Reinforcement Learning for Intermodal Transportation Planning with Time Windows and Limited Cargo Capacity
Bibliographic record
Abstract
This paper addresses the enhancement of practical intermodal transportation efficiency by synergizing train and truck utilization for the seamless movement of freights across diverse geographical locations in a country. The core challenge revolves around determining the optimal allocation of freights, either individually by trucks or collectively with train mode in each location, while accounting for time windows constraints associated with each order and the inherent capacity limitations of the transportation modes. To tackle this complex optimization problem, we employ the renowned Q-Learning reinforcement learning algorithm. This enables the derivation of an optimal dispatch policy predicated on the selection of appropriate transportation modes. In order to establish a robust benchmark for comparison, we introduce three baseline metaheuristic models: Tabu Search, Simulated Annealing, and a hybrid approach merging Tabu Search with Simulated Annealing. Our methodologies undergo rigorous testing using realistic datasets of varying sizes. The outcomes distinctly demonstrate the superior performance of Q-learning over the baseline models. Furthermore, the Q-Learning approach showcases its efficacy in real-time scenario handling, even when confronted with substantial intermodal transportation challenges on a large scale.
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 | 0.003 | 0.009 |
| 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 | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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".