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 interpretable and scalable policy learning frameworks.

Education

• B.S., Management Science and Engineering, Tongji University, 2021
• B,S.(Minor Degree), Law, Fudan University, 2021
• Ph.D, Industrial System and Engineering, National University of Singapore, 2026 (pending defense)

Publication

• Yang, S. and Liu, Y., 2024. Markov Game for CV Joint Adaptive Routing in Stochastic Traffic Networks: A Scalable Learning Approach, Transportation Research Part B: Methodological, 189, 102997.
• Wang, J., Wang, X.L., Yang, S., Yang, H., Zhang, X.N. and Gao, Z.Y., 2021. Predicting the matching probability and ride/shared distance for each dynamic ridepooling order: A mathematical modeling approach. Transportation Research Part B 154, 125-146.

Remark: Transportation Research Part B is a top-2 journal in transportation theory.

Papers Under Review

• Yang S. and Liu Y., Descent-Guided Policy Gradient for Scalable Cooperative Multi-Agent Learning, under review at NeurIPS.
• Yang S., Feng Y., Wang X.L., Liu Y., Designing a Forward-Looking Probabilistic Matching Policy for Dynamic Ridepooling Service, R&R at Manufacturing & Service Operations Management (utd24).
• Yang S., Zhong L.H., Liu Y., Model-Supplementary Learning for Congestion Pricing: A Bias-Aware Natural Policy Gradient Approach, accepted by ISTTT26, selected for publishing in Transportation Research series.

Working Papers

• Yang S., Mean-Field Reinforcement Learning without Synchrony.
• Yang S., Wang X.L., Liu Y. Scalable decision-making for networked urban mobility via hierarchical action beliefs.
• Yang S., Liu Y. Learn to Desseminate Personalized Information to Vehicles in Stochastic Traffic Networks.

Conference Proceeding

• Yang S., Liu Y., 2024. Markov Game for CV Joint Adaptive Routing in Stochastic Traffic Networks: A Scalable Learning Approach. The 25nd International Symposium on Transportation and Traffic Theory.

Remark: ISTTT is the prestigious gathering for the world’s transportation and traffic theorists, regular acceptance rate: 10%.

Academic Services

Reviwer, The 22nd COTA International Conference of Transportation Professionals (CICTP 2022)

Honors

• NUS Research Scholarship, 2022
• National First Prize, China Contemporary Undergraduate Mathematical Contest in Modeling, 2020
• Kaisa Innovation and Entrepreneurship Scholarship of Tongji University, 2019
• Second Prize in Shanghai, “Internet+” Innovation and Entrepreneurship Competition, 2017