|Production scheduling, the problem of sequentially configuring a factory to meet forecasted demands, is a critical problem throughout the manufacturing industry. The requirement of maintaining product inventories in the face of unpredictable demand and stochastic factory output makes standard scheduling models, such as job-shop, inadequate. Currently applied algorithms, such as simulated annealing and constraint propagation, must employ ad-hoc methods such as frequent replanning to cope with uncertainty.
In this paper, we describe a Markov Decision Process (MDP) formulation of production scheduling which captures stochasticity in both production and demands. The solution to this MDP is a value function which can be used to generate optimal scheduling decisions online. A simple example illustrates the theoretical superiority of this approach over replanning-based methods. We then describe an industrial application and two reinforcement learning methods for generating an approximate value function on this domain. Our results demonstrate that in both deterministic and noisy scenarios, value function approximation is an effective technique.
Associated Lab(s) / Group(s):
Reliable Autonomous Systems Lab and Auton Lab
Associated Project(s): Auton Project and Federation of Intelligent Robotic Explorers Project
|Jeff Schneider, Justin Boyan, and Andrew Moore, "Value Function Based Production Scheduling," Machine Learning: Proceedings of the Fifteenth International Conference (ICML '98), March, 1998.|
author = "Jeff Schneider and Justin Boyan and Andrew Moore",
title = "Value Function Based Production Scheduling",
booktitle = "Machine Learning: Proceedings of the Fifteenth International Conference (ICML '98)",
month = "March",
year = "1998",
|The Robotics Institute is part of the School of Computer Science, Carnegie Mellon University.|
Contact Us | Update Instructions