Please use this identifier to cite or link to this item:
Title: An intelligent resource allocation decision support system with Q-learning
Authors: YOW AI NEE
Keywords: learning, resource allocation, decision process, control policy, uncertain, wafer testing
Issue Date: 12-Jun-2009
Citation: YOW AI NEE (2009-06-12). An intelligent resource allocation decision support system with Q-learning. ScholarBank@NUS Repository.
Abstract: This thesis studies into the learning effect of resource allocation problems of wafer testing industry. Due to the uncertain environment, Markov decision process is considered as the core of the decision procedures. The objective is to optimize the control policy under the changing environment subject to limited time constraints. Different learning methods are proposed and explored to improve existing control policy. The fuzzy Q-learning algorithm learns from past policies in a model-free environment for resource allocation problem to handle continuous state of Markov decision processes that encountered in large-scale stochastic problems. Numerical experiments are implemented on real wafer testing system to verify the effectiveness. The proposed fuzzy Q learns to significantly capable and stable for real-time uncertain wafer testing environment. The results in this thesis could be generalized to resource allocation problems in fields of resources management, decision making, and learning algorithm.
Appears in Collections:Master's Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
YowAN.pdf1.27 MBAdobe PDF



Page view(s)

checked on May 17, 2019


checked on May 17, 2019

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.