MaCAR: Urban Traffic Light Control via Active Multi-agent Communication and Action Rectification
Authors: Zhengxu Yu, Shuxian Liang, Long Wei, Zhongming Jin, Jianqiang Huang, Deng Cai, Xiaofei He, Xian-Sheng Hua
IJCAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In experiments, we show that our proposal can outperforms state-of-the-art methods on both synthetic and real-world datasets. |
| Researcher Affiliation | Collaboration | 1State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China 2Computer Science Department, Zhejiang University, Hangzhou, China 3DAMO Academy, Alibaba Group, Hangzhou, China 4Fabu Inc., Hangzhou, China |
| Pseudocode | Yes | Algorithm 1 Online Training algorithm |
| Open Source Code | No | The paper mentions "open-source traffic simulators: City Flow 1 and SUMO 2" with links to their respective GitHub pages, but does not provide a link or explicit statement about the availability of the source code for the Ma CAR framework described in the paper. |
| Open Datasets | Yes | We used three real-world datasets: DHangzhou, DJinan and DNew York. All three datasets are obtained from Co Light [Wei et al., 2019b]. |
| Dataset Splits | No | The paper mentions a "training interval M" but does not explicitly define training, validation, and test dataset splits by percentage, sample count, or by referencing predefined splits with specific details. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware (e.g., CPU, GPU models, memory) used to run the experiments. |
| Software Dependencies | No | The paper mentions using "City Flow" and "SUMO" simulators but does not provide specific version numbers for these or any other software libraries or dependencies used. |
| Experiment Setup | No | The paper mentions general parameters like "period length P" and "training interval M" and states "We followed the experimental setup used by Co Light", but it does not provide specific hyperparameter values (e.g., learning rate, batch size, number of epochs) or other detailed configuration settings for the experiments within the main text. |