DreamerV3 for Traffic Signal Control: Hyperparameter Tuning and Performance
This is an incremental application of an existing method to a new domain (traffic signal control), with limited practical impact due to mixed results on data-efficiency.
The paper applied the DreamerV3 reinforcement learning algorithm to traffic signal control, finding that smaller model sizes and medium training ratios reduce hyperparameter tuning time, but data-efficiency claims were only modestly supported with larger models showing some benefit.
Reinforcement learning (RL) has evolved into a widely investigated technology for the development of smart TSC strategies. However, current RL algorithms necessitate excessive interaction with the environment to learn effective policies, making them impractical for large-scale tasks. The DreamerV3 algorithm presents compelling properties for policy learning. It summarizes general dynamics knowledge about the environment and enables the prediction of future outcomes of potential actions from past experience, reducing the interaction with the environment through imagination training. In this paper, a corridor TSC model is trained using the DreamerV3 algorithm to explore the benefits of world models for TSC strategy learning. In RL environment design, to manage congestion levels effectively, both the state and reward functions are defined based on queue length, and the action is designed to manage queue length efficiently. Using the SUMO simulation platform, the two hyperparameters (training ratio and model size) of the DreamerV3 algorithm were tuned and analyzed across different OD matrix scenarios. We discovered that choosing a smaller model size and initially attempting several medium training ratios can significantly reduce the time spent on hyperparameter tuning. Additionally, we found that the approach is generally applicable as it can solve two TSC task scenarios with the same hyperparameters. Regarding the claimed data-efficiency of the DreamerV3 algorithm, due to the significant fluctuation of the episode reward curve in the early stages of training, it can only be confirmed that larger model sizes exhibit modest data-efficiency, and no evidence was found that increasing the training ratio accelerates convergence.