 |
| CV |
Marek Petrik
I graduated from University of Massachusetts Amherst with my advisor Shlomo Zilberstein.
My main interests are in approximate dynamic programming, machine learning, robust and risk-sensitive optimization, and mathematical optimization.
Contact Information
|
IBM T.J. Watson Research Center Yorktown Heights, NY 10598 Cell-phone: +1-413-230-7479 You can still email me at: petrik@cs.umass.edu |
|
Papers and Talks [bib]
| The Price of Dynamic Inconsistency for Distortion Risk Measures Pu Huang, Dan Iancu, Marek Petrik, Dharmashankar Subramanian. (to be) Submitted, 2011 [PDF] |
| Distributionally Robust Approach to Approximate Dynamic Programming Marek Petrik. Submitted, 2011. [PDF] |
| Linear Dynamic Programs for Resource Management Marek Petrik and Shlomo Zilberstein. Proceedings of Conference on Artificial Intelligence (AAAI) 2011 [Computational Sustainability Track]. [PDF] |
| Robust Approximate Bilinear Programming for Value Function Approximation Marek Petrik and Shlomo Zilberstein. Submitted to Journal of Machine Learning Research 2010/2011. [PDF] |
| Optimization-based Approximate Dynamic Programming Marek Petrik. Ph.D. Dissertation [Single Spaced] Double Spaced [Slides] |
| Feature Selection Using Regularization in Approximate Linear Program for Markov Decision Processes Marek Petrik, Gavin Taylor, Ron Parr, Shlomo Zilberstein. International Conference on Machine Learning (ICML) 27, 2010. [PDF] Technical Report (includes proofs and algorithms): arXiv 1005.1860 [PDF] |
| Robust Value Function Approximation Using Bilinear Programming Marek Petrik and Shlomo Zilberstein. Advances in Neural Information Processing Systems (NIPS) 22, 2009. [PDF] Technical Report (includes proofs) UM-CS-2009-052 [PDF] |
| A Bilinear Programming Approach for Multiagent Planning Marek Petrik and Shlomo Zilberstein. Journal of Artificial Intelligence Research 35:235-274, 2009. [PDF] |
| Hybrid Least-Squares Algorithms for Approximate Policy Evaluation Jeff Johns and Marek Petrik and Sridhar Mahadevan. European Conference on Machine Learning 2009, and Machine Learning. [Link] |
| Robust Approximate Optimization for Large Scale Planning Problems Marek Petrik. AAAI Doctoral Consortium 2009. [PDF] |
| Constraint Relaxation in Approximate Linear Programs
Marek Petrik and Shlomo Zilberstein. International Conference on Machine Learning (ICML) 2009. [PDF] |
| Blood Management Using Approximate Linear Programming
Marek Petrik and Shlomo Zilberstein. Presented at INFORMS Computing Society Meeting, Charleston, SC 2009. [PDF] |
| Biasing Approximate Dynamic Programming with a Lower Discount
Factor Marek Petrik and Bruno Scherrer. Twenty-Second Annual Conference on Neural Information Processing Systems (NIPS) 2008/2009. [PDF] |
| Learning Heuristic Functions Through Approximate Linear Programming
Marek Petrik and Shlomo Zilberstein. International Conference on Automated Planning and Scheduling (ICAPS) 2008. [PDF] |
| Interaction Structure and Dimensionality Reduction in Decentralized
MDPs Martin Allen and Marek Petrik and Shlomo Zilberstein. In the National Conference on Artificial Intelligence (AAAI), 2008. Short paper. [PDF] Tech report #UM-CS-2008-11 [PDF] |
| A Successive Approximation Algorithm for Coordination Problems
Marek Petrik and Shlomo Zilberstein. In the 9th International Symposium on Artificial Intelligence and Mathematics, Fort Lauderdale, Florida, January, 2008 [PDF] |
| Anytime Coordination Using Separable Bilinear Programs
Marek Petrik, Shlomo Zilberstein. In the National Conference on Artificial Intelligence (AAAI), 2007. (Corrected) [PDF] |
| An Analysis of Laplacian Methods for Value Function Approximation
in MDPs. Marek Petrik. In the International Joint Conference on Artificial Intelligence (IJCAI), 2007. (Corrected) [PDF] |
| Average-Reward Decentralized Markov Decision Processes.
Marek Petrik, Shlomo Zilberstein. In the International Joint Conference on Artificial Intelligence (IJCAI), 2007. [PDF] |
| Learning Parallel Portfolios of Algorithms Marek Petrik, Shlomo Zilberstein Annals of Mathematics and Artificial Intelligence, 48(1-2):85-106, 2006 (Preliminary) [PDF] |
| Learning Static Parallel Portfolios of Algorithms. Marek Petrik, Shlomo Zilberstein. In the 9th International Symposium on Artificial Intelligence and Mathematics, Fort Lauderdale, Florida, January 4-6, 2006. [PDF] |
| Learning Parallel Portfolios of Algorithms. Marek Petrik. Diploma (Master) Thesis at Comenius University. Defended on June 7th 2005. [PDF] [Code] [Slides] |
| Constrained Dynamic Programming for TSPTW. Marek Petrik. Whitestein Technologies Technical Report. [Email] |
| Statistically Optimal Combination of Algorithms.
Marek Petrik. In the local proceedings of Sofsem 2005. (Best Student Poster). [PDF] |