Trailer allocation and truck routing using bipartite graph assignment and deep reinforcement learning
Bibliographic record
Abstract
Abstract Trailer allocation and truck routing are critical components of truck transportation management. However, in real‐world applications, inter‐influence between selecting the best trailers and trucks, strict fulfillment of Pickup or Delivery (PD) orders, and the size of the fleet are some of the challenges that need to be dealt with in a large truck company. In addition, trailer allocation and truck routing problems are considered to be NP‐hard combinatorial optimization (CO) problems. Therefore, we use deep reinforcement learning (DRL), which has the capability of solving routing problems with a single set of hyperparameters. This is significant progress toward finding strong heuristics for a special case of the trailer allocation to customers and truck routing problem presented in this article. Given a set of trailers, trucks, customers, and orders we propose a novel two‐phase framework based on Bipartite Graph Assignment (BGA) and attention‐based DRL to minimize the total traveling distance traveled from trucks to trailers and then to customers. The BGA heuristic finds the minimum traveling distance from the trailers to the customers based on the edge information and the encoder‐decoder helps DRL to get useful node and graph feature representations and trains the model to find the proper solutions for the trailer allocation and truck routing problem. Our experiments on three different problem sizes showcase the effectiveness of ARTT‐DRL. The results indicate that ARTT‐DRL produces desirable outcomes and has strong generalization capabilities.
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 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".