AI RESEARCH
Deep Reinforcement Learning for Dynamic Origin-Destination Matrix Estimation in Microscopic Traffic Simulations Considering Credit Assignment
arXiv CS.LG
•
ArXi:2511.06229v2 Announce Type: replace This paper focuses on dynamic origin-destination matrix estimation (DODE), a crucial calibration process necessary for the effective application of microscopic traffic simulations. The fundamental challenge of the DODE problem in microscopic simulations stems from the complex temporal dynamics and inherent uncertainty of individual vehicle dynamics.