← authors · overview

• On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift
  2019 · 111 citations
• Agnostic Q-learning with Function Approximation in Deterministic Systems: Tight Bounds on Approximation Error and Sample Complexity
  2020 · 23 citations
• Bilinear Classes: A Structural Framework for Provable Generalization in RL
  2021 · 21 citations
• Neural Temporal-Difference and Q-Learning Provably Converge to Global Optima
  2019 · 15 citations
• Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence
  2021 · 8 citations
• MUSBO: Model-based Uncertainty Regularized and Sample Efficient Batch Optimization for Deployment Constrained Reinforcement Learning
  2021 · 6 citations
• Offline Reinforcement Learning with Realizability and Single-policy Concentrability
  2022 · 6 citations
• Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems