Ziqi Zhang

Decoupled Offline to Online finetuning via Dynamics Model

Distribution Corrected Estimation via Adversarial Density Weighted Regression

Improving Offline-to-Online Reinforcement Learning with Q Conditioned State Entropy Exploration

Revisiting the Design Choices in Max-Return Sequence Modeling

SERA: Sample Efficient Reward Augmentation in offline-to-online Reinforcement Learning