Average-reward reinforcement learning for product delivery by multiple vehicles

Graduate Project

Öffentlich Deposited

Citeable URL: https://ir.library.oregonstate.edu/concern/graduate_projects/4b29bf26t

Descriptions

Attribute Name	Values
Creator	Tang, Hong
Abstract	Real time delivery of products is the context of stochastic demands and multiple vehicles is a difficult problem as it requires the joint investigation of the problems in inventory control and vehicle routing. We model this problem in the framework of Average reward Reinforcement Learning (ARL) and present experimental results on several ARL algorithms including a novel model-free algorithm called AR learning that automatically explores the state space while always choosing the greedy action with respect to the current approximate value function. Another contribution is a hybrid of linear and feature based function approximation method that yields superior performance to either method.
Resource Type	Capstone Project
Date Issued	2002-06
Degree Level	Master's
Degree Name	Master of Science (M.S.)
Degree Field	Computer Science
Degree Grantor	Oregon State University
Commencement Year	2002
Advisor	Tadepalli, Prasad
Academic Affiliation	Computer Science
Urheberrechts-Erklärung	In Copyright
Publisher	Oregon State University
Peer Reviewed	No
Language	English [eng]

Miniaturansicht	Titel	Hochladedatum	Sichtbarkeit	Aktionen
	Tang_Hong_2002_06.pdf	2023-03-27	Öffentlich	Herunterladen