Closed-loop Rescheduling using Deep Reinforcement Learning

In this work, a novel approach for generating rescheduling knowledge which can be used in real-time for handling unforeseen events without extra deliberation is presented. For generating such control knowledge, the rescheduling task is modelled and solved as a closed-loop control problem by resortin...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Palombarini, Jorge A., Martínez, Ernesto C.
Formato: Objeto de conferencia Resumen
Lenguaje:Inglés
Publicado: 2019
Materias:
Ciencias Informáticas
Control knowledge
Schedule state simulator
Computational tool
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/89513
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-89513
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
Control knowledge
Schedule state simulator
Computational tool
spellingShingle Ciencias Informáticas
Control knowledge
Schedule state simulator
Computational tool
Palombarini, Jorge A.
Martínez, Ernesto C.
Closed-loop Rescheduling using Deep Reinforcement Learning
topic_facet Ciencias Informáticas
Control knowledge
Schedule state simulator
Computational tool
description In this work, a novel approach for generating rescheduling knowledge which can be used in real-time for handling unforeseen events without extra deliberation is presented. For generating such control knowledge, the rescheduling task is modelled and solved as a closed-loop control problem by resorting to the integration of a schedule state simulator with a rescheduling agent that can learn successful schedule repairing policies directly from a variety of simulated transitions between schedule states, using as input readily available schedule color-rich Gantt chart images, and negligible prior knowledge. The generated knowledge is stored in a deep Q-network, which can be used as a computational tool in a closed-loop rescheduling control way that select repair actions to make progress towards a goal schedule state, without requiring to compute the rescheduling problem solution every time a disruptive event occurs and safely generalize control knowledge to unseen schedule states.
format Objeto de conferencia
Resumen
author Palombarini, Jorge A.
Martínez, Ernesto C.
author_facet Palombarini, Jorge A.
Martínez, Ernesto C.
author_sort Palombarini, Jorge A.
title Closed-loop Rescheduling using Deep Reinforcement Learning
title_short Closed-loop Rescheduling using Deep Reinforcement Learning
title_full Closed-loop Rescheduling using Deep Reinforcement Learning
title_fullStr Closed-loop Rescheduling using Deep Reinforcement Learning
title_full_unstemmed Closed-loop Rescheduling using Deep Reinforcement Learning
title_sort closed-loop rescheduling using deep reinforcement learning
publishDate 2019
url http://sedici.unlp.edu.ar/handle/10915/89513
work_keys_str_mv AT palombarinijorgea closedloopreschedulingusingdeepreinforcementlearning
AT martinezernestoc closedloopreschedulingusingdeepreinforcementlearning
bdutipo_str Repositorios
_version_ 1764820489885188102

Ejemplares similares