Jiayi Weng 翁家翌
trinkle23897 [at] gmail [dot] com
I'm currently an undergraduate researcher at TSAIL, working with Professor Hang Su and Jun Zhu in the field of Reinforcement Learning.
I'll graduate with a bachelor's degree from the Department of Computer Science and Technology, Tsinghua University in July 2020.
I have applied for up to 25 graduate programs, but only MCDS@CMU gave me an offer. All of Ph.D. programs and DRL professors rejected me, including Berkeley, CMU [1, 2, 3, 4, 5, 6, 7], MIT, Stanford, Mila, UW, UIUC, Princeton, Caltech, UMich, ETHz, Columbia, UCLA, UCSD, USC, UCI. So, in the future, I would like to dive into the industry. I'm looking for an internship in 2021 (which is mandatory in MCDS program), and if you are interested in working with me, please contact me through email.
I'm broadly interested in the problem of creating machines that exhibit intelligence, the hallmarks of which I consider to be adaptability, flexibility, and generality. In my exploration of this interest, I have studied and done research in reinforcement learning, computer vision, and natural language processing. I've had the fortune of participating in a range of interesting research projects with talented and patient collaborators.
For the summer of 2019, I was a visiting student researcher at the Montreal Institute for Learning Algorithms (MILA), where I worked with Professor Yoshua Bengio on the Consciousness Prior based on Transformer architecture. [Photo]
Prior to that, I worked on the reinforcement learning algorithm based on the VizDoom platform with Professor Hang Su and Jun Zhu in TSAIL. As the team leader, we proposed an environment-aware hierarchical reinforcement learning architecture and achieved first place in VizDoom AI Competition 2018 Single Player Track(1). I am also the main contributor of Tianshou, an elegant, flexible, and superfast PyTorch deep Reinforcement Learning platform .
Previously, I had experience in image denoising during my internship at Sensetime Inc., mentored by Hongwei Qin. My first research project was a rule-based escape routing problem working with Professor Hailong Yao.
Publications and/or Submitted Manuscripts
Playing FPS Game with Environment-aware Hierarchical Reinforcement Learning
Dong Yan, Haosheng Zou,
The 28th International Joint Conferences on Artificial Intelligence (IJCAI 2019). Oral Presentation.
URBER: Ultrafast Rule-Based Escape Routing Method for Large-Scale Sample Delivery Biochips
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2018.
Model-based Credit Assignment for Model-free Deep Reinforcement Learning
Submitted to IEEE Transactions on Neural Networks and Learning Systems (TNNLS).
I'm also engaged (but an amateur) in Photography / Computer Graphics / Web Security.