MTLight: Efficient Multi-Task Reinforcement Learning for Traffic Signal Control
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916186957021184 |
|---|---|
| author | Zhu, Liwen Peng, Peixi Lu, Zongqing Tian, Yonghong |
| author_facet | Zhu, Liwen Peng, Peixi Lu, Zongqing Tian, Yonghong |
| contents | Traffic signal control has a great impact on alleviating traffic congestion in modern cities. Deep reinforcement learning (RL) has been widely used for this task in recent years, demonstrating promising performance but also facing many challenges such as limited performances and sample inefficiency. To handle these challenges, MTLight is proposed to enhance the agent observation with a latent state, which is learned from numerous traffic indicators. Meanwhile, multiple auxiliary and supervisory tasks are constructed to learn the latent state, and two types of embedding latent features, the task-specific feature and task-shared feature, are used to make the latent state more abundant. Extensive experiments conducted on CityFlow demonstrate that MTLight has leading convergence speed and asymptotic performance. We further simulate under peak-hour pattern in all scenarios with increasing control difficulty and the results indicate that MTLight is highly adaptable. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_00886 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MTLight: Efficient Multi-Task Reinforcement Learning for Traffic Signal Control Zhu, Liwen Peng, Peixi Lu, Zongqing Tian, Yonghong Artificial Intelligence Traffic signal control has a great impact on alleviating traffic congestion in modern cities. Deep reinforcement learning (RL) has been widely used for this task in recent years, demonstrating promising performance but also facing many challenges such as limited performances and sample inefficiency. To handle these challenges, MTLight is proposed to enhance the agent observation with a latent state, which is learned from numerous traffic indicators. Meanwhile, multiple auxiliary and supervisory tasks are constructed to learn the latent state, and two types of embedding latent features, the task-specific feature and task-shared feature, are used to make the latent state more abundant. Extensive experiments conducted on CityFlow demonstrate that MTLight has leading convergence speed and asymptotic performance. We further simulate under peak-hour pattern in all scenarios with increasing control difficulty and the results indicate that MTLight is highly adaptable. |
| title | MTLight: Efficient Multi-Task Reinforcement Learning for Traffic Signal Control |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2404.00886 |