Deep Reinforcement Learning for Dynamic Origin-Destination Matrix Estimation in Microscopic Traffic Simulations Considering Credit Assignment

TL;DR

This paper introduces a deep reinforcement learning framework to estimate dynamic origin-destination matrices in microscopic traffic simulations, effectively addressing the credit assignment problem and improving accuracy over traditional methods.

Contribution

It formulates the DODE problem as an MDP and applies model-free DRL to learn optimal OD matrices, a novel approach in microscopic traffic simulation calibration.

Findings

Reduces mean squared error by over 20% compared to baseline.

Addresses credit assignment through learned policy in DODE.

Validates approach on real highway network case study.

Abstract

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. This makes it highly challenging to precisely determine which vehicle traverses which link at any given moment, resulting in intricate and often ambiguous relationships between origin-destination (OD) matrices and their contributions to resultant link flows. This phenomenon constitutes the credit assignment problem, a central challenge addressed in this study. We formulate the DODE problem as a Markov Decision Process (MDP) and propose a novel framework that applies model-free deep reinforcement learning (DRL). Within our proposed framework, the agent learns an optimal policy to sequentially generate OD matrices, refining its strategy through direct interaction with the simulation environment. This approach was evaluated through a toy experiment on the Nguyen-Dupuis network and a case study utilizing an actual highway subnetwork spanning Santa Clara and San Jose. Experimental results demonstrate that our approach reduces the mean squared error (MSE) by over 20% compared to the best-performing conventional baseline. By reframing DODE as a sequential decision-making problem, our approach addresses the credit assignment challenge through its learned policy, thereby overcoming the limitations of conventional methods and proposing a novel framework for calibration of microscopic traffic simulations.