Online model-based reinforcement learning for decision-making in long distance routes
Ver/
Compartir
Estadísticas
Ver Estadísticas de usoMetadatos
Mostrar el registro completo del ítemÁrea de conocimiento
Teoría de la Señal y las ComunicacionesPatrocinadores
This work has been funded by Consejeria de Desarrollo Economico, Turismo y Empleo, Region de Murcia, under the RIS3Mur project grant SiSPERT (ref. 2I16SAE00023), and by project Grant PID2020-116329GB-C22 funded by MCIN/AEI/10.13039/501100011033 .Realizado en/con
Universidad Politécnica de CartagenaFecha de publicación
2022-06-25Editorial
ELSEVIERCita bibliográfica
Juan J. Alcaraz, Fernando Losilla, Luis Caballero-Arnaldos, Online model-based reinforcement learning for decision-making in long distance routes, Transportation Research Part E: Logistics and Transportation Review, Volume 164, 2022, 102790, ISSN 1366-5545, https://doi.org/10.1016/j.tre.2022.102790.Revisión por pares
SIPalabras clave
Route schedulingReinforcement learning
Model predictive control
Monte Carlo tree search
Resumen
In road transportation, long-distance routes require scheduled driving times, breaks, and rest periods, in compliance with the regulations on working conditions for truck drivers, while ensuring goods are delivered within the time windows of each customer. However, routes are subject to uncertain travel and service times, and incidents may cause additional delays, making predefined schedules ineffective in many real-life situations. This paper presents a reinforcement learning (RL) algorithm capable of making en-route decisions regarding driving times, breaks, and rest periods, under uncertain conditions. Our proposal aims at maximizing the likelihood of on-time delivery while complying with drivers’ work regulations. We use an online model-based RL strategy that needs no prior training and is more flexible than model-free RL approaches, where the agent must be trained offline before making online decisions. Our proposal combines model predictive control with a rollout strategy and Monte ...
Colecciones
- Artículos [1768]
El ítem tiene asociados los siguientes ficheros de licencia:
Redes sociales