Marek Petrik

Marek Petrik

I am an Assistant Professor in the Department of Computer Science at the University of New Hampshire. Before UNH, I was a Research Staff Member at the IBM’s T. J. Watson Research Center in Yorktown, NY. I received my Ph.D. from University of Massachusetts Amherst in 2010. My advisor was: Shlomo Zilberstein.

I am also a member of the artificial intelligence research group at UNH.

Research Interests

I am interested in robust data-driven decision making and in particular in reinforcement learning with limited data sets, risk aversion, and Bayesian models of uncertainty. My application areas include natural resource management, agriculture, and space physics. I had previously worked on applications in precision agriculture, natural resources, renewable energy management, supply chains, advertising, and others.

Selected Recent Publications

Partial Policy Iteration for L1-Robust Markov Decision Processes, Chin Pang Ho, Marek Petrik, Wolfram Wiesemann, Forthcoming in Journal of Machine Learning Research, 2021. Preprint

Optimizing Percentile Criterion using Robust MDPs, Bahram Behzadian, Reazul Hasan Russel, Marek Petrik, Chin Pang Ho, Artificial Intelligence and Statistics (AISTATS), 2021.

Bayesian Robust Optimization for Imitation Learning, Daniel S. Brown, Scott Niekum, Marek Petrik, Advances in Neural Information Processing Systems (NeurIPS), 2020. Arxiv

Beyond Confidence Regions: Tight Bayesian Ambiguity Sets for Robust MDPs, Reazul Hasan Russel, Marek Petrik, Advances in Neural Information Processing Systems (NeurIPS), 2019.

Fast Feature Selection for Linear Value Function Approximation, Bahram Behzadian, Soheil Gharatappeh, Marek Petrik, International Conference on Automated Planning and Scheduling (ICAPS) 2019.

Fast Bellman Updates for Robust MDPs, Chin Pang Ho, Marek Petrik, Wolfram Wiesemann, International Conference on Machine Learning (ICML), 2018. [Full Paper].

All Publications

Contact Information

If you would like to schedule a meeting with me, please see my calendar and change it to the weekly view to see my availability.