Coordinated Variable Speed Limit Control for Consecutive Bottlenecks on Freeways Using Multiagent Reinforcement Learning
Bibliographic record
Abstract
Most of the current variable speed limit (VSL) strategies are designed to alleviate congestion in relatively short freeway segments with a single bottleneck. However, in reality, consecutive bottlenecks can occur simultaneously due to the merging flow from multiple ramps. In such situations, the existing strategies use multiple VSL controllers that operate independently, without considering the traffic flow interactions and speed limit differences. In this research, we introduced a multiagent reinforcement learning-based VSL (MARL-VSL) approach to enhance collaboration among VSL controllers. The MARL-VSL approach employed a centralized training with decentralized execution structure to achieve a joint optimal solution for a series of VSL controllers. The consecutive bottleneck scenarios were simulated in the modified cell transmission model to validate the effectiveness of the proposed strategy. An independent single-agent reinforcement learning-based VSL (ISARL-VSL) and a feedback-based VSL (feedback-VSL) were also applied for comparison. Time-varying heterogeneous traffic flow stemming from the mainline and ramps was loaded into the freeway network. The results demonstrated that the proposed MARL-VSL achieved superior performance compared to the baseline methods. The proposed approach reduced the total time spent by the vehicles by 18.01% and 17.07% in static and dynamic traffic scenarios, respectively. The control actions of the MARL-VSL were more appropriate in maintaining a smooth freeway traffic flow due to its superior collaboration performance. More specifically, the MARL-VSL significantly improved the average driving speed and speed homogeneity across the entire freeway.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".