← authors · overview

• Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems
  2018 · 26 citations
• Stochastic approximation with cone-contractive operators: Sharp $\ell_ınfty$-bounds for $Q$-learning
  2019 · 23 citations
• Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning
  2021 · 14 citations
• Instance-dependent $\ell_ınfty$-bounds for policy evaluation in tabular reinforcement learning
  2019 · 6 citations
• Optimal policy evaluation using kernel-based temporal difference methods
  2021 · 4 citations
• Optimal oracle inequalities for solving projected fixed-point equations
  2020 · 2 citations
• Instance-optimality in optimal value estimation: Adaptivity via variance-reduced Q-learning
  2021 · 2 citations
• Instance-Dependent Confidence and Early Stopping for Reinforcement Learning
  2022 · 1 citations
• Exploiting Exogenous Structure for Sample-Efficient Reinforcement Learning
  2024
• Bellman Residual Orthogonalization for Offline Reinforcement Learning
  2022
• Stabilizing Q-learning with Linear Architectures for Provably Efficient Learning
  2022
• Taming "data-hungry" reinforcement learning? Stability in continuous state-action spaces
  2024