← authors · overview

• Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator
  2018 · 241 citations
• On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift
  2019 · 111 citations
• What are the Statistical Limits of Offline RL with Linear Function Approximation?
  2020 · 37 citations
• Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity
  2020 · 24 citations
• Is Long Horizon Reinforcement Learning More Difficult Than Short Horizon Reinforcement Learning?
  2020 · 23 citations
• Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning?
  2019 · 21 citations
• Bilinear Classes: A Structural Framework for Provable Generalization in RL
  2021 · 21 citations
• Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity
  2022 · 12 citations
• An Exponential Lower Bound for Linearly-Realizable MDPs with Constant Suboptimality Gap