| An approximate solution method for large risk-averse Markov decision processes M Petrik, D Subramanian arXiv preprint arXiv:1210.4901, 2012 | 203 | 2012 |
| Finite-sample analysis of proximal gradient td algorithms B Liu, J Liu, M Ghavamzadeh, S Mahadevan, M Petrik arXiv preprint arXiv:2006.14364, 2020 | 187 | 2020 |
| Safe policy improvement by minimizing robust baseline regret M Ghavamzadeh, M Petrik, Y Chow Advances in Neural Information Processing Systems 29, 2016 | 182 | 2016 |
| An Analysis of Laplacian Methods for Value Function Approximation in MDPs. M Petrik IJCAI, 2574-2579, 2007 | 98 | 2007 |
| Feature selection using regularization in approximate linear programs for Markov decision processes M Petrik, G Taylor, R Parr, S Zilberstein arXiv preprint arXiv:1005.1860, 2010 | 94 | 2010 |
| Fast Bellman updates for robust MDPs CP Ho, M Petrik, W Wiesemann International Conference on Machine Learning, 1979-1988, 2018 | 87 | 2018 |
| Biasing approximate dynamic programming with a lower discount factor M Petrik, B Scherrer Advances in neural information processing systems 21, 2008 | 82 | 2008 |
| Beyond confidence regions: Tight bayesian ambiguity sets for robust mdps M Petrik, RH Russel Advances in neural information processing systems 32, 2019 | 80 | 2019 |
| Partial policy iteration for l1-robust markov decision processes CP Ho, M Petrik, W Wiesemann Journal of Machine Learning Research 22 (275), 1-46, 2021 | 79 | 2021 |
| A practical method for solving contextual bandit problems using decision trees AN Elmachtoub, R McNellis, S Oh, M Petrik arXiv preprint arXiv:1706.04687, 2017 | 74 | 2017 |
| Learning parallel portfolios of algorithms M Petrik, S Zilberstein Annals of Mathematics and Artificial Intelligence 48 (1), 85-106, 2006 | 63 | 2006 |
| Bayesian robust optimization for imitation learning D Brown, S Niekum, M Petrik Advances in Neural Information Processing Systems 33, 2479-2491, 2020 | 59 | 2020 |
| Tight approximations of dynamic risk measures DA Iancu, M Petrik, D Subramanian Mathematics of Operations Research 40 (3), 655-682, 2015 | 59 | 2015 |
| RAAM: The benefits of robustness in approximating aggregated MDPs in reinforcement learning M Petrik, D Subramanian Advances in Neural Information Processing Systems 27, 2014 | 48 | 2014 |
| Constraint relaxation in approximate linear programs M Petrik, S Zilberstein Proceedings of the 26th Annual International Conference on Machine Learning …, 2009 | 48 | 2009 |
| A bilinear programming approach for multiagent planning M Petrik, S Zilberstein Journal of Artificial Intelligence Research 35, 235-274, 2009 | 47 | 2009 |
| Average-Reward Decentralized Markov Decision Processes. M Petrik, S Zilberstein IJCAI, 1997-2002, 2007 | 40 | 2007 |
| Entropic risk optimization in discounted MDPs JL Hau, M Petrik, M Ghavamzadeh International Conference on Artificial Intelligence and Statistics, 47-76, 2023 | 39 | 2023 |
| Policy gradient in robust mdps with global convergence guarantee Q Wang, CP Ho, M Petrik International Conference on Machine Learning, 35763-35797, 2023 | 38 | 2023 |
| Fast Algorithms for -constrained S-rectangular Robust MDPs B Behzadian, M Petrik, CP Ho Advances in Neural Information Processing Systems 34, 25982-25992, 2021 | 38 | 2021 |
Mohammad GhavamzadehQualcomm AI ResearchVerified email at qti.qualcomm.com
