← authors · overview

• An Improved Analysis of (Variance-Reduced) Policy Gradient and Natural Policy Gradient Methods
  2022 · 30 citations
• Provably Efficient Exploration for Reinforcement Learning Using Unsupervised Learning
  2020 · 7 citations
• How Does an Approximate Model Help in Reinforcement Learning?
  2019 · 6 citations
• Provably Correct Optimization and Exploration with Non-linear Policies
  2021 · 2 citations
• AsyncQVI: Asynchronous-Parallel Q-Value Iteration for Discounted Markov Decision Processes with Near-Optimal Sample Complexity
  2018 · 1 citations
• DeepVision-103K: A Visually Diverse, Broad-Coverage, and Verifiable Mathematical Dataset for Multimodal Reasoning
  2026
• Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward
  2025