I am generally interested in embodied AI that enables learning through interaction with environments. I study reinforcement learning and imitation learning. Before I came to Stanford, I worked toward surpassing human-level performance in 3D games with deep reinforcement learning.
Besides dealing with MDPs, my previous work also lies at the intersection of deep learning, physics, engineering, and social science. With these diverse backgrounds, my curiosities naturally extend to neuroscience, epistemology, and cognition science. I believe that the community of embodied AI will evolve together with these fields.
Many Ways to be Lonely: Fine-grained Characterization of Loneliness and its Potential Changes in
Yueyi Jiang, Yunfan Jiang, Liu Leqi, Piotr Winkielman
Under review as a conference paper at AAAI ICWSM-2022.
CSTNet: A Dual-Branch Convolutional Neural Network for Imaging of Reactive Flows using Chemical
Yunfan Jiang, Jingjing Si, Rui Zhang, Godwin Enemali, Bin Zhou, Hugh McCann, Chang Liu
Under review as a journal article at IEEE Transactions on Neural Networks and Learning Systems
EE 277 Fall 2021 (Instructor: Prof. Benjamin Van Roy), EE 236A Fall 2021