Szczegóły publikacji
Opis bibliograficzny
A transductive learning-based method for vehicle routing problems using off-policy proximal policy optimization and hyperparameter optimization / Xiaobo Liu, Chin Soon Ku, Jing Yang, Roohallah Alizadehsani, Paweł Pławiak, Ryszard TADEUSIEWICZ, Qi Han, Uzair Aslam Bhatti, Lip Yee Por // Information Sciences ; ISSN 0020-0255 . — 2026 — vol. 754 art. no. 123671, s. 1–33. — Bibliogr. s. 32–33, Abstr. — Publikacja dostępna online od: 2026-05-22
Autorzy (9)
- Liu Xiaobo
- Ku Chin Soon
- Yang Jing
- Alizadehsani Roohallah
- Pławiak Paweł
- AGHTadeusiewicz Ryszard
- Han Qi
- Bhatti Uzair Aslam
- Por Lip Yee
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 168476 |
|---|---|
| Data dodania do BaDAP | 2026-06-23 |
| Tekst źródłowy | URL |
| DOI | 10.1016/j.ins.2026.123671 |
| Rok publikacji | 2026 |
| Typ publikacji | artykuł w czasopiśmie |
| Otwarty dostęp |  |
| Creative Commons | |
| Czasopismo/seria | Information Sciences |
Abstract
The Vehicle Routing Problem (VRP) is a fundamental combinatorial optimization task that involves determining cost-effective routes subject to operational constraints. This study proposes a deep reinforcement learning framework that integrates Off-policy Proximal Policy Optimization (PPO) with a transductive LSTM (TLSTM), further enhanced by a differential evolution-based hyperparameter optimization (HO) procedure. The TLSTM module captures spatiotemporal dependencies more effectively than conventional LSTMs, while the off-policy PPO component enables robust policy updates under diverse VRP variants. The HO module ensures stable convergence by adaptively balancing exploration and exploitation. The proposed approach is evaluated on five VRP variants—including the Traveling Salesman Problem (TSP), Capacitated VRP (CVRP), Split Delivery VRP (SDVRP), Orienteering Problem (OP), and Prize Collecting TSP (PCTSP)—demonstrating consistent improvements in both solution quality and computational efficiency. On average, the framework achieves a 4.12% reduction in route costs and a 94.34% improvement in computational speed, underscoring its potential for advancing VRP research and supporting practical applications in logistics and transportation. © 2026 The Author(s)
