I’m Qisen Yang (杨琪森 in Chinese), a Ph.D. student at Tsinghua University, advised by Prof. Gao Huang and Prof. Shiji Song. My research interests include LLMs for social science, foundation models for decision making, offline reinforcement learning, interpretable RL, and efficient deep learning techniques.
🔥I’m on job market now!
🔥If you are interested in me, please contact me via yangqs19@mails.tsinghua.edu.cn.
Ph.D. Student in Artificial Intelligence, 2019 - Present
Tsinghua University
B.S. in Psychology, 2016 - 2019
Tsinghua University
B.E. in Precision Instrument, 2015 - 2019
Tsinghua University
We propose PsychoGAT (Psychological Game AgenTs) to transform standardized psychological scales into personalized and engaging interactive fiction games.
The commonly used action matching principle may lead to irrelevant or misplaced feature attribution when different DNNs’ outputs lead to the same rewards or different rewards result from the same outputs.
Compared to online fine-tuning, querying the preferences between pre-collected and learned actions can be equally or even more helpful to the erroneous estimate problem.
Responsibilities include:
I’m always open to exploring interesting ideas and collaborations!