Marek Petrik - RankMe

108 papers A* 30A 13Misc 3Journal 55Unranked 6

Year	Rank	Type	Title / Venue / Authors
2026	A*	`conf`	Convergence of Fast Policy Iteration in Markov Games and Robust MDPs. AAAI Keith Badger, Jefferson Huang, Marek Petrik
2026	J	`jnl`	Dynamic Programming for Epistemic Uncertainty in Markov Decision Processes. CoRR Axel Benyamine, Julien Grand-Clément, Marek Petrik, Michael I. Jordan, Alain Durmus
2026	J	`jnl`	Efficient Algorithms for Robust Markov Decision Processes with CoRR Chin Pang Ho, Marek Petrik, Wolfram Wiesemann
2025	J	`jnl`	Convergence of Fast Policy Iteration in Markov Games and Robust MDPs. CoRR Keith Badger, Marek Petrik, Jefferson Huang
2025	J	`jnl`	On the Convex Formulations of Robust Markov Decision Processes. Math. Oper. Res. Julien Grand-Clément, Marek Petrik
2025	J	`jnl`	Probabilistic Safety Guarantee for Stochastic Control Systems Using Average Reward MDPs. CoRR Saber Omidi, Marek Petrik, Se Young Yoon, Momotaz Begum
2025	A*	`conf`	Provable Policy Gradient for Robust Average-Reward MDPs Beyond Rectangularity. ICML Qiuhao Wang, Yuqi Zha, Chin Pang Ho, Marek Petrik
2025	A	`conf`	Q-learning for Quantile MDPs: A Decomposition, Performance, and Convergence Analysis. AISTATS Jia Lin Hau, Erick Delage, Esther Derman, Mohammad Ghavamzadeh, Marek Petrik
2025	J	`jnl`	Risk-Averse Total-Reward Reinforcement Learning. CoRR Xihong Su, Jia Lin Hau, Gersi Doko, Kishan Panaganti, Marek Petrik
2025	A*	`conf`	Risk-averse Total-reward MDPs with ERM and EVaR. AAAI Xihong Su, Marek Petrik, Julien Grand-Clément
2024	A*	`conf`	Bayesian Regret Minimization in Offline Bandits. ICML Marek Petrik, Guy Tennenholtz, Mohammad Ghavamzadeh
2024	J	`jnl`	Data Poisoning Attacks on Off-Policy Policy Evaluation Methods. CoRR Elita A. Lobo, Harvineet Singh, Marek Petrik, Cynthia Rudin, Himabindu Lakkaraju
2024	J	`jnl`	Non-adaptive Online Finetuning for Offline Reinforcement Learning. RLJ Audrey Huang, Mohammad Ghavamzadeh, Nan Jiang, Marek Petrik
2024	J	`jnl`	Percentile Criterion Optimization in Offline Reinforcement Learning. CoRR Elita A. Lobo, Cyrus Cousins, Yair Zick, Marek Petrik
2024	J	`jnl`	Policy Gradient for Robust Markov Decision Processes. CoRR Qiuhao Wang, Shaohang Xu, Chin Pang Ho, Marek Petrik
2024	J	`jnl`	Q-learning for Quantile MDPs: A Decomposition, Performance, and Convergence Analysis. CoRR Jia Lin Hau, Erick Delage, Esther Derman, Mohammad Ghavamzadeh, Marek Petrik
2024	J	`jnl`	ROIL: Robust Offline Imitation Learning without Trajectories. RLJ Gersi Doko, Guang Yang, Daniel S. Brown, Marek Petrik
2024	J	`jnl`	Solving Multi-Model MDPs by Coordinate Ascent and Dynamic Programming. CoRR Xihong Su, Marek Petrik
2024	J	`jnl`	Stationary Policies are Optimal in Risk-averse Total-reward MDPs with EVaR. CoRR Xihong Su, Marek Petrik, Julien Grand-Clément
2023	J	`jnl`	A Convex Relaxation Approach to Bayesian Regret Minimization in Offline Bandits. CoRR Mohammad Ghavamzadeh, Marek Petrik, Guy Tennenholtz
2023	J	`jnl`	Beyond discounted returns: Robust Markov decision processes with average and Blackwell optimality. CoRR Julien Grand-Clément, Marek Petrik, Nicolas Vieille
2023	A	`conf`	Entropic Risk Optimization in Discounted MDPs. AISTATS Jia Lin Hau, Marek Petrik, Mohammad Ghavamzadeh
2023	J	`jnl`	On Dynamic Program Decompositions of Static Risk Measures. CoRR Jia Lin Hau, Erick Delage, Mohammad Ghavamzadeh, Marek Petrik
2023	A*	`conf`	On Dynamic Programming Decompositions of Static Risk Measures in Markov Decision Processes. NeurIPS Jia Lin Hau, Erick Delage, Mohammad Ghavamzadeh, Marek Petrik
2023	A*	`conf`	Percentile Criterion Optimization in Offline Reinforcement Learning. NeurIPS Cyrus Cousins, Elita A. Lobo, Marek Petrik, Yair Zick
2023	A*	`conf`	Policy Gradient in Robust MDPs with Global Convergence Guarantee. ICML Qiuhao Wang, Chin Pang Ho, Marek Petrik
2023	A*	`conf`	Reducing Blackwell and Average Optimality to Discounted MDPs via the Blackwell Discount Factor. NeurIPS Julien Grand-Clément, Marek Petrik
2023	J	`jnl`	Reducing Blackwell and Average Optimality to Discounted MDPs via the Blackwell Discount Factor. CoRR Julien Grand-Clément, Marek Petrik
2023	A	`conf`	Solving multi-model MDPs by coordinate ascent and dynamic programming. UAI Xihong Su, Marek Petrik
2022	A	`conf`	Data poisoning attacks on off-policy policy evaluation methods. UAI Elita A. Lobo, Harvineet Singh, Marek Petrik, Cynthia Rudin, Himabindu Lakkaraju
2022	J	`jnl`	On the Convergence of Policy Gradient in Robust MDPs. CoRR Qiuhao Wang, Chin Pang Ho, Marek Petrik
2022	J	`jnl`	On the convex formulations of robust Markov decision processes. CoRR Julien Grand-Clément, Marek Petrik
2022	J	`jnl`	RASR: Risk-Averse Soft-Robust MDPs with EVaR and Entropic Risk. CoRR Jia Lin Hau, Marek Petrik, Mohammad Ghavamzadeh, Reazul Hasan Russel
2022	A*	`conf`	Robust $\phi$-Divergence MDPs. NeurIPS Chin Pang Ho, Marek Petrik, Wolfram Wiesemann
2022	J	`jnl`	Robust Phi-Divergence MDPs. CoRR Chin Pang Ho, Marek Petrik, Wolfram Wiesemann
2021	A*	`conf`	Fast Algorithms for $L_\infty$-constrained S-rectangular Robust MDPs. NeurIPS Bahram Behzadian, Marek Petrik, Chin Pang Ho
2021	A	`conf`	Optimizing Percentile Criterion using Robust MDPs. AISTATS Bahram Behzadian, Reazul Hasan Russel, Marek Petrik, Chin Pang Ho
2021	J	`jnl`	Partial Policy Iteration for L1-Robust Markov Decision Processes. J. Mach. Learn. Res. Chin Pang Ho, Marek Petrik, Wolfram Wiesemann
2021	A*	`conf`	Policy Gradient Bayesian Robust Optimization for Imitation Learning. ICML Zaynah Javed, Daniel S. Brown, Satvik Sharma, Jerry Zhu, Ashwin Balakrishna, Marek Petrik, Anca D. Dragan, Ken Goldberg
2021	J	`jnl`	Policy Gradient Bayesian Robust Optimization for Imitation Learning. CoRR Zaynah Javed, Daniel S. Brown, Satvik Sharma, Jerry Zhu, Ashwin Balakrishna, Marek Petrik, Anca D. Dragan, Ken Goldberg
2021	A	`conf`	Robust Behavior Cloning with Adversarial Demonstration Detection. IROS Mostafa Hussein, Brendan Crowe, Madison Clark-Turner, Paul Gesel, Marek Petrik, Momotaz Begum
2021	J	`jnl`	Robust Maximum Entropy Behavior Cloning. CoRR Mostafa Hussein, Brendan Crowe, Marek Petrik, Momotaz Begum
2020	A*	`conf`	Bayesian Robust Optimization for Imitation Learning. NeurIPS Daniel S. Brown, Scott Niekum, Marek Petrik
2020	J	`jnl`	Bayesian Robust Optimization for Imitation Learning. CoRR Daniel S. Brown, Scott Niekum, Marek Petrik
2020	A*	`conf`	Beliefs We Can Believe in: Replacing Assumptions with Data in Real-Time Search. AAAI Maximilian Fickert, Tianyi Gu, Leonhard Staut, Wheeler Ruml, Jörg Hoffmann, Marek Petrik
2020	J	`jnl`	Entropic Risk Constrained Soft-Robust Policy Optimization. CoRR Reazul Hasan Russel, Bahram Behzadian, Marek Petrik
2020	J	`jnl`	Finite-Sample Analysis of GTD Algorithms. CoRR Bo Liu, Ji Liu, Mohammad Ghavamzadeh, Sridhar Mahadevan, Marek Petrik
2020	J	`jnl`	Partial Policy Iteration for L1-Robust Markov Decision Processes. CoRR Chin Pang Ho, Marek Petrik, Wolfram Wiesemann
2020	J	`jnl`	Proximal Gradient Temporal Difference Learning: Stable Reinforcement Learning with Polynomial Sample Complexity. CoRR Bo Liu, Ian Gemp, Mohammad Ghavamzadeh, Ji Liu, Sridhar Mahadevan, Marek Petrik
2020	J	`jnl`	Soft-Robust Algorithms for Handling Model Misspecification. CoRR Elita A. Lobo, Mohammad Ghavamzadeh, Marek Petrik
2019	A*	`conf`	Beyond Confidence Regions: Tight Bayesian Ambiguity Sets for Robust MDPs. NeurIPS Marek Petrik, Reazul Hasan Russel
2019	J	`jnl`	Beyond Confidence Regions: Tight Bayesian Ambiguity Sets for Robust MDPs. CoRR Marek Petrik, Reazul Hasan Russel
2019	A*	`conf`	Fast Feature Selection for Linear Value Function Approximation. ICAPS Bahram Behzadian, Soheil Gharatappeh, Marek Petrik
2019	J	`jnl`	High-Confidence Policy Optimization: Reshaping Ambiguity Sets in Robust MDPs. CoRR Bahram Behzadian, Reazul Hasan Russel, Marek Petrik
2019	A*	`conf`	Inverse Reinforcement Learning of Interaction Dynamics from Demonstrations. ICRA Mostafa Hussein, Momotaz Begum, Marek Petrik
2019	J	`jnl`	Optimizing Norm-Bounded Weighted Ambiguity Sets for Robust MDPs. CoRR Reazul Hasan Russel, Bahram Behzadian, Marek Petrik
2019	A*	`conf`	Real-Time Planning as Decision-Making under Uncertainty. AAAI Andrew Mitchell, Wheeler Ruml, Fabian Spaniol, Jörg Hoffmann, Marek Petrik
2019	J	`jnl`	Robust Exploration with Tight Bayesian Plausibility Sets. CoRR Reazul Hasan Russel, Tianyi Gu, Marek Petrik
2018	A*	`conf`	Fast Bellman Updates for Robust MDPs. ICML Chin Pang Ho, Marek Petrik, Wolfram Wiesemann
2018	J	`jnl`	Interpretable Reinforcement Learning with Ensemble Methods. CoRR Alexander Brown, Marek Petrik
2018	Misc	`conf`	Low-rank Feature Selection for Reinforcement Learning. ISAIM Bahram Behzadian, Marek Petrik
2018	A*	`conf`	Policy-Conditioned Uncertainty Sets for Robust Markov Decision Processes. NeurIPS Andrea Tirinzoni, Marek Petrik, Xiangli Chen, Brian D. Ziebart
2018	J	`jnl`	Proximal Gradient Temporal Difference Learning: Stable Reinforcement Learning with Polynomial Sample Complexity. J. Artif. Intell. Res. Bo Liu, Ian Gemp, Mohammad Ghavamzadeh, Ji Liu, Sridhar Mahadevan, Marek Petrik
2018	J	`jnl`	Tight Bayesian Ambiguity Sets for Robust MDPs. CoRR Reazul Hasan Russel, Marek Petrik
2017	A	`conf`	A Practical Method for Solving Contextual Bandit Problems Using Decision Trees. UAI Adam N. Elmachtoub, Ryan McNellis, Sechan Oh, Marek Petrik
2017	J	`jnl`	A Practical Method for Solving Contextual Bandit Problems Using Decision Trees. CoRR Adam N. Elmachtoub, Ryan McNellis, Sechan Oh, Marek Petrik
2017	A*	`conf`	Robust Partially-Compressed Least-Squares. AAAI Stephen Becker, Ban Kawas, Marek Petrik
2017	A	`conf`	Value Directed Exploration in Multi-Armed Bandits with Structured Priors. UAI Bence Cserna, Marek Petrik, Reazul Hasan Russel, Wheeler Ruml
2017	J	`jnl`	Value Directed Exploration in Multi-Armed Bandits with Structured Priors. CoRR Bence Cserna, Marek Petrik, Reazul Hasan Russel, Wheeler Ruml
2016	J	`jnl`	Building an Interpretable Recommender via Loss-Preserving Transformation. CoRR Amit Dhurandhar, Sechan Oh, Marek Petrik
2016	A	`conf`	Interpretable Policies for Dynamic Product Recommendations. UAI Marek Petrik, Ronny Luss
2016	A*	`conf`	Proximal Gradient Temporal Difference Learning Algorithms. IJCAI Bo Liu, Ji Liu, Mohammad Ghavamzadeh, Sridhar Mahadevan, Marek Petrik
2016	—	`conf`	Safe Policy Improvement by Minimizing Robust Baseline Regret. NIPS Mohammad Ghavamzadeh, Marek Petrik, Yinlam Chow
2015	A	`conf`	Finite-Sample Analysis of Proximal Gradient TD Algorithms. UAI Bo Liu, Ji Liu, Mohammad Ghavamzadeh, Sridhar Mahadevan, Marek Petrik
2015	A	`conf`	Optimal Threshold Control for Energy Arbitrage with Degradable Battery Storage. UAI Marek Petrik, Xiaojian Wu
2015	J	`jnl`	Robust Partially-Compressed Least-Squares. CoRR Stephen Becker, Ban Kawas, Marek Petrik, Karthikeyan Natesan Ramamurthy
2015	J	`jnl`	Tight Approximations of Dynamic Risk Measures. Math. Oper. Res. Dan Andrei Iancu, Marek Petrik, Dharmashankar Subramanian
2014	J	`jnl`	A Bilinear Programming Approach for Multiagent Planning. CoRR Marek Petrik, Shlomo Zilberstein
2014	J	`jnl`	Efficient and accurate methods for updating generalized linear models with multiple feature additions. J. Mach. Learn. Res. Amit Dhurandhar, Marek Petrik
2014	—	`conf`	RAAM: The Benefits of Robustness in Approximating Aggregated MDPs in Reinforcement Learning. NIPS Marek Petrik, Dharmashankar Subramanian
2014	J	`jnl`	Social media and customer behavior analytics for personalized customer engagements. IBM J. Res. Dev. Stephen J. Buckley, Markus Ettl, Prateek Jain, Ronny Luss, Marek Petrik, Rajesh Kumar Ravi, Chitra Venkatramani
2013	Misc	`conf`	Agile logistics simulation and optimization for managing disaster responses. WSC Francisco Barahona, Markus Ettl, Marek Petrik, Peter M. Rimshnick
2013	A	`conf`	Solution Methods for Constrained Markov Decision Process with Continuous Probability Modulation. UAI Marek Petrik, Dharmashankar Subramanian, Janusz Marecki
2013	J	`jnl`	Solution Methods for Constrained Markov Decision Process with Continuous Probability Modulation. CoRR Marek Petrik, Dharmashankar Subramanian, Janusz Marecki
2012	J	`jnl`	An Approximate Solution Method for Large Risk-Averse Markov Decision Processes CoRR Marek Petrik, Dharmashankar Subramanian
2012	A	`conf`	An Approximate Solution Method for Large Risk-Averse Markov Decision Processes. UAI Marek Petrik, Dharmashankar Subramanian
2012	J	`jnl`	Approximate Dynamic Programming By Minimizing Distributionally Robust Bounds CoRR Marek Petrik
2012	A*	`conf`	Approximate Dynamic Programming By Minimizing Distributionally Robust Bounds. ICML Marek Petrik
2012	—	`ch.`	Learning Feature-Based Heuristic Functions. Autonomous Search Marek Petrik, Shlomo Zilberstein
2011	A*	`conf`	Linear Dynamic Programs for Resource Management. AAAI Marek Petrik, Shlomo Zilberstein
2011	J	`jnl`	Robust Approximate Bilinear Programming for Value Function Approximation. J. Mach. Learn. Res. Marek Petrik, Shlomo Zilberstein
2010	J	`jnl`	Feature Selection Using Regularization in Approximate Linear Programs for Markov Decision Processes CoRR Marek Petrik, Gavin Taylor, Ronald Parr, Shlomo Zilberstein
2010	A*	`conf`	Feature Selection Using Regularization in Approximate Linear Programs for Markov Decision Processes. ICML Marek Petrik, Gavin Taylor, Ronald Parr, Shlomo Zilberstein
2010	J	`jnl`	Global Optimization for Value Function Approximation CoRR Marek Petrik, Shlomo Zilberstein
2009	J	`jnl`	A Bilinear Programming Approach for Multiagent Planning. J. Artif. Intell. Res. Marek Petrik, Shlomo Zilberstein
2009	A*	`conf`	Constraint relaxation in approximate linear programs. ICML Marek Petrik, Shlomo Zilberstein
2009	—	`conf`	Hybrid Least-Squares Algorithms for Approximate Policy Evaluation. ECML/PKDD (1) Jeffrey Johns, Marek Petrik, Sridhar Mahadevan
2009	J	`jnl`	Hybrid least-squares algorithms for approximate policy evaluation. Mach. Learn. Jeffrey Johns, Marek Petrik, Sridhar Mahadevan
2009	—	`conf`	Robust Value Function Approximation Using Bilinear Programming. NIPS Marek Petrik, Shlomo Zilberstein
2008	Misc	`conf`	A Successive Approximation Algorithm for Coordination Problems. ISAIM Marek Petrik, Shlomo Zilberstein
2008	—	`conf`	Biasing Approximate Dynamic Programming with a Lower Discount Factor. NIPS Marek Petrik, Bruno Scherrer
2008	A*	`conf`	Interaction Structure and Dimensionality Reduction in Decentralized MDPs. AAAI Martin Allen, Marek Petrik, Shlomo Zilberstein
2008	A*	`conf`	Learning Heuristic Functions through Approximate Linear Programming. ICAPS Marek Petrik, Shlomo Zilberstein
2007	A*	`conf`	An Analysis of Laplacian Methods for Value Function Approximation in MDPs. IJCAI Marek Petrik
2007	A*	`conf`	Anytime Coordination Using Separable Bilinear Programs. AAAI Marek Petrik, Shlomo Zilberstein
2007	A*	`conf`	Average-Reward Decentralized Markov Decision Processes. IJCAI Marek Petrik, Shlomo Zilberstein
2006	—	`conf`	Learning Static Parallel Portfolios of Algorithms. AI&M Marek Petrik, Shlomo Zilberstein
2006	J	`jnl`	Learning parallel portfolios of algorithms. Ann. Math. Artif. Intell. Marek Petrik, Shlomo Zilberstein