Shaofeng Zou

24 papers · 2019–2025 · 7 conferences · across top CS/AI conferences

Achievements

+10 more ↓

🏃 Academic Marathon (6) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (7) 🐝 Cross-Pollinator (9)

🌍 Conference Polyglot (7) 🏃 Academic Marathon (6) 🧭 Keyword Pioneer 🏆 Keyword Champion (2) 🏆 Grand Slam 🔥 Unstoppable (7) 💎 Century Club (24) ⚡ Prolific Year (7) 📈 Trend Setter 🗃️ Keyword Collector (87)

Conferences

NIPS (7) ICML (5) AAAI (4) ICLR (3) AISTATS (2) UAI (2) JMLR (1)

Top co-authors

Yue Wang (9) Yi Zhou (8) Ashley Prater-Bennette (4) Zhongchang Sun (3) Ziyi Chen (3) Qi Zhang (3) Shaocong Ma (3) Yingbin Liang (3) Fei Miao (2) Simon Khan (2)

Keywords

sample complexity (5) markov decision process (5) reinforcement learning (4) off-policy learning (3) linear function approximation (3) robust reinforcement learning (3) robust markov decision process (3) distributionally robust optimization (2) finite-sample analysis (2) linear convergence (2) temporal-difference learning (2) policy gradient (2) function approximation (2) temporal difference learning (2) bellman equation (2) convergence analysis (2) model uncertainty (2) stochastic approximation (2) non-asymptotic analysis (2) average reward (2)

Papers

Near-Optimal Sample Complexity for Iterated CVaR Reinforcement Learning with a Generative Model AISTATS 2025 MGDA Converges under Generalized Smoothness, Provably ICLR 2025 Revisiting Large-Scale Non-convex Distributionally Robust Optimization ICLR 2025 Model-Free Robust Reinforcement Learning with Sample Complexity Analysis UAI 2024 A Unified Principle of Pessimism for Offline Reinforcement Learning under Model Mismatch NIPS 2024 Policy Optimization for Robust Average Reward MDPs NIPS 2024 Large-Scale Non-convex Stochastic Constrained Distributionally Robust Optimization AAAI 2024 Sample Complexity Characterization for Linear Contextual MDPs AISTATS 2024 Constrained Reinforcement Learning Under Model Mismatch ICML 2024 Non-Asymptotic Analysis for Single-Loop (Natural) Actor-Critic with Compatible Function Approximation ICML 2024 Model-Free Robust Average-Reward Reinforcement Learning ICML 2023 Decentralized Robust V-learning for Solving Markov Games with Model Uncertainty JMLR 2023 Robust Average-Reward Markov Decision Processes AAAI 2023 Policy Gradient Method For Robust Reinforcement Learning ICML 2022 Sample and Communication-Efficient Decentralized Actor-Critic Algorithms with Finite-Time Analysis ICML 2022 Greedy-GQ with Variance Reduction: Finite-time Analysis and Improved Complexity ICLR 2021 Online Robust Reinforcement Learning with Model Uncertainty NIPS 2021 Learning Graph Neural Networks with Approximate Gradient Descent AAAI 2021 Non-Asymptotic Analysis for Two Time-scale TDC with General Smooth Function Approximation NIPS 2021 Variance-Reduced Off-Policy TDC Learning: Non-Asymptotic Convergence Analysis NIPS 2020 Finite-sample Analysis of Greedy-GQ with Linear Function Approximation under Markovian Noise UAI 2020 Information-Theoretic Understanding of Population Risk Improvement with Model Compression AAAI 2020 Finite-Sample Analysis for SARSA with Linear Function Approximation NIPS 2019 Two Time-scale Off-Policy TD Learning: Non-asymptotic Analysis over Markovian Samples NIPS 2019