Unicorn: A Universal and Collaborative Reinforcement Learning Approach Towards Generalizable Network-Wide Traffic Signal Control

Researchers have developed Unicorn, a universal reinforcement learning framework for adaptive traffic signal control that addresses challenges in heterogeneous urban traffic networks. The system uses collaborative multi-agent reinforcement learning with unified mapping and specialized representation modules to optimize traffic flow across diverse intersection topologies.

• →Unicorn introduces a universal MARL framework that can adapt to different intersection topologies and traffic dynamics in real-world networks.
• →The system uses a Universal Traffic Representation module with decoder-only architecture for general feature extraction across diverse scenarios.
• →An Intersection Specifics Representation module employs variational inference to capture unique intersection characteristics.
• →Contrastive learning in a self-supervised manner helps differentiate intersection-specific features for better optimization.
• →The framework integrates neighboring agent interactions into policy optimization for improved regional collaboration.