← authors · overview

• Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes
  2022 · 5 citations
• Improved Corruption Robust Algorithms for Episodic Reinforcement Learning
  2021 · 4 citations
• Beyond No Regret: Instance-Dependent PAC Reinforcement Learning
  2021 · 4 citations
• Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL
  2024 · 4 citations
• First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach
  2021 · 3 citations
• Instance-Dependent Near-Optimal Policy Identification in Linear MDPs via Online Experiment Design
  2022 · 3 citations
• Task-Optimal Exploration in Linear Dynamical Systems
  2021 · 1 citations
• Optimal Exploration for Model-Based RL in Nonlinear Systems
  2023 · 1 citations
• Minimax Optimal Strategy for Delayed Observations in Online Reinforcement Learning
  2026
• On the Limitations and Possibilities of Nash Regret Minimization in Zero-Sum Matrix Games under Noisy Feedback
  2023
• Sample Complexity Reduction via Policy Difference Estimation in Tabular Reinforcement Learning
  2024
• Cost-Effective Proxy Reward Model Construction with On-Policy and Active Learning
  2024