Paper ID: 2411.06601

OffLight: An Offline Multi-Agent Reinforcement Learning Framework for Traffic Signal Control

Rohit Bokade, Xiaoning Jin

Efficient traffic signal control is critical for modern urban mobility, but traditional systems often struggle to adapt to complex city traffic patterns. Multi-Agent Reinforcement Learning, or MARL, offers adaptive solutions, yet online MARL methods require extensive real-time interactions, which are costly and time-intensive. Offline MARL addresses these issues by using historical traffic data, but it faces challenges due to the diverse behavior policies in real-world datasets, where different controllers complicate learning.

Submitted: Nov 10, 2024