Yuqing Du
yuqing_du (at) berkeley (dot) edu
Hello! I am a Research Scientist at Google DeepMind. I received my PhD from UC Berkeley, advised by Professor Pieter Abbeel at the Berkeley Artificial Intelligence Research (BAIR) Lab. My thesis, "Human-Centric Reward Design" can be found here.
I have a B.A.Sc in Engineering Physics with a minor in Honours Mathematics from the University of British Columbia, where I was advised by Professors Machiel Van der Loos and Elizabeth Croft at the Collaborative Advanced Robotics and Intelligent Systems (CARIS) Lab, where I worked on human-robot interaction.Previously, I have also been a visiting researcher at FAIR (Meta), and have interned at DeepMind and X, the moonshot factory.
I am broadly interested in helping agents learn from humans -- whether that be modelling human preferences, learning via interaction, or acquiring world priors from people. For example, some of my prior works include training multimodal reward models from human feedback, learning to assist and empower people, and helping agents leverage human priors. Currently, I am interested in developing agents that can learn from diverse sets of human preferences.
preprints
publications
- Neural Information Processing Systems (NeurIPS) 2023
- Conference on Lifelong Learning Agents (CoLLAs) 2023
(Oral) - International Conference on Machine Learning (ICML) 2023
- International Conference on Robotics and Automation (ICRA) 2023
- International Conference on Machine Learning (ICML) 2022
- International Conference on Learning Representations (ICLR) 2022
- International Conference on Robotics and Automation (ICRA) 2021
(Best Cognitive Robotics Paper Finalist) - Neural Information Processing Systems (NeurIPS) 2020
- International Conference on Robotics and Automation (ICRA) 2019