Marek Petrik

30 papers · 2008–2026 · 7 conferences · across top CS/AI conferences

Achievements

+11 more ↓

🌍 Conference Polyglot (7) 🌉 Interdisciplinary Bridge 🐣 Hot Topic Early Bird 🧭 Keyword Pioneer 🏃 Academic Marathon (17)

🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🔬 Deep Specialist (19) 🏆 Keyword Champion (8) 🧬 Topic Evolution 🗃️ Keyword Collector (106) 🚀 Conference Pioneer 📈 Trend Setter 💎 Century Club (29) 🔥 Unstoppable (8) ⚡ Prolific Year (6)

Conferences

NIPS (12) ICML (5) AAAI (4) AISTATS (3) JMLR (3) UAI (2) IJCAI (1)

Top co-authors

Chin Pang Ho (7) Mohammad Ghavamzadeh (6) Wolfram Wiesemann (3) Jia Lin Hau (3) Wheeler Ruml (2) Bahram Behzadian (2) Reazul Hasan Russel (2) Shlomo Zilberstein (2) Erick Delage (2) Julien Grand-Clément (2)

Research topics

Optimization (1)

Keywords

markov decision process (9) robust optimization (9) robust markov decision process (8) reinforcement learning (8) policy iteration (6) dynamic programming (5) ambiguity set (5) value function approximation (4) approximate dynamic programming (4) policy optimization (3) policy gradient (3) robust mdp (3) bellman residual (2) optimization algorithm (2) imitation learning (2) bilinear programming (2) risk management (2) regret minimization (2) heuristic search (2) bayesian inference (2)

Papers

Convergence of Fast Policy Iteration in Markov Games and Robust MDPs AAAI 2026 Risk-averse Total-reward MDPs with ERM and EVaR AAAI 2025 Q-learning for Quantile MDPs: A Decomposition, Performance, and Convergence Analysis AISTATS 2025 Provable Policy Gradient for Robust Average-Reward MDPs Beyond Rectangularity ICML 2025 Bayesian Regret Minimization in Offline Bandits ICML 2024 Policy Gradient in Robust MDPs with Global Convergence Guarantee ICML 2023 Solving multi-model MDPs by coordinate ascent and dynamic programming UAI 2023 Entropic Risk Optimization in Discounted MDPs AISTATS 2023 On Dynamic Programming Decompositions of Static Risk Measures in Markov Decision Processes NIPS 2023 Reducing Blackwell and Average Optimality to Discounted MDPs via the Blackwell Discount Factor NIPS 2023 Percentile Criterion Optimization in Offline Reinforcement Learning NIPS 2023 Robust $\phi$-Divergence MDPs NIPS 2022 Data poisoning attacks on off-policy policy evaluation methods UAI 2022 Optimizing Percentile Criterion using Robust MDPs AISTATS 2021 Fast Algorithms for $L_\infty$-constrained S-rectangular Robust MDPs NIPS 2021 Policy Gradient Bayesian Robust Optimization for Imitation Learning ICML 2021 Partial Policy Iteration for L1-Robust Markov Decision Processes JMLR 2021 Bayesian Robust Optimization for Imitation Learning NIPS 2020 Beliefs We Can Believe in: Replacing Assumptions with Data in Real-Time Search AAAI 2020 Real-Time Planning as Decision-Making under Uncertainty AAAI 2019 Beyond Confidence Regions: Tight Bayesian Ambiguity Sets for Robust MDPs NIPS 2019 Policy-Conditioned Uncertainty Sets for Robust Markov Decision Processes NIPS 2018 Fast Bellman Updates for Robust MDPs ICML 2018 Safe Policy Improvement by Minimizing Robust Baseline Regret NIPS 2016 Proximal Gradient Temporal Difference Learning Algorithms IJCAI 2016 RAAM: The Benefits of Robustness in Approximating Aggregated MDPs in Reinforcement Learning NIPS 2014 Efficient and Accurate Methods for Updating Generalized Linear Models with Multiple Feature Additions JMLR 2014 Robust Approximate Bilinear Programming for Value Function Approximation JMLR 2011 Robust Value Function Approximation Using Bilinear Programming NIPS 2009 Biasing Approximate Dynamic Programming with a Lower Discount Factor NIPS 2008