Wang Kaixin

I am a postdoctoral researcher in Prof. Shie Mannor's group at Technion. Previously, I finished my PhD study in Institute of Data Science at National University of Singapore, fortunately supervised by Prof. Bryan Hooi, Dr. Jiashi Feng and Prof. Xinchao Wang. Even earlier, I spent my undergraduate years at Nanjing University.

I am broadly interested in topics in (deep) reinforcement learning, such as state/action representation, exploration and generalization. I particularly enjoy doing research that answers an interesting question or resolves an open issue. Feel free to contact me for discussion or collaboration!

 /  CV  /   / 

profile photo
Selected Research Works (Full List)
Reachability-Aware Laplacian Representation in Reinforcement Learning
Kaixin Wang*, Kuangqi Zhou*, Jiashi Feng, Bryan Hooi, Xinchao Wang
ICML, 2023
The Geometry of Robust Value Functions
Kaixin Wang, Navdeep Kumar, Kuangqi Zhou, Bryan Hooi, Jiashi Feng, Shie Mannor
ICML, 2022
arXiv  /  presentation
Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawing
Kaixin Wang*, Kuangqi Zhou*, Qixin Zhang, Jie Shao, Bryan Hooi, Jiashi Feng
ICML, 2021
arXiv  /  code (coming soon)  /  presentation

Academic Services Volunteer Reviewer Top reviewer
  • AAAI: 2023 ()
  • ICLR: 2020 () , 2021 () , 2022 () , 2023 ()
  • ICML: 2020 () , 2021 ( ) , 2022 ()
  • NeurIPS: 2020 () , 2021 ()
  • IEEE Transactions on Pattern Analysis and Machine Intelligence ()
  • Transactions on Machine Learning Research ()
  • IEEE Transactions on Image Processing ()
  • IEEE Transactions on Multimedia ()
  • Machine Vision and Applications ()
My Academic Toolbox
  • 🎨 (now A very powerful yet easy-to-use tool for creating diagrams / plots.
  • 💿 PaperMemory: A handy browser extension to store papers I read, and much more.
  • 📐 GeoGebra: A nice tool for interactive visualization of 2D/3D geometry.
  • LaTeXiT: A handy equation editor when I do need LaTex rather than MathJax (e.g., using euscript font).

This page is forked from here 🚀