About Me

I am a Postdoctoral Research Associate in the Department of Mathematics at the University of Oxford, and a member of the Erlangen AI Hub. I completed my Ph.D. in Industrial Engineering & Operations Research at UC Berkeley in Summer 2025, advised by Professor Xin Guo. Prior to pursuing Ph.D., I earned a B.S. degree in Mathematics at New York University Shanghai in 2020.

My research interests are at the intersection of stochastic control, reinforcement learning, game theory, and machine learning. More specifically, my research tries to address the following challenges:

• Curse of Many Agents in Stochastic Dynamic Systems:
  Many systems are inherently stochastic and dynamic, and involve multiple agents that interact with each other. To address this, we develop a game-theoretic framework called α-potential games, employing stochastic control approaches and designing multi-agent reinforcement learning (MARL) algorithms for equilibrium analysis and policy learning.

• Lack of Generalizability and Robustness:
  Learned policies and models may fail to generalize to new tasks or withstand adversarial perturbations. Our work studies transfer learning in reinforcement learning (RL) to enable efficient knowledge transfer across related tasks. In parallel, we study machine learning (ML) with adversarial attacks to investigate the robustness and model stability.

• Inefficient Feature Identification in Data Streams:
  Decision-making in high-dimensional systems with limited data remains a major challenge. We address this by exploring rough path methods to extract features from data streams, combining them with ML models for improved prediction and decision-making.

Please find my [CV] here.

Email: xinyu.li@maths.ox.ac.uk, xinyu_li@berkeley.edu

Publications

• X Guo, X Li, Y Zhang, Distributed Games with Jumps: an α-Potential Game Approach, preprint, Minor Revision at Mathematical Finance, 2026 [arXiv] [code]

• X Guo, X Li, and R Xu, Fast Policy Learning for Linear Quadratic Regulator with Entropy Regularization, SIAM Journal on Control and Optimization, 2026 [arXiv] [Journal]

• X Li, An α-Potential Game Framework for Non-Cooperative Dynamic Games: Theory and Algorithms, 2025. University of California, Berkeley, PhD dissertation [pdf]

• X Guo, X Li, Y Zhang, An α-Potential Game Framework for N-player Games, SIAM Journal on Control and Optimization, 2025 [arXiv] [Journal]

• X Guo, X Li, C Maheshwari, S Sastry, and M Wu, Markov α-Potential Games, IEEE Transactions and Control, 2025 [arXiv] [Journal]

• H Gu, X Guo, TL Jacobs, P Kaminsky, and X Li, Transportation Market Rate Forecast Using Signature Transform, KDD, 2024 [Conference Version]
  INFORMS Journal of Applied Analytics, 2025 [Journal] [arXiv]
  Finalist for the 2024 Daniel H. Wagner Prize
  

• H Gu, X Guo, and X Li, Adversarial Training for Gradient Descent: Analysis Through its Continuous-time Approximation, Revision at Applied Probability Journals, 2025 [arXiv]

• Z Zong, X Li, and P Sanaei, Effects of nutrient depletion on tissue growth in a tissue engineering scaffold pore, Physics of Fluids, 2021 [Journal]

Recent Honors & Awards

• Finalist, INFORMS Daniel H. Wagner Prize for Excellence in the Practice of Advanced Analytics and Operations Research, 2024
• Berkeley Marshall-Oliver-Rosenberger Fellowship, 2024

Talks

• Stochastic Finance Seminar, The University of Warwick, Coventry, UK, 2025
• PGMODAYS, EDF Lab Paris-Saclay, Palaiseau, France, 2025
• Bridging Stochastic Control and Reinforcement Learning: Theories and Applications, Newton Institute, Cambridge, UK, 2025
• 2025 INFORMS Annual Meeting, Atlanta, GA, 2025
• Oxford Mathematical and Computational Finance Seminar, University of Oxford, Oxford, UK, 2025
• Machine Learning and Data Science Seminar, University of Oxford, Oxford, UK, 2025
• Erlangen AI Hub Seminar, University of Oxford, Oxford, UK, 2025
• Oxford–Princeton Workshop on Stochastic Analysis and Mathematical Finance, University of Oxford, Oxford, UK, 2025
• SIAM Conference on Financial Mathematics and Engineering (FM25), Miami, FL, 2025
• Advances in Stochastic Control and Reinforcement Learning, Banff, Canada, 2025
• 2025 Western Conference on Mathematical Finance, USC, CA, 2025
• INFORMS 2024, Seattle, WA, 2024
• DIMACS 2024 Workshop on Forecasting, Rutgers University, NJ, 2024
• Joint Statistical Meetings, Portland, OR, 2024
• Banff International Station, Canada, 2024 (Online)
• Cyber Risk and Insurance France-Berkeley Conference, UC Berkeley, CA, 2024
• 58th Annual Conference on Information Sciences and Systems, Princeton University, NJ, 2024
• 4th ACM International Conference on AI in Finance, NY, 2023
• 10th International Congress on Industrial and Applied Mathematics, Waseda University, Tokyo, Japan, 2023 (Online)
• INFORMS 2023, Phoenix, AZ, 2023
• Berkeley-Columbia Workshop, Columbia University, NY, 2023
• Western Conference on Mathematical Finance, UC Berkeley, CA, 2023

Teaching Experience

Graduate Student Instructor, UC Berkeley

• IEOR 221 — Introduction to Financial Engineering, Spring 2025
• IEOR 221 — Introduction to Financial Engineering, Spring 2024
• IEOR 222 — Financial Engineering Systems I, Spring 2023
• IEOR 242 — Applications in Data Analysis, Spring 2022
• IEOR 142 — Applications in Data Analysis, Spring 2021

Professional Service

Reviewer

• Journal of Machine Learning Research
• SIAM Journal on Control and Optimization
• Applied Mathematics and Optimization
• SIAM Journal on Applied Mathematics
• Journal of Applied Probability
• Mathematical Finance
• Applied Mathematical Finance
• Finance & Stochastics
• IEEE Transactions on Human-Machine Systems
• NeurIPS 2025 GenAI in Finance Workshop

Organizer

• Co-organizer of the workshop Reinforcement Learning for Science: Discovery and Automation
  at the Isaac Newton Institute Satellite Program (March 2026)

Industrial Experience

• Research Scientist Intern, Amazon, Middle Mile Product & Technology (Santa Clara, CA) May 2023 - Aug 2023
• Research Scientist Intern, Amazon, Middle Mile Product & Technology (Santa Clara, CA) May 2022 - December 2022