Zhaoran Wang

Reward-Augmented Data Enhances Direct Preference Alignment of LLMs ICML 2025 BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning ICML 2025 Toward Optimal LLM Alignments Using Two-Player Games EMNLP 2025 An Instrumental Value for Data Production and its Application to Data Pricing ICML 2025 The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability ICML 2025 What and How does In-Context Learning Learn? Bayesian Model Averaging, Parameterization, and Generalization AISTATS 2025 Are Transformers Able to Reason by Connecting Separated Knowledge in Training Data? ICLR 2025 Sample-Efficient Multi-Agent RL: An Optimization Perspective ICLR 2024 Let Models Speak Ciphers: Multiagent Debate through Embeddings ICLR 2024 A General Framework for Sequential Decision-Making under Adaptivity Constraints ICML 2024 How Does Goal Relabeling Improve Sample Efficiency? ICML 2024 Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer NIPS 2024 Instrumental Variable Value Iteration for Causal Offline Reinforcement Learning JMLR 2024 Learning Regularized Graphon Mean-Field Games with Unknown Graphons JMLR 2024 Reason for Future, Act for Now: A Principled Architecture for Autonomous LLM Agents ICML 2024 Learning Dynamic Mechanisms in Unknown Environments: A Reinforcement Learning Approach JMLR 2024 Adaptive-Gradient Policy Optimization: Enhancing Policy Learning in Non-Smooth Differentiable Simulations ICML 2024 Learning Regularized Monotone Graphon Mean-Field Games NIPS 2023 Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning ICML 2023 Adaptive Barrier Smoothing for First-Order Policy Gradient with Contact Dynamics ICML 2023 Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments ICML 2023 Achieving Hierarchy-Free Approximation for Bilevel Programs with Equilibrium Constraints ICML 2023 Provably Efficient Generalized Lagrangian Policy Optimization for Safe Multi-Agent Reinforcement Learning L4DC 2023 Double Duality: Variational Primal-Dual Policy Optimization for Constrained Reinforcement Learning JMLR 2023 Can Reinforcement Learning Find Stackelberg-Nash Equilibria in General-Sum Markov Games with Myopically Rational Followers? JMLR 2023 Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration NIPS 2023 Posterior Sampling for Competitive RL: Function Approximation and Partial Observation NIPS 2023 Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithms NIPS 2023 Finding Regularized Competitive Equilibria of Heterogeneous Agent Macroeconomic Models via Reinforcement Learning AISTATS 2023 Optimistic Exploration with Learned Features Provably Solves Markov Decision Processes with Neural Dynamics ICLR 2023 Represent to Control Partially Observed Systems: Representation Learning with Provable Sample Efficiency ICLR 2023 Latent Variable Representation for Reinforcement Learning ICLR 2023 Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processes ICLR 2023 Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization ICLR 2023 Inducing Equilibria via Incentives: Simultaneous Design-and-Play Ensures Global Convergence NIPS 2022 Relational Reasoning via Set Transformers: Provable Efficiency and Applications to MARL NIPS 2022 Towards General Function Approximation in Zero-Sum Markov Games ICLR 2022 Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets ICML 2022 Welfare Maximization in Competitive Equilibrium: Reinforcement Learning for Markov Exchange Economy ICML 2022 Provably Efficient Offline Reinforcement Learning for Partially Observable Markov Decision Processes ICML 2022 Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning ICLR 2022 Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation ICML 2022 FinRL-Meta: Market Environments and Benchmarks for Data-Driven Financial Reinforcement Learning NIPS 2022 Adaptive Model Design for Markov Decision Process ICML 2022 A Unifying Framework of Off-Policy General Value Function Evaluation NIPS 2022 Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning ICML 2022 Pessimism meets VCG: Learning Dynamic Mechanism Design via Offline Reinforcement Learning ICML 2022 Learning from Demonstration: Provably Efficient Adversarial Policy Imitation with Linear Function Approximation ICML 2022 Learn to Match with No Regret: Reinforcement Learning in Markov Matching Markets NIPS 2022 RORL: Robust Offline Reinforcement Learning via Conservative Smoothing NIPS 2022 Exponential Family Model-Based Reinforcement Learning via Score Matching NIPS 2022 Gap-Dependent Bounds for Two-Player Markov Games AISTATS 2022 Reinforcement Learning from Partial Observation: Linear Function Approximation with Provable Sample Efficiency ICML 2022 Infinite-Dimensional Optimization for Zero-Sum Games via Variational Transport ICML 2021 BooVI: Provably Efficient Bootstrapped Value Iteration NIPS 2021 Wasserstein Flow Meets Replicator Dynamics: A Mean-Field Analysis of Representation Learning in Actor-Critic NIPS 2021 Dynamic Bottleneck for Robust Self-Supervised Exploration NIPS 2021 Exponential Bellman Equation and Improved Regret Bounds for Risk-Sensitive Reinforcement Learning NIPS 2021 Pessimism Meets Invariance: Provably Efficient Offline Mean-Field Multi-Agent RL NIPS 2021 Provably Efficient Causal Reinforcement Learning with Confounded Observational Data NIPS 2021 Offline Constrained Multi-Objective Reinforcement Learning via Pessimistic Dual Value Iteration NIPS 2021 A Near-Optimal Algorithm for Stochastic Bilevel Optimization via Double-Momentum NIPS 2021 Is Pessimism Provably Efficient for Offline RL? ICML 2021 Randomized Exploration in Reinforcement Learning with General Value Function Approximation ICML 2021 Sample Elicitation AISTATS 2021 Provably Efficient Actor-Critic for Risk-Sensitive and Robust Adversarial RL: A Linear-Quadratic Case AISTATS 2021 Provably Efficient Safe Exploration via Primal-Dual Policy Optimization AISTATS 2021 Decentralized Single-Timescale Actor-Critic on Zero-Sum Two-Player Stochastic Games ICML 2021 Risk-Sensitive Reinforcement Learning with Function Approximation: A Debiasing Approach ICML 2021 Principled Exploration via Optimistic Bootstrapping and Backward Induction ICML 2021 Learning While Playing in Mean-Field Games: Convergence and Optimality ICML 2021 Provably Sample Efficient Reinforcement Learning in Competitive Linear Quadratic Systems L4DC 2021 Global Convergence of Policy Gradient for Linear-Quadratic Mean-Field Control/Game in Continuous Time ICML 2021 On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game ICML 2021 Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality ICML 2021 Single-Timescale Actor-Critic Provably Finds Globally Optimal Policy ICLR 2021 Provably Efficient Fictitious Play Policy Optimization for Zero-Sum Markov Games with Structured Transitions ICML 2021 Actor-Critic Provably Finds Nash Equilibria of Linear-Quadratic Mean-Field Games ICLR 2020 Dynamic Regret of Policy Optimization in Non-Stationary Environments NIPS 2020 Pontryagin Differentiable Programming: An End-to-End Learning and Control Framework NIPS 2020 Provably Efficient Neural Estimation of Structural Equation Models: An Adversarial Approach NIPS 2020 Provably Efficient Neural GTD for Off-Policy Learning NIPS 2020 Provably Efficient Reinforcement Learning with Kernel and Neural Function Approximations NIPS 2020 Upper Confidence Primal-Dual Reinforcement Learning for CMDP with Adversarial Loss NIPS 2020 End-to-End Learning and Intervention in Games NIPS 2020 Can Temporal-Difference and Q-Learning Learn Representation? A Mean-Field Theory NIPS 2020 Risk-Sensitive Reinforcement Learning: Near-Optimal Risk-Sample Tradeoff in Regret NIPS 2020 Provably efficient reinforcement learning with linear function approximation COLT 2020 Learning Zero-Sum Simultaneous-Move Markov Games Using Function Approximation and Correlated Equilibrium COLT 2020 Neural Policy Gradient Methods: Global Optimality and Rates of Convergence ICLR 2020 On Computation and Generalization of Generative Adversarial Imitation Learning ICLR 2020 Provably Efficient Exploration in Policy Optimization ICML 2020 Computational and Statistical Tradeoffs in Inferring Combinatorial Structures of Ising Model ICML 2020 Semiparametric Nonlinear Bipartite Graph Representation Learning with Provable Guarantees ICML 2020 Deep Reinforcement Learning with Robust and Smooth Policy ICML 2020 On the Global Optimality of Model-Agnostic Meta-Learning ICML 2020 Breaking the Curse of Many Agents: Provable Mean Embedding Q-Iteration for Mean-Field Reinforcement Learning ICML 2020 Generative Adversarial Imitation Learning with Neural Network Parameterization: Global Optimality and Convergence Rate ICML 2020 Agnostic Estimation for Phase Retrieval JMLR 2020 A Theoretical Analysis of Deep Q-Learning L4DC 2020 Provably Global Convergence of Actor-Critic: A Case for Linear Quadratic Regulator with Ergodic Cost NIPS 2019 Variance Reduced Policy Evaluation with Smooth Function Approximation NIPS 2019 Neural Trust Region/Proximal Policy Optimization Attains Globally Optimal Policy NIPS 2019 Off-Policy Evaluation and Learning from Logged Bandit Feedback: Error Reduction via Surrogate Policy ICLR 2019 ACCELERATING NONCONVEX LEARNING VIA REPLICA EXCHANGE LANGEVIN DIFFUSION ICLR 2019 On the statistical rate of nonlinear recovery in generative models with heavy-tailed data ICML 2019 High-dimensional Varying Index Coefficient Models via Stein's Identity JMLR 2019 Statistical-Computational Tradeoff in Single Index Models NIPS 2019 Convergent Policy Optimization for Safe Reinforcement Learning NIPS 2019 Neural Temporal-Difference Learning Converges to Global Optima NIPS 2019 The Edge Density Barrier: Computational-Statistical Tradeoffs in Combinatorial Inference ICML 2018 Minimax-Optimal Privacy-Preserving Sparse PCA in Distributed Systems AISTATS 2018 Nonlinear Structured Signal Estimation in High Dimensions via Iterative Hard Thresholding AISTATS 2018 Contrastive Learning from Pairwise Measurements NIPS 2018 Multi-Agent Reinforcement Learning via Double Averaging Primal-Dual Optimization NIPS 2018 Provable Gaussian Embedding with One Observation NIPS 2018 Estimating High-dimensional Non-Gaussian Multiple Index Models via Stein’s Lemma NIPS 2017 Agnostic Estimation for Misspecified Phase Retrieval Models NIPS 2016 Blind Attacks on Machine Learners NIPS 2016 Online ICA: Understanding Global Dynamics of Nonconvex Optimization via Diffusion Processes NIPS 2016 On the Statistical Limits of Convex Relaxations ICML 2016 More Supervision, Less Computation: Statistical-Computational Tradeoffs in Weakly Supervised Learning NIPS 2016 NESTT: A Nonconvex Primal-Dual Splitting Method for Distributed and Stochastic Optimization NIPS 2016 Sparse Nonlinear Regression: Parameter Estimation under Nonconvexity ICML 2016 A Nonconvex Optimization Framework for Low Rank Matrix Estimation NIPS 2015 Non-convex Statistical Optimization for Sparse Tensor Graphical Model NIPS 2015 Optimal Linear Estimation under Unknown Nonlinear Transform NIPS 2015 High Dimensional EM Algorithm: Statistical Optimization and Asymptotic Normality NIPS 2015 Tighten after Relax: Minimax-Optimal Sparse PCA in Polynomial Time NIPS 2014 Sparse PCA with Oracle Property NIPS 2014 Sparse Principal Component Analysis for High Dimensional Multivariate Time Series AISTATS 2013