Marek Petrik

According to our database, Marek Petrik authored at least 80 papers between 2006 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Q-learning for Quantile MDPs: A Decomposition, Performance, and Convergence Analysis.

Jia Lin Hau, Erick Delage, Esther Derman, Mohammad Ghavamzadeh, Marek Petrik

CoRR, 2024

Policy Gradient for Robust Markov Decision Processes.

Qiuhao Wang, Shaohang Xu, Chin Pang Ho, Marek Petrik

CoRR, 2024

Stationary Policies are Optimal in Risk-averse Total-reward MDPs with EVaR.

Xihong Su, Marek Petrik, Julien Grand-Clément

CoRR, 2024

Non-adaptive Online Finetuning for Offline Reinforcement Learning.

Audrey Huang, Mohammad Ghavamzadeh, Nan Jiang, Marek Petrik

RLJ, 2024

ROIL: Robust Offline Imitation Learning without Trajectories.

Gersi Doko, Guang Yang, Daniel S. Brown, Marek Petrik

RLJ, 2024

Bayesian Regret Minimization in Offline Bandits.

Marek Petrik, Guy Tennenholtz, Mohammad Ghavamzadeh

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

Beyond discounted returns: Robust Markov decision processes with average and Blackwell optimality.

Julien Grand-Clément, Marek Petrik, Nicolas Vieille

CoRR, 2023

A Convex Relaxation Approach to Bayesian Regret Minimization in Offline Bandits.

Mohammad Ghavamzadeh, Marek Petrik, Guy Tennenholtz

CoRR, 2023

On Dynamic Program Decompositions of Static Risk Measures.

Jia Lin Hau, Erick Delage, Mohammad Ghavamzadeh, Marek Petrik

CoRR, 2023

Solving multi-model MDPs by coordinate ascent and dynamic programming.

Xihong Su, Marek Petrik

Proceedings of the Uncertainty in Artificial Intelligence, 2023

On Dynamic Programming Decompositions of Static Risk Measures in Markov Decision Processes.

Jia Lin Hau, Erick Delage, Mohammad Ghavamzadeh, Marek Petrik

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Reducing Blackwell and Average Optimality to Discounted MDPs via the Blackwell Discount Factor.

Julien Grand-Clément, Marek Petrik

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Percentile Criterion Optimization in Offline Reinforcement Learning.

Cyrus Cousins, Elita A. Lobo, Marek Petrik, Yair Zick

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Policy Gradient in Robust MDPs with Global Convergence Guarantee.

Qiuhao Wang, Chin Pang Ho, Marek Petrik

Proceedings of the International Conference on Machine Learning, 2023

Entropic Risk Optimization in Discounted MDPs.

Jia Lin Hau, Marek Petrik, Mohammad Ghavamzadeh

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022

On the Convergence of Policy Gradient in Robust MDPs.

Qiuhao Wang, Chin Pang Ho, Marek Petrik

CoRR, 2022

On the convex formulations of robust Markov decision processes.

Julien Grand-Clément, Marek Petrik

CoRR, 2022

RASR: Risk-Averse Soft-Robust MDPs with EVaR and Entropic Risk.

Jia Lin Hau, Marek Petrik, Mohammad Ghavamzadeh, Reazul Hasan Russel

CoRR, 2022

Data poisoning attacks on off-policy policy evaluation methods.

Elita A. Lobo, Harvineet Singh, Marek Petrik, Cynthia Rudin, Himabindu Lakkaraju

Proceedings of the Uncertainty in Artificial Intelligence, 2022

Robust $\phi$-Divergence MDPs.

Chin Pang Ho, Marek Petrik, Wolfram Wiesemann

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021

Partial Policy Iteration for L1-Robust Markov Decision Processes.

Chin Pang Ho, Marek Petrik, Wolfram Wiesemann

J. Mach. Learn. Res., 2021

Robust Maximum Entropy Behavior Cloning.

Mostafa Hussein, Brendan Crowe, Marek Petrik, Momotaz Begum

CoRR, 2021

Fast Algorithms for $L_\infty$-constrained S-rectangular Robust MDPs.

Bahram Behzadian, Marek Petrik, Chin Pang Ho

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Robust Behavior Cloning with Adversarial Demonstration Detection.

Mostafa Hussein, Brendan Crowe, Madison Clark-Turner, Paul Gesel, Marek Petrik, Momotaz Begum

Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2021

Policy Gradient Bayesian Robust Optimization for Imitation Learning.

Zaynah Javed, Daniel S. Brown, Satvik Sharma, Jerry Zhu, Ashwin Balakrishna, Marek Petrik, Anca D. Dragan, Ken Goldberg

Proceedings of the 38th International Conference on Machine Learning, 2021

Optimizing Percentile Criterion using Robust MDPs.

Bahram Behzadian, Reazul Hasan Russel, Marek Petrik, Chin Pang Ho

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020

Soft-Robust Algorithms for Handling Model Misspecification.

Elita A. Lobo, Mohammad Ghavamzadeh, Marek Petrik

CoRR, 2020

Finite-Sample Analysis of GTD Algorithms.

Bo Liu, Ji Liu, Mohammad Ghavamzadeh, Sridhar Mahadevan, Marek Petrik

CoRR, 2020

Entropic Risk Constrained Soft-Robust Policy Optimization.

Reazul Hasan Russel, Bahram Behzadian, Marek Petrik

CoRR, 2020

Bayesian Robust Optimization for Imitation Learning.

Daniel S. Brown, Scott Niekum, Marek Petrik

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Beliefs We Can Believe in: Replacing Assumptions with Data in Real-Time Search.

Maximilian Fickert, Tianyi Gu, Leonhard Staut, Wheeler Ruml, Jörg Hoffmann, Marek Petrik

Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

2019

Optimizing Norm-Bounded Weighted Ambiguity Sets for Robust MDPs.

Reazul Hasan Russel, Bahram Behzadian, Marek Petrik

CoRR, 2019

High-Confidence Policy Optimization: Reshaping Ambiguity Sets in Robust MDPs.

Bahram Behzadian, Reazul Hasan Russel, Marek Petrik

CoRR, 2019

Robust Exploration with Tight Bayesian Plausibility Sets.

Reazul Hasan Russel, Tianyi Gu, Marek Petrik

CoRR, 2019

Beyond Confidence Regions: Tight Bayesian Ambiguity Sets for Robust MDPs.

Marek Petrik, Reazul Hasan Russel

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Inverse Reinforcement Learning of Interaction Dynamics from Demonstrations.

Mostafa Hussein, Momotaz Begum, Marek Petrik

Proceedings of the International Conference on Robotics and Automation, 2019

Fast Feature Selection for Linear Value Function Approximation.

Bahram Behzadian, Soheil Gharatappeh, Marek Petrik

Proceedings of the Twenty-Ninth International Conference on Automated Planning and Scheduling, 2019

Real-Time Planning as Decision-Making under Uncertainty.

Andrew Mitchell, Wheeler Ruml, Fabian Spaniol, Jörg Hoffmann, Marek Petrik

Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, 2019

2018

Proximal Gradient Temporal Difference Learning: Stable Reinforcement Learning with Polynomial Sample Complexity.

Bo Liu, Ian Gemp, Mohammad Ghavamzadeh, Ji Liu, Sridhar Mahadevan, Marek Petrik

J. Artif. Intell. Res., 2018

Tight Bayesian Ambiguity Sets for Robust MDPs.

Reazul Hasan Russel, Marek Petrik

CoRR, 2018

Interpretable Reinforcement Learning with Ensemble Methods.

Alexander Brown, Marek Petrik

CoRR, 2018

Policy-Conditioned Uncertainty Sets for Robust Markov Decision Processes.

Andrea Tirinzoni, Marek Petrik, Xiangli Chen, Brian D. Ziebart

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Low-rank Feature Selection for Reinforcement Learning.

Bahram Behzadian, Marek Petrik

Proceedings of the International Symposium on Artificial Intelligence and Mathematics, 2018

Fast Bellman Updates for Robust MDPs.

Chin Pang Ho, Marek Petrik, Wolfram Wiesemann

Proceedings of the 35th International Conference on Machine Learning, 2018

2017

A Practical Method for Solving Contextual Bandit Problems Using Decision Trees.

Adam N. Elmachtoub, Ryan McNellis, Sechan Oh, Marek Petrik

Proceedings of the Thirty-Third Conference on Uncertainty in Artificial Intelligence, 2017

Value Directed Exploration in Multi-Armed Bandits with Structured Priors.

Bence Cserna, Marek Petrik, Reazul Hasan Russel, Wheeler Ruml

Proceedings of the Thirty-Third Conference on Uncertainty in Artificial Intelligence, 2017

Robust Partially-Compressed Least-Squares.

Stephen Becker, Ban Kawas, Marek Petrik

Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, 2017

2016

Building an Interpretable Recommender via Loss-Preserving Transformation.

Amit Dhurandhar, Sechan Oh, Marek Petrik

CoRR, 2016

Interpretable Policies for Dynamic Product Recommendations.

Marek Petrik, Ronny Luss

Proceedings of the Thirty-Second Conference on Uncertainty in Artificial Intelligence, 2016

Safe Policy Improvement by Minimizing Robust Baseline Regret.

Mohammad Ghavamzadeh, Marek Petrik, Yinlam Chow

Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Proximal Gradient Temporal Difference Learning Algorithms.

Bo Liu, Ji Liu, Mohammad Ghavamzadeh, Sridhar Mahadevan, Marek Petrik

Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, 2016

2015

Tight Approximations of Dynamic Risk Measures.

Dan Andrei Iancu, Marek Petrik, Dharmashankar Subramanian

Math. Oper. Res., 2015

Robust Partially-Compressed Least-Squares.

Stephen Becker, Ban Kawas, Marek Petrik, Karthikeyan Natesan Ramamurthy

CoRR, 2015

Optimal Threshold Control for Energy Arbitrage with Degradable Battery Storage.

Marek Petrik, Xiaojian Wu

Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence, 2015

Finite-Sample Analysis of Proximal Gradient TD Algorithms.

Bo Liu, Ji Liu, Mohammad Ghavamzadeh, Sridhar Mahadevan, Marek Petrik

Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence, 2015

2014

Efficient and accurate methods for updating generalized linear models with multiple feature additions.

Amit Dhurandhar, Marek Petrik

J. Mach. Learn. Res., 2014

Social media and customer behavior analytics for personalized customer engagements.

Stephen J. Buckley, Markus Ettl, Prateek Jain, Ronny Luss, Marek Petrik, Rajesh Kumar Ravi, Chitra Venkatramani

IBM J. Res. Dev., 2014

RAAM: The Benefits of Robustness in Approximating Aggregated MDPs in Reinforcement Learning.

Marek Petrik, Dharmashankar Subramanian

Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

2013

Agile logistics simulation and optimization for managing disaster responses.

Francisco Barahona, Markus Ettl, Marek Petrik, Peter M. Rimshnick

Proceedings of the Winter Simulations Conference: Simulation Making Decisions in a Complex World, 2013

Solution Methods for Constrained Markov Decision Process with Continuous Probability Modulation.

Marek Petrik, Dharmashankar Subramanian, Janusz Marecki

Proceedings of the Twenty-Ninth Conference on Uncertainty in Artificial Intelligence, 2013

2012

An Approximate Solution Method for Large Risk-Averse Markov Decision Processes.

Marek Petrik, Dharmashankar Subramanian

Proceedings of the Twenty-Eighth Conference on Uncertainty in Artificial Intelligence, 2012

Approximate Dynamic Programming By Minimizing Distributionally Robust Bounds.

Marek Petrik

Proceedings of the 29th International Conference on Machine Learning, 2012

Learning Feature-Based Heuristic Functions.

Marek Petrik, Shlomo Zilberstein

Proceedings of the Autonomous Search, 2012

2011

Robust Approximate Bilinear Programming for Value Function Approximation.

Marek Petrik, Shlomo Zilberstein

J. Mach. Learn. Res., 2011

Linear Dynamic Programs for Resource Management.

Marek Petrik, Shlomo Zilberstein

Proceedings of the Twenty-Fifth AAAI Conference on Artificial Intelligence, 2011

2010

Global Optimization for Value Function Approximation

Marek Petrik, Shlomo Zilberstein

CoRR, 2010

Feature Selection Using Regularization in Approximate Linear Programs for Markov Decision Processes.

Marek Petrik, Gavin Taylor, Ronald Parr, Shlomo Zilberstein

Proceedings of the 27th International Conference on Machine Learning (ICML-10), 2010

2009

Hybrid least-squares algorithms for approximate policy evaluation.

Jeffrey Johns, Marek Petrik, Sridhar Mahadevan

Mach. Learn., 2009

A Bilinear Programming Approach for Multiagent Planning.

Marek Petrik, Shlomo Zilberstein

J. Artif. Intell. Res., 2009

Robust Value Function Approximation Using Bilinear Programming.

Marek Petrik, Shlomo Zilberstein

Proceedings of the Advances in Neural Information Processing Systems 22: 23rd Annual Conference on Neural Information Processing Systems 2009. Proceedings of a meeting held 7-10 December 2009, 2009

Constraint relaxation in approximate linear programs.

Marek Petrik, Shlomo Zilberstein

Proceedings of the 26th Annual International Conference on Machine Learning, 2009

2008

Biasing Approximate Dynamic Programming with a Lower Discount Factor.

Marek Petrik, Bruno Scherrer

Proceedings of the Advances in Neural Information Processing Systems 21, 2008

A Successive Approximation Algorithm for Coordination Problems.

Marek Petrik, Shlomo Zilberstein

Proceedings of the International Symposium on Artificial Intelligence and Mathematics, 2008

Learning Heuristic Functions through Approximate Linear Programming.

Marek Petrik, Shlomo Zilberstein

Proceedings of the Eighteenth International Conference on Automated Planning and Scheduling, 2008

Interaction Structure and Dimensionality Reduction in Decentralized MDPs.

Martin Allen, Marek Petrik, Shlomo Zilberstein

Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence, 2008

2007

Average-Reward Decentralized Markov Decision Processes.

Marek Petrik, Shlomo Zilberstein

Proceedings of the IJCAI 2007, 2007

An Analysis of Laplacian Methods for Value Function Approximation in MDPs.

Marek Petrik

Proceedings of the IJCAI 2007, 2007

Anytime Coordination Using Separable Bilinear Programs.

Marek Petrik, Shlomo Zilberstein

Proceedings of the Twenty-Second AAAI Conference on Artificial Intelligence, 2007

2006

Learning parallel portfolios of algorithms.

Marek Petrik, Shlomo Zilberstein

Ann. Math. Artif. Intell., 2006

Learning Static Parallel Portfolios of Algorithms.

Marek Petrik, Shlomo Zilberstein

Proceedings of the International Symposium on Artificial Intelligence and Mathematics, 2006