] [bibtex]
Konstantinos V. Katsikopoulos and Özgür Şimşek Optimal doubling strategy against a sub-optimal opponent Journal of Applied Probability 42(3), pp. 867–872, 2005 [pdf] [abstract]
Alvah C. Bittner, Jr., Özgür Şimşek, William H. Levison, John L. Campbell On-road vs. simulator data in driver model development: Driver Performance Model experience Transportation Research Record 1803, pp. 38–44, 2002 [abstract]
William H. Levison, Özgür Şimşek, Alvah C. Bittner, Jr., S. J. Hunn Computational techniques used in the Driver Performance Model of the Interactive Highway Safety Design Model Transportation Research Record 1779, pp. 17–25, 2001 [abstract]
Refereed Conferences
Özgür Şimşek and Andrew G. Barto Skill characterization based on betweenness Advances in Neural Information Processing Systems (NIPS) 22, 2009 [pdf] [bibtex]
Özgür Şimşek and Andrew G. Barto An intrinsic reward mechanism for efficient exploration 23rd International Conference on Machine Learning (ICML), 2006 [pdf] [bibtex] [abstract]
Özgür Şimşek and David Jensen Decentralized search in networks using homophily and degree disparity 19th International Joint Conference on Artificial Intelligence (IJCAI), 2005 [pdf] [bibtex] [abstract]
Özgür Şimşek, Alicia P. Wolfe, Andrew G. Barto Identifying useful subgoals in reinforcement learning by local graph partitioning 22nd International Conference on Machine Learning (ICML), 2005 [pdf] [bibtex] [abstract]
Jennifer Neville, Özgür Şimşek, David Jensen, John Komoroske, Kelly Palmer, Henry Goldberg Using relational knowledge discovery to prevent securities fraud 11th International Conference on Knowledge Discovery and Data Mining (KDD), 2005 [pdf] [bibtex] [abstract]
Özgür Şimşek and Andrew G. Barto Using relative novelty to identify useful temporal abstractions in reinforcement learning 21st International Conference on Machine Learning (ICML), 2004 [ps] [pdf] [bibtex] [abstract]
Alvah C. Bittner, Jr. and Özgür Şimşek Simulator validation: Methods and illustrations International Symposium on Automotive Technology and Automation (ISATA)—Simulation and Virtual Reality, 2000, pp.63-69. Epson, UK: Epson House
Refereed Workshops
Andrew G. Barto and Özgür Şimşek Intrinsic motivation for reinforcement learning systems 13th Yale Workshop on Adaptive and Learning Systems, 2005 [pdf] [bibtex] [abstract]
Özgür Şimşek, Alicia P. Wolfe, Andrew G. Barto Local graph partitioning as a basis for generating temporally-extended actions in reinforcement learning AAAI Workshop on Learning and Planning in Markov Processes—Advances and Challenges, 2004. [ps] [pdf] [bibtex] [abstract]
Jennifer Neville, Özgür Şimşek, David Jensen Autocorrelation and relational learning: Challenges and opportunities ICML Workshop on Statistical Relational Learning, 2004 [ps] [pdf] [bibtex] [abstract]
Book Chapters
Barry H. Kantowitz and Özgür Şimşek Secondary-task measures of driver workload In Peter A. Hancock and Paula A. Desmond (Eds.), Stress, workload, and fatigue, 2001, pp. 395–408. Mahwah, NJ: Lawrence Erlbaum Associates
Other
Özgür Şimşek Behavioral building blocks for autonomous agents: description, identification, and learning PhD thesis, University of Massachusetts Amherst, 2008. [pdf]
Özgür Şimşek and Andrew G. Barto Betweenness centrality as a basis for forming skills University of Massachusetts, Department of Computer Science, Technical Report TR-2007-26, 2007 [pdf]
Özgür Şimşek Towards competence in autonomous agents 20th National Conference on Artificial Intelligence (AAAI), 2005 (Doctoral Symposium)