An enhanced approximate dynamic programming approach to on-demand ride-Pooling
Bibliographic record
Abstract
Ride-pooling services have been growing in popularity, increasing the need for efficient and effective operations. The main goal of ride-pooling services is to maximise the number of passengers served while limiting wait and delay times. However, factors such as the timing and volume of passenger requests, pick-up and drop-off locations, available vehicle capacity, and the trajectory to fulfil multiple requests introduce high degrees of uncertainty, creating challenges for ride-pooling operators. This study aims to expand the current state-of-the-art Approximate Dynamic Programming (ADP) approach for ride-pooling services, introduce key extensions, and perform a comparative analysis with the Neural Approximate Dynamic Programming (NeurADP) approach to optimise the efficiency and effectiveness of these services. Specifically, we develop an ADP approach that incorporates three important problem specifications: (i) pick-up and drop-off deadlines, (ii) vehicle rebalancing, and (iii) allowing more than two passengers in a vehicle. We conduct a detailed numerical study with the New York City taxi-cab dataset and a dataset of taxi-cab requests collected in the city of Chicago. We also provide a sensitivity analysis on key model parameters such as wait and delay times, passenger group sizes, and vehicle capacity. Our comparative analysis highlights the strengths and limitations of both ADP and NeurADP methodologies. Network density and road directionality are found to significantly impact the performance. NeurADP is found to be more efficient in learning value function approximations for larger and more complex problem settings than the ADP approach. However, in less complex cases, ADP is shown to outperform NeurADP.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 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 source (direct Gemma or distilled Codex), 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".