Traffic Optimization for a Mixture of Self-Interested and Compliant Agents
Authors: Guni Sharon, Michael Albert, Tarun Rambha, Stephen Boyles, Peter Stone
AAAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results are presented showing that in several large-scale, realistic traffic networks optimal flow can be achieved with as low as 13% of the agent being compliant and up to 54%. Experimental Results We are interested in the viability of opt-in micro-tolling schemes to more efficiently utilize road networks. As such, we have undertaken an empirical study to investigate the minimal amount of compliant flow required for SO (r UE) in six realistic traffic scenarios over actual road networks. |
| Researcher Affiliation | Academia | 1Department of Computer Science, University of Texas at Austin, Austin, TX 78712, USA 2Department of Computer Science, Duke University, Durham, NC 27708, USA 3Civil and Environmental Engineering, Cornell University, Ithaca, NY 14853, USA 4Civil, Architectural and Environmental Engineering, The University of Texas at Austin, Austin, TX 78712, USA |
| Pseudocode | No | The paper describes methods and references algorithms (e.g., 'algorithm B') but does not provide any structured pseudocode or algorithm blocks within its text. |
| Open Source Code | No | The paper provides a link for 'traffic scenarios' (datasets) at 'https://github.com/bstabler/ Transportation Networks' but does not explicitly state that the source code for the methodology described in this paper is openly available or provide a link to it. |
| Open Datasets | Yes | All traffic scenarios are available at: https://github.com/bstabler/ Transportation Networks. The following benchmark scenarios were chosen both for their diversity of topology and traffic volume and their widespread use within the traffic literature: Sioux Falls, Eastern Massachusetts, Anaheim, Chicago Sketch, Philadelphia, and Chicago-regional. |
| Dataset Splits | No | The paper describes using six benchmark traffic scenarios and a macroscopic model to evaluate traffic formation and compute solutions, but it does not specify any training, validation, or test dataset splits in the conventional sense needed to reproduce data partitioning for typical machine learning experiments. Instead, it seems to simulate on the entire defined network instances. |
| Hardware Specification | No | The paper does not provide any specific details regarding the hardware (e.g., GPU models, CPU types, memory) used for running the experiments. |
| Software Dependencies | No | The paper mentions algorithms ('algorithm B') and mathematical functions ('Bureau of Public Roads (BPR) function') and computational methods ('linear program'), but it does not specify any software dependencies with version numbers (e.g., Python 3.8, PyTorch 1.9, CPLEX 12.4) that would be needed to replicate the experiments. |
| Experiment Setup | Yes | For all scenarios, the model assumed that travel times follow the Bureau of Public Roads (BPR) function (Moses and Mtoi 2017) with the commonly used parameters β = 4, α = 0.15. The algorithm terminates when the AEC is less than 1E-12 minutes (except for Chicago-regional for which 1E-10 was used due to the size of the network). |