Dongruo Zhou

Instance-Dependent Continuous-Time Reinforcement Learning via Maximum Likelihood Estimation

Near-Optimal Second-Order Guarantees for Model-Based Adversarial Imitation Learning

On the Limits of Test-Time Compute: Sequential Reward Filtering for Better Inference

FERA: Uncertainty-aware Federated Reasoning for Large Language Models

Model-based RL as a Minimalist Approach to Horizon-Free and Second-Order Bounds

Breaking the $\log(1/\Delta_2)$ Barrier: Better Batched Best Arm Identification with Adaptive Grids

Towards Zero-Shot Generalization in Offline Reinforcement Learning

Federated In-Context Learning: Iterative Refinement for Improved Answer Quality

CoPS: Empowering LLM Agents with Provable Cross-Task Experience Sharing

Leveraging Imitation Learning and LLMs for Efficient Hierarchical Reinforcement Learning

Provable Zero-Shot Generalization in Offline Reinforcement Learning