Xiaolin Sun

Xiaolin Sun

PhD Candidate

Tulane University

Biography

Xiaolin Sun is a forth year PhD Candidate advised by Dr.Zizhan Zheng at Computer Science Department of Tulane University. His research interests include Reinforcement Learning, Multi-agent Reinforcement Learning and Robust Reinforcement Learning.

Interests
  • Reinforcement Learning
  • Adversarial Machine Learning
  • Multi-agent Learning
Education
  • PhD Candidate in Computer Science, 2020-Present

    Tulane University

  • Bachelor of Arts in Mathematical Economics and Computer Science, 2016-2020

    Colgate University

Skills

Technical
Python
Pytorch
Hobbies
Photography
Computer Hardwares

Experience

 
 
 
 
 
Research Assistant
Colgate University
May 2018 – August 2020 Hamilton, NY
I worked as a research assistant for Prof. Gember-Jacobson. The project aims at developing a tool that can automatically detect the errors in router configurations that cause the policies violation in a network by using SMT solver to get unsatisfiable cores.
 
 
 
 
 
Teaching Assistant
Tulane University
September 2020 – September 2021 New Orleans, LA
Holding Lab sessions and office hours for Intro to Computer Science and Computer Organizations courses
 
 
 
 
 
Research Assistant
Tulane University
September 2021 – Present New Orleans, LA
I worked as a research assistant for Prof.Zizhan Zheng. I have worked projects on multi-agent reinforcement learning and robust reinforcement learning.

Recent Publications

Quickly discover relevant content by filtering publications.
(2024). Belief-Enriched Pessimistic Q-Learning against Adversarial State Perturbations. The Twelfth International Conference on Learning Representations (ICLR 2024).

Cite Paper Code

(2023). Does Delegating Votes Protect Against Pandering Candidates?. Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems (AAMAS) (Extended Abstract).

Cite Paper Code

(2023). Pandering in a (flexible) representative democracy. Uncertainty in Artificial Intelligence (UAI).

Cite Paper Code

(2023). Robust Q-Learning against State Perturbations: a Belief-Enriched Pessimistic Approach. Multi-Agent Security Workshop @ NeurIPS'23.

Cite URL

(2022). Learning to attack federated learning: A model-based reinforcement learning attack framework. Advances in Neural Information Processing Systems (NeurIPS).

Cite Paper Code