Zhiyuan Zhou

Robust Fine-tuning of Vision-Language-Action Robot Policies via Parameter Merging

Generalizing Subgoals from Single Instances using Hypothesis-Preserving Ensembles

Compute-Optimal Scaling for Value-Based Deep RL

Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data

Reinforcement Learning with Action Chunking

Behavioral Exploration: Learning to Explore via In-Context Adaptation

Learning Transferable Sub-goals by Hypothesizing Generalizing Features