Kun Lei

I am a first-year CS Ph.D. student at Washington University in St. Louis. Prior to this, I worked as a research assistant at Shanghai Qizhi institute, where I am fortunate to work with Prof. Huazhe Xu at Tsinghua University. I also did my research internship for four months at Westlake University. Previously, I graduated from Southwest Jiaotong University, where I fortunately worked with Prof. Peng Guo at SWJTU and Prof. Yi Wang at Auburn University.

Research interest

I am interested in research on the sample efficiency and adaptation capabilities of deep reinforcement learning algorithms and agents. My research objective is to create reliable, robust, and efficient algorithms to tackle a diverse range of sequential decision-making problems in real-world scenarios.

I am currently focused on the post-training of robotics (foundation) models to enhance specific objectives such as task acceleration, precision, adaptation [3⬆️], and/with safety considerations [2⬆️].

Previously, I conducted research on neural solvers for combinatorial optimization problems, i.e., in the field of AI for Operations Research. These neural agents have the potential to solve NP-hard problems with linear time complexity, see Zhihu.

Publications and preprints (Offline & online RL algorithms and robotics)

Papers sorted by recency, * indicates equal contribution.

Publications and preprints (RL for Operations Research)

Papers sorted by recency.

Misc. open-source projects

I am from Si Chuan, China. My name in chinese is 雷坤. I used to live in the charming cities of Chengdu and Hangzhou in China. Currently, I live in the vibrant city of Shanghai (as depicted in the background picture).