Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2022
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2211.01025 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914779452407808 |
|---|---|
| author | Zhang, Liang Zhang, Yutong Xie, Shubin Deng, Jianming Li, Chen |
| author_facet | Zhang, Liang Zhang, Yutong Xie, Shubin Deng, Jianming Li, Chen |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2211_01025 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | DynamicLight: Two-Stage Dynamic Traffic Signal Timing Zhang, Liang Zhang, Yutong Xie, Shubin Deng, Jianming Li, Chen Machine Learning Artificial Intelligence 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. |
| title | DynamicLight: Two-Stage Dynamic Traffic Signal Timing |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2211.01025 |