 SelfBC: Self Behavior Cloning for Offline Reinforcement LearningEuropean Conference on Artificial Intelligence (ECAI), 2024 |
 Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for
Autonomous Real-World Reinforcement LearningIEEE International Conference on Robotics and Automation (ICRA), 2023 |
 Iteratively Refined Behavior Regularization for Offline Reinforcement
LearningNeural Information Processing Systems (NeurIPS), 2023 |
 Revisiting the Minimalist Approach to Offline Reinforcement LearningNeural Information Processing Systems (NeurIPS), 2023 |
 Balancing policy constraint and ensemble size in uncertainty-based
offline reinforcement learningMachine-mediated learning (ML), 2023 |
 Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online
Fine-TuningNeural Information Processing Systems (NeurIPS), 2023 |
