Deep Reinforcement Learning Two-Way Transit Signal Priority Algorithm for Optimizing Headway Adherence and Speed
Bibliographic record
Abstract
Transit Signal Priority (TSP) is a broadly used traffic signal control strategy designed for reducing transit delays at signalized intersections. Although recent TSP systems began to consider more objectives, TSPs that addressed transit reliability issues commonly focused on improving schedule adherence and were only able to reduce schedule delays by expediting buses. Buses running ahead of the schedule were not considered. This paper proposed a dual-objective two-way TSP algorithm (D2 TSP) using Deep Reinforcement Learning (DRL). D2 TSP concurrently optimizes transit delays and reliability (i.e., headway adherence) by expediting late buses or delaying early buses. Further, the DRL agents were enhanced with a coordination algorithm for an optimized solution balancing opposite directions. This D2 TSP reacts adaptively and efficiently to real-time bus performance using data provided by readily available technology (loop detector) at low communication frequencies. We trained and tested this algorithm in a stochastic microsimulation environment in Aimsun Next that modelled a transit route segment with reliability issues in the City of Toronto. The performance of D2 TSP was compared with four baseline scenarios, one without TSP, one with the current TSP algorithm used in the field in the City of Toronto, one conditional TSP with an arrival prediction model, and one using DRL agents with a First-Come-First-Served logic. D2 TSP demonstrated its advantages in providing an efficient and balanced solution in reducing headway variability and travel time for both directions.
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".