default search action
Marek Petrik
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
- [j11]Audrey Huang, Mohammad Ghavamzadeh, Nan Jiang, Marek Petrik:
Non-adaptive Online Finetuning for Offline Reinforcement Learning. RLJ 1: 182-197 (2024) - [j10]Gersi Doko, Guang Yang, Daniel S. Brown, Marek Petrik:
ROIL: Robust Offline Imitation Learning without Trajectories. RLJ 2: 593-605 (2024) - [c48]Marek Petrik, Guy Tennenholtz, Mohammad Ghavamzadeh:
Bayesian Regret Minimization in Offline Bandits. ICML 2024 - [i38]Elita A. Lobo, Harvineet Singh, Marek Petrik, Cynthia Rudin, Himabindu Lakkaraju:
Data Poisoning Attacks on Off-Policy Policy Evaluation Methods. CoRR abs/2404.04714 (2024) - [i37]Elita A. Lobo, Cyrus Cousins, Yair Zick, Marek Petrik:
Percentile Criterion Optimization in Offline Reinforcement Learning. CoRR abs/2404.05055 (2024) - [i36]Xihong Su, Marek Petrik:
Solving Multi-Model MDPs by Coordinate Ascent and Dynamic Programming. CoRR abs/2407.06329 (2024) - [i35]Xihong Su, Marek Petrik, Julien Grand-Clément:
Stationary Policies are Optimal in Risk-averse Total-reward MDPs with EVaR. CoRR abs/2408.17286 (2024) - [i34]Qiuhao Wang, Shaohang Xu, Chin Pang Ho, Marek Petrik:
Policy Gradient for Robust Markov Decision Processes. CoRR abs/2410.22114 (2024) - [i33]Jia Lin Hau, Erick Delage, Esther Derman, Mohammad Ghavamzadeh, Marek Petrik:
Q-learning for Quantile MDPs: A Decomposition, Performance, and Convergence Analysis. CoRR abs/2410.24128 (2024) - 2023
- [c47]Jia Lin Hau, Marek Petrik, Mohammad Ghavamzadeh:
Entropic Risk Optimization in Discounted MDPs. AISTATS 2023: 47-76 - [c46]Qiuhao Wang, Chin Pang Ho, Marek Petrik:
Policy Gradient in Robust MDPs with Global Convergence Guarantee. ICML 2023: 35763-35797 - [c45]Cyrus Cousins, Elita A. Lobo, Marek Petrik, Yair Zick:
Percentile Criterion Optimization in Offline Reinforcement Learning. NeurIPS 2023 - [c44]Julien Grand-Clément, Marek Petrik:
Reducing Blackwell and Average Optimality to Discounted MDPs via the Blackwell Discount Factor. NeurIPS 2023 - [c43]Jia Lin Hau, Erick Delage, Mohammad Ghavamzadeh, Marek Petrik:
On Dynamic Programming Decompositions of Static Risk Measures in Markov Decision Processes. NeurIPS 2023 - [c42]Xihong Su, Marek Petrik:
Solving multi-model MDPs by coordinate ascent and dynamic programming. UAI 2023: 2016-2025 - [i32]Julien Grand-Clément, Marek Petrik:
Reducing Blackwell and Average Optimality to Discounted MDPs via the Blackwell Discount Factor. CoRR abs/2302.00036 (2023) - [i31]Jia Lin Hau, Erick Delage, Mohammad Ghavamzadeh, Marek Petrik:
On Dynamic Program Decompositions of Static Risk Measures. CoRR abs/2304.12477 (2023) - [i30]Mohammad Ghavamzadeh, Marek Petrik, Guy Tennenholtz:
A Convex Relaxation Approach to Bayesian Regret Minimization in Offline Bandits. CoRR abs/2306.01237 (2023) - [i29]Julien Grand-Clément, Marek Petrik, Nicolas Vieille:
Beyond discounted returns: Robust Markov decision processes with average and Blackwell optimality. CoRR abs/2312.03618 (2023) - 2022
- [c41]Chin Pang Ho, Marek Petrik, Wolfram Wiesemann:
Robust $\phi$-Divergence MDPs. NeurIPS 2022 - [c40]Elita A. Lobo, Harvineet Singh, Marek Petrik, Cynthia Rudin, Himabindu Lakkaraju:
Data poisoning attacks on off-policy policy evaluation methods. UAI 2022: 1264-1274 - [i28]Chin Pang Ho, Marek Petrik, Wolfram Wiesemann:
Robust Phi-Divergence MDPs. CoRR abs/2205.14202 (2022) - [i27]Jia Lin Hau, Marek Petrik, Mohammad Ghavamzadeh, Reazul Hasan Russel:
RASR: Risk-Averse Soft-Robust MDPs with EVaR and Entropic Risk. CoRR abs/2209.04067 (2022) - [i26]Julien Grand-Clément, Marek Petrik:
On the convex formulations of robust Markov decision processes. CoRR abs/2209.10187 (2022) - [i25]Qiuhao Wang, Chin Pang Ho, Marek Petrik:
On the Convergence of Policy Gradient in Robust MDPs. CoRR abs/2212.10439 (2022) - 2021
- [j9]Chin Pang Ho, Marek Petrik, Wolfram Wiesemann:
Partial Policy Iteration for L1-Robust Markov Decision Processes. J. Mach. Learn. Res. 22: 275:1-275:46 (2021) - [c39]Bahram Behzadian, Reazul Hasan Russel, Marek Petrik, Chin Pang Ho:
Optimizing Percentile Criterion using Robust MDPs. AISTATS 2021: 1009-1017 - [c38]Zaynah Javed, Daniel S. Brown, Satvik Sharma, Jerry Zhu, Ashwin Balakrishna, Marek Petrik, Anca D. Dragan, Ken Goldberg:
Policy Gradient Bayesian Robust Optimization for Imitation Learning. ICML 2021: 4785-4796 - [c37]Mostafa Hussein, Brendan Crowe, Madison Clark-Turner, Paul Gesel, Marek Petrik, Momotaz Begum:
Robust Behavior Cloning with Adversarial Demonstration Detection. IROS 2021: 7858-7864 - [c36]Bahram Behzadian, Marek Petrik, Chin Pang Ho:
Fast Algorithms for $L_\infty$-constrained S-rectangular Robust MDPs. NeurIPS 2021: 25982-25992 - [i24]Mostafa Hussein, Brendan Crowe, Marek Petrik, Momotaz Begum:
Robust Maximum Entropy Behavior Cloning. CoRR abs/2101.01251 (2021) - [i23]Zaynah Javed, Daniel S. Brown, Satvik Sharma, Jerry Zhu, Ashwin Balakrishna, Marek Petrik, Anca D. Dragan, Ken Goldberg:
Policy Gradient Bayesian Robust Optimization for Imitation Learning. CoRR abs/2106.06499 (2021) - 2020
- [c35]Maximilian Fickert
, Tianyi Gu, Leonhard Staut, Wheeler Ruml, Jörg Hoffmann, Marek Petrik:
Beliefs We Can Believe in: Replacing Assumptions with Data in Real-Time Search. AAAI 2020: 9827-9834 - [c34]Daniel S. Brown, Scott Niekum, Marek Petrik:
Bayesian Robust Optimization for Imitation Learning. NeurIPS 2020 - [i22]Bo Liu, Ian Gemp, Mohammad Ghavamzadeh, Ji Liu, Sridhar Mahadevan, Marek Petrik:
Proximal Gradient Temporal Difference Learning: Stable Reinforcement Learning with Polynomial Sample Complexity. CoRR abs/2006.03976 (2020) - [i21]Chin Pang Ho, Marek Petrik, Wolfram Wiesemann:
Partial Policy Iteration for L1-Robust Markov Decision Processes. CoRR abs/2006.09484 (2020) - [i20]Reazul Hasan Russel, Bahram Behzadian, Marek Petrik:
Entropic Risk Constrained Soft-Robust Policy Optimization. CoRR abs/2006.11679 (2020) - [i19]Bo Liu, Ji Liu, Mohammad Ghavamzadeh, Sridhar Mahadevan, Marek Petrik:
Finite-Sample Analysis of GTD Algorithms. CoRR abs/2006.14364 (2020) - [i18]Daniel S. Brown, Scott Niekum, Marek Petrik:
Bayesian Robust Optimization for Imitation Learning. CoRR abs/2007.12315 (2020) - [i17]Elita A. Lobo, Mohammad Ghavamzadeh, Marek Petrik:
Soft-Robust Algorithms for Handling Model Misspecification. CoRR abs/2011.14495 (2020)
2010 – 2019
- 2019
- [c33]Andrew Mitchell, Wheeler Ruml, Fabian Spaniol, Jörg Hoffmann, Marek Petrik:
Real-Time Planning as Decision-Making under Uncertainty. AAAI 2019: 2338-2345 - [c32]Bahram Behzadian, Soheil Gharatappeh, Marek Petrik:
Fast Feature Selection for Linear Value Function Approximation. ICAPS 2019: 601-609 - [c31]Mostafa Hussein, Momotaz Begum, Marek Petrik:
Inverse Reinforcement Learning of Interaction Dynamics from Demonstrations. ICRA 2019: 2267-2274 - [c30]Marek Petrik, Reazul Hasan Russel:
Beyond Confidence Regions: Tight Bayesian Ambiguity Sets for Robust MDPs. NeurIPS 2019: 7047-7056 - [i16]Marek Petrik, Reazul Hasan Russel:
Beyond Confidence Regions: Tight Bayesian Ambiguity Sets for Robust MDPs. CoRR abs/1902.07605 (2019) - [i15]Reazul Hasan Russel, Tianyi Gu, Marek Petrik:
Robust Exploration with Tight Bayesian Plausibility Sets. CoRR abs/1904.08528 (2019) - [i14]Bahram Behzadian, Reazul Hasan Russel, Marek Petrik:
High-Confidence Policy Optimization: Reshaping Ambiguity Sets in Robust MDPs. CoRR abs/1910.10786 (2019) - [i13]Reazul Hasan Russel, Bahram Behzadian, Marek Petrik:
Optimizing Norm-Bounded Weighted Ambiguity Sets for Robust MDPs. CoRR abs/1912.02696 (2019) - 2018
- [j8]Bo Liu, Ian Gemp, Mohammad Ghavamzadeh, Ji Liu, Sridhar Mahadevan, Marek Petrik:
Proximal Gradient Temporal Difference Learning: Stable Reinforcement Learning with Polynomial Sample Complexity. J. Artif. Intell. Res. 63: 461-494 (2018) - [c29]Chin Pang Ho, Marek Petrik, Wolfram Wiesemann:
Fast Bellman Updates for Robust MDPs. ICML 2018: 1984-1993 - [c28]Bahram Behzadian, Marek Petrik:
Low-rank Feature Selection for Reinforcement Learning. ISAIM 2018 - [c27]Andrea Tirinzoni, Marek Petrik, Xiangli Chen, Brian D. Ziebart:
Policy-Conditioned Uncertainty Sets for Robust Markov Decision Processes. NeurIPS 2018: 8953-8963 - [i12]Alexander Brown, Marek Petrik:
Interpretable Reinforcement Learning with Ensemble Methods. CoRR abs/1809.06995 (2018) - [i11]Reazul Hasan Russel, Marek Petrik:
Tight Bayesian Ambiguity Sets for Robust MDPs. CoRR abs/1811.06512 (2018) - 2017
- [c26]Stephen Becker, Ban Kawas, Marek Petrik:
Robust Partially-Compressed Least-Squares. AAAI 2017: 1742-1748 - [c25]Bence Cserna, Marek Petrik, Reazul Hasan Russel, Wheeler Ruml:
Value Directed Exploration in Multi-Armed Bandits with Structured Priors. UAI 2017 - [c24]Adam N. Elmachtoub, Ryan McNellis, Sechan Oh, Marek Petrik:
A Practical Method for Solving Contextual Bandit Problems Using Decision Trees. UAI 2017 - [i10]Bence Cserna, Marek Petrik, Reazul Hasan Russel, Wheeler Ruml:
Value Directed Exploration in Multi-Armed Bandits with Structured Priors. CoRR abs/1704.03926 (2017) - [i9]Adam N. Elmachtoub
A Practical Method for Solving Contextual Bandit Problems Using Decision Trees. CoRR abs/1706.04687 (2017) - 2016
- [c23]Bo Liu, Ji Liu, Mohammad Ghavamzadeh, Sridhar Mahadevan, Marek Petrik:
Proximal Gradient Temporal Difference Learning Algorithms. IJCAI 2016: 4195-4199 - [c22]Mohammad Ghavamzadeh, Marek Petrik, Yinlam Chow:
Safe Policy Improvement by Minimizing Robust Baseline Regret. NIPS 2016: 2298-2306 - [c21]Marek Petrik, Ronny Luss:
Interpretable Policies for Dynamic Product Recommendations. UAI 2016 - [i8]Amit Dhurandhar, Sechan Oh, Marek Petrik:
Building an Interpretable Recommender via Loss-Preserving Transformation. CoRR abs/1606.05819 (2016) - 2015
- [j7]Dan Andrei Iancu, Marek Petrik, Dharmashankar Subramanian:
Tight Approximations of Dynamic Risk Measures. Math. Oper. Res. 40(3): 655-682 (2015) - [c20]Bo Liu, Ji Liu, Mohammad Ghavamzadeh, Sridhar Mahadevan, Marek Petrik:
Finite-Sample Analysis of Proximal Gradient TD Algorithms. UAI 2015: 504-513 - [c19]Marek Petrik, Xiaojian Wu:
Optimal Threshold Control for Energy Arbitrage with Degradable Battery Storage. UAI 2015: 692-701 - [i7]Stephen Becker, Ban Kawas, Marek Petrik, Karthikeyan Natesan Ramamurthy:
Robust Partially-Compressed Least-Squares. CoRR abs/1510.04905 (2015) - 2014
- [j6]Stephen J. Buckley, Markus Ettl, Prateek Jain, Ronny Luss, Marek Petrik, Rajesh Kumar Ravi, Chitra Venkatramani:
Social media and customer behavior analytics for personalized customer engagements. IBM J. Res. Dev. 58(5/6) (2014) - [j5]Amit Dhurandhar, Marek Petrik:
Efficient and accurate methods for updating generalized linear models with multiple feature additions. J. Mach. Learn. Res. 15(1): 2607-2627 (2014) - [c18]Marek Petrik, Dharmashankar Subramanian:
RAAM: The Benefits of Robustness in Approximating Aggregated MDPs in Reinforcement Learning. NIPS 2014: 1979-1987 - [i6]Marek Petrik, Shlomo Zilberstein:
A Bilinear Programming Approach for Multiagent Planning. CoRR abs/1401.3461 (2014) - 2013
- [c17]Marek Petrik, Dharmashankar Subramanian, Janusz Marecki:
Solution Methods for Constrained Markov Decision Process with Continuous Probability Modulation. UAI 2013 - [c16]Francisco Barahona, Markus Ettl, Marek Petrik, Peter M. Rimshnick:
Agile logistics simulation and optimization for managing disaster responses. WSC 2013: 3340-3351 - [i5]Marek Petrik, Dharmashankar Subramanian, Janusz Marecki:
Solution Methods for Constrained Markov Decision Process with Continuous Probability Modulation. CoRR abs/1309.6857 (2013) - 2012
- [c15]Marek Petrik:
Approximate Dynamic Programming By Minimizing Distributionally Robust Bounds. ICML 2012 - [c14]Marek Petrik, Dharmashankar Subramanian:
An Approximate Solution Method for Large Risk-Averse Markov Decision Processes. UAI 2012: 805-814 - [p1]Marek Petrik, Shlomo Zilberstein
Learning Feature-Based Heuristic Functions. Autonomous Search 2012: 269-305 - [i4]Marek Petrik:
Approximate Dynamic Programming By Minimizing Distributionally Robust Bounds. CoRR abs/1205.1782 (2012) - [i3]Marek Petrik, Dharmashankar Subramanian:
An Approximate Solution Method for Large Risk-Averse Markov Decision Processes. CoRR abs/1210.4901 (2012) - 2011
- [j4]Marek Petrik, Shlomo Zilberstein:
Robust Approximate Bilinear Programming for Value Function Approximation. J. Mach. Learn. Res. 12: 3027-3063 (2011) - [c13]Marek Petrik, Shlomo Zilberstein:
Linear Dynamic Programs for Resource Management. AAAI 2011: 1377-1383 - 2010
- [c12]Marek Petrik, Gavin Taylor, Ronald Parr, Shlomo Zilberstein:
Feature Selection Using Regularization in Approximate Linear Programs for Markov Decision Processes. ICML 2010: 871-878 - [i2]Marek Petrik, Gavin Taylor, Ronald Parr, Shlomo Zilberstein:
Feature Selection Using Regularization in Approximate Linear Programs for Markov Decision Processes. CoRR abs/1005.1860 (2010) - [i1]Marek Petrik, Shlomo Zilberstein:
Global Optimization for Value Function Approximation. CoRR abs/1006.2743 (2010)
2000 – 2009
- 2009
- [j3]Marek Petrik, Shlomo Zilberstein:
A Bilinear Programming Approach for Multiagent Planning. J. Artif. Intell. Res. 35: 235-274 (2009) - [j2]Jeffrey Johns, Marek Petrik, Sridhar Mahadevan:
Hybrid least-squares algorithms for approximate policy evaluation. Mach. Learn. 76(2-3): 243-256 (2009) - [c11]Marek Petrik, Shlomo Zilberstein
Constraint relaxation in approximate linear programs. ICML 2009: 809-816 - [c10]Marek Petrik, Shlomo Zilberstein:
Robust Value Function Approximation Using Bilinear Programming. NIPS 2009: 1446-1454 - [c9]Jeffrey Johns, Marek Petrik, Sridhar Mahadevan:
Hybrid Least-Squares Algorithms for Approximate Policy Evaluation. ECML/PKDD (1) 2009: 9 - 2008
- [c8]Martin Allen, Marek Petrik, Shlomo Zilberstein:
Interaction Structure and Dimensionality Reduction in Decentralized MDPs. AAAI 2008: 1440-1441 - [c7]Marek Petrik, Shlomo Zilberstein:
Learning Heuristic Functions through Approximate Linear Programming. ICAPS 2008: 248-255 - [c6]Marek Petrik, Shlomo Zilberstein:
A Successive Approximation Algorithm for Coordination Problems. ISAIM 2008 - [c5]Marek Petrik, Bruno Scherrer:
Biasing Approximate Dynamic Programming with a Lower Discount Factor. NIPS 2008: 1265-1272 - 2007
- [c4]Marek Petrik, Shlomo Zilberstein:
Anytime Coordination Using Separable Bilinear Programs. AAAI 2007: 750-755 - [c3]Marek Petrik, Shlomo Zilberstein:
Average-Reward Decentralized Markov Decision Processes. IJCAI 2007: 1997-2002 - [c2]Marek Petrik:
An Analysis of Laplacian Methods for Value Function Approximation in MDPs. IJCAI 2007: 2574-2579 - 2006
- [j1]Marek Petrik, Shlomo Zilberstein
Learning parallel portfolios of algorithms. Ann. Math. Artif. Intell. 48(1-2): 85-106 (2006) - [c1]Marek Petrik, Shlomo Zilberstein:
Learning Static Parallel Portfolios of Algorithms. AI&M 2006
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from ,
, and
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and
to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from .
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-12-01 01:16 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by: