Enhancing Traffic Signal Control through Model-based Reinforcement Learning and Policy Reuse
This work addresses the adaptability issue in traffic signal control for urban traffic management, offering a solution to reduce retraining costs and improve deployment efficiency, though it is incremental in nature.
The paper tackled the problem of insufficient generalization in multi-agent reinforcement learning for traffic signal control by proposing PLight and PRLight algorithms, which use model-based reinforcement learning and policy reuse to adapt to new traffic scenarios, reducing adaptation time significantly compared to learning from scratch.
Multi-agent reinforcement learning (MARL) has shown significant potential in traffic signal control (TSC). However, current MARL-based methods often suffer from insufficient generalization due to the fixed traffic patterns and road network conditions used during training. This limitation results in poor adaptability to new traffic scenarios, leading to high retraining costs and complex deployment. To address this challenge, we propose two algorithms: PLight and PRLight. PLight employs a model-based reinforcement learning approach, pretraining control policies and environment models using predefined source-domain traffic scenarios. The environment model predicts the state transitions, which facilitates the comparison of environmental features. PRLight further enhances adaptability by adaptively selecting pre-trained PLight agents based on the similarity between the source and target domains to accelerate the learning process in the target domain. We evaluated the algorithms through two transfer settings: (1) adaptability to different traffic scenarios within the same road network, and (2) generalization across different road networks. The results show that PRLight significantly reduces the adaptation time compared to learning from scratch in new TSC scenarios, achieving optimal performance using similarities between available and target scenarios.