 ArrayBot: Reinforcement Learning for Generalizable Distributed Manipulation through TouchIEEE International Conference on Robotics and Automation (ICRA), 2023 |
 MAD-TD: Model-Augmented Data stabilizes High Update Ratio RLInternational Conference on Learning Representations (ICLR), 2024 |
 Curious Replay for Model-based AdaptationInternational Conference on Machine Learning (ICML), 2023 |
 Self-Consistent Models and ValuesNeural Information Processing Systems (NeurIPS), 2021 |
 Understanding and Mitigating the Limitations of Prioritized Experience
ReplayConference on Uncertainty in Artificial Intelligence (UAI), 2020 |
 Learning to Sample with Local and Global Contexts in Experience Replay
BufferInternational Conference on Learning Representations (ICLR), 2020 |
 An implicit function learning approach for parametric modal regressionNeural Information Processing Systems (NeurIPS), 2020 |
