DynamicLight: Two-Stage Dynamic Traffic Signal Timing
This addresses traffic congestion by improving signal timing adaptability, though it is incremental as it builds on existing RL methods.
The paper tackles the inflexibility of single-stage reinforcement learning for traffic signal control by introducing DynamicLight, a two-stage framework that separately optimizes phase selection and duration, resulting in outperforming state-of-the-art models with demonstrated generalization and robustness.
Reinforcement learning (RL) is gaining popularity as an effective approach for traffic signal control (TSC) and is increasingly applied in this domain. However, most existing RL methodologies are confined to a single-stage TSC framework, primarily focusing on selecting an appropriate traffic signal phase at fixed action intervals, leading to inflexible and less adaptable phase durations. To address such limitations, we introduce a novel two-stage TSC framework named DynamicLight. This framework initiates with a phase control strategy responsible for determining the optimal traffic phase, followed by a duration control strategy tasked with determining the corresponding phase duration. Experimental results show that DynamicLight outperforms state-of-the-art TSC models and exhibits exceptional model generalization capabilities. Additionally, the robustness and potential for real-world implementation of DynamicLight are further demonstrated and validated through various DynamicLight variants. The code is released at https://github.com/LiangZhang1996/DynamicLight.