← authors · overview

• Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP
  2019 · 38 citations
• Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature
  2021 · 5 citations
• $\sqrtn$-Regret for Learning in Markov Decision Processes with Function Approximation and Low Bellman Rank
  2019 · 4 citations
• Exploration via Hindsight Goal Generation
  2019 · 3 citations
• On the Expressivity of Neural Networks for Deep Reinforcement Learning
  2019 · 1 citations
• Asymptotic Instance-Optimal Algorithms for Interactive Decision Making
  2022 · 1 citations
• STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving
  2025
• Refined Analysis of FPL for Adversarial Markov Decision Processes
  2020
• Model-based Offline Reinforcement Learning with Local Misspecification
  2023