原文传递
A cold-start-free reinforcement learning approach for traffic signal control
| 题名： | A cold-start-free reinforcement learning approach for traffic signal control |
| 正文语种： | eng |
| 作者： | Nan Xiao;Liang Yu;Jinqiang Yu;Peng Chen;Yuehu Liu |
| 作者单位： | Alibaba Cloud Intelligence Alibaba Group;Alibaba Cloud Intelligence Alibaba Group;Alibaba Cloud Intelligence Alibaba Group;Alibaba Cloud Intelligence Alibaba Group;Alibaba Cloud Intelligence Alibaba Group |
| 关键词： | cold start;deep learning;model-based control;reinforcement learning;traffic signal control |
| 摘要： | Abstract Typical reinforcement learning (RL) requires a huge amount of data before achieving an acceptable result, and its performance can be rather poor during initial interacting process. Sample inefficiency and cold-start phenomenon of RL limits its feasibility in a range of real-world applications such as traffic signal control (TSC). On the other hand, a large amount of data on TSC can be accumulated by various model-based controllers (MBCs) rooted in traffic engineering. In this context, we propose a new RL approach which can avoid the appearance of cold starts by taking advantage of MBC experiences. First, three frameworks of joint utilization of RL and MBC are summarized for TSC, and staged framework is considered to have the edge over the other two. Then, a staged noisy-net prioritized dueling double deep Q-network (NPDD-DQN) is described in detail for TSC, where MBC experiences are used in both pre-training and online training processes. Experimental evaluation demonstrates that staged NPDD-DQN can achieve a boost in initial performance as compared to pure NPDD-DQN that does not utilize any control experiences, and learn to improve final performance beyond the underlying MBC. The effectiveness of the proposed method opens up the possibility of real implementation of RL in TSC. |
| 出版年： | 2022 |
| 期刊名称： | Journal of Intelligent Transportation Systems |
| 卷： | 26 |
| 期： | 1/6 |
| 页码： | 481-490 |
相关文献
- An Attention Reinforcement Learning-Based Strategy for Large-Scale Adaptive Traffic Signal Control System
- Asynchronous n-step Q-learning adaptive traffic signal control
- Network-wide traffic signal control based on the discovery of critical nodes and deep reinforcement learning
- Artificial intelligence for traffic signal control based solely on video images
- Learning based Traffic Signal Control Algorithms with Neighborhood Information Sharing: An Application for Sustainable Mobility
- Optimizing multi-agent based urban traffic signal control system
检索历史
应用推荐
