Reinforcement Learning Approaches for Traffic Signal Control under Missing Data
Authors: Hao Mei, Junxian Li, Bin Shi, Hua Wei
IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Through extensive experiments on both synthetic and real-world road network traffic, we reveal that our method outperforms conventional approaches and performs consistently with different missing rates. We also investigate how missing data influences the performance of our model. |
| Researcher Affiliation | Academia | 1 New Jersey Institute of Technology 2 Xi an Jiaotong University 3 Arizona State University |
| Pseudocode | Yes | Algorithm 1: Algorithm for Remedy 2.3 SDQNSDQN (model-based) with imaginary rollout |
| Open Source Code | Yes | 1The code and dataset can be found on the authors website. |
| Open Datasets | Yes | Datasets. We testify our two approaches on TSC task under missing data on a synthetic dataset and two real-world datasets 1. DSY N is a synthetic dataset generated by City Flow [Zhang et al., 2019], an open-source microscopic traffic simulator. ... DHZ is a public traffic dataset that recorded a 4 4 network at Hangzhou in 2016. ... DNY is a public traffic dataset collected in New York City within 16 3 intersections. 1The code and dataset can be found on the authors website. |
| Dataset Splits | Yes | The training samples are collected from observed intersections and divided into 80% and 20% for training and testing. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory specifications) used for running the experiments. |
| Software Dependencies | No | The paper mentions software like City Flow, but does not provide specific version numbers for any software dependencies or libraries used in the experiments. |
| Experiment Setup | Yes | RL settings. We follow the past work [Wei et al., 2019b; Wu et al., 2021; Huang et al., 2021] to set up the RL environment, and details on the state, reward, and action definition can be found in Sec. 3. We take exploration rate ϵ = 0.1, discount factor γ = 0.95, minimum exploration rate ϵmin = 0.01, exploration decay rate ϵdecay = 0.995, and model learning rate r = 0.0001. |