YANG Shan

Research Fellow at the National University of Singapore

Reinforcement Learning Game Theory Optimization

I am YANG Shan (羊山), a Research Fellow at the National University of Singapore (NUS). I am dedicated to developing intelligent decision-making and modeling methods for complex systems, focusing on the integration of reinforcement learning and optimization theory to create scalable, reliable, and interpretable learning methods. I am particularly interested in complex systems in transportation and energy.

Selected Publications

Arxiv Online

Teaching Agents the “Principle”, Not the “Reward”

Website

Shan Yang

Learning Methods and Theory

Website
ICLR Under Review

Descent-Guided Policy Gradient for Scalable Cooperative Multi-Agent Learning

Tutorial

Shan Yang and Yang Liu

Under review at ICLR

Learning Methods and Theory Code

Tutorial
Arxiv Online

Mean-Field Reinforcement Learning without Synchrony

Tutorial

Shan Yang

Learning Methods and Theory

Tutorial
TR-B/ISTTT

Markov Game for CV Joint Adaptive Routing in Stochastic Traffic Networks: A Scalable Learning Approach

Tutorial

Shan Yang and Yang Liu

Transportation Research Part B: Methodological (ISTTT Special Issue), 2024

Learning Methods and Theory

Tutorial

Latest Posts

November 2026	Prescriptive Policy Learning: Interactive Visualizations and Tutorials
November 2026	Decision for Complex Systems: Interactive Visualizations of AI Decision-Making
August 2026	Why Do We Need Analytical Models to Guide Training for Cooperative Multi-Agent Learning?

News

Nov 09, 2026	Launched Prescriptive Policy Learning, interactive visualizations and tutorials with training code.
Nov 09, 2026	Launched Decision for Complex Systems, interactive visualizations of AI decision-making in large systems.
Jun 16, 2026	Thrilled to share that I successfully defended my Ph.D. thesis at the National University of Singapore! 🎓