Learning Phase Competition for Traffic Signal Control
| Autor: | Hua Wei, Yuanhao Xiong, Guanjie Zheng, Xinshi Zang, Kai Xu, Yong Li, Huichu Zhang, Jie Feng, Zhenhui Li |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computer science Computer Science - Artificial Intelligence Control (management) Machine Learning (stat.ML) 02 engineering and technology Machine learning computer.software_genre Machine Learning (cs.LG) Competition (economics) Statistics - Machine Learning 0502 economics and business 0202 electrical engineering electronic engineering information engineering Selection (linguistics) Reinforcement learning 050210 logistics & transportation business.industry 05 social sciences Work (physics) Traffic flow Artificial Intelligence (cs.AI) 020201 artificial intelligence & image processing Artificial intelligence business computer Rotation (mathematics) |
| Zdroj: | CIKM |
| Popis: | Increasingly available city data and advanced learning techniques have empowered people to improve the efficiency of our city functions. Among them, improving the urban transportation efficiency is one of the most prominent topics. Recent studies have proposed to use reinforcement learning (RL) for traffic signal control. Different from traditional transportation approaches which rely heavily on prior knowledge, RL can learn directly from the feedback. On the other side, without a careful model design, existing RL methods typically take a long time to converge and the learned models may not be able to adapt to new scenarios. For example, a model that is trained well for morning traffic may not work for the afternoon traffic because the traffic flow could be reversed, resulting in a very different state representation. In this paper, we propose a novel design called FRAP, which is based on the intuitive principle of phase competition in traffic signal control: when two traffic signals conflict, priority should be given to one with larger traffic movement (i.e., higher demand). Through the phase competition modeling, our model achieves invariance to symmetrical cases such as flipping and rotation in traffic flow. By conducting comprehensive experiments, we demonstrate that our model finds better solutions than existing RL methods in the complicated all-phase selection problem, converges much faster during training, and achieves superior generalizability for different road structures and traffic conditions. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|