You are here

REINFORCEMENT LEARNING FOR OPTIMAL CONTROL OF NETWORK EPIDEMIC PROCESSES

Download pdf | Full Screen View

Date Issued:
2019
Abstract/Description:
Our society is increasingly interconnected, making it easy for cascades/epidemic (diseases, disinformation etc). Current epidemic control efforts are based on approximate network epidemic models, which often ignore the unique complexity and rich information embedded in the complex interconnections of real-world networks/populations.Deep reinforcement learning (RL) is a powerful tool at learning policies for these nonlinear, complex processes in high-dimension. To control an epidemic outbreak on a Susceptible-Infected-Susceptible network epidemic model, we design a RL framework with a custom reward structure using the node2vec embedding technique. Results indicate deep RL is able to determine and converge on an optimal intervention policy in a relatively short time.
Title: REINFORCEMENT LEARNING FOR OPTIMAL CONTROL OF NETWORK EPIDEMIC PROCESSES.
15 views
8 downloads
Name(s): Kerrigan, Alec H, Author
Enyioha, Chinwendu, Committee Chair
Shuai, Zhisheng, Committee Member
University of Central Florida, Degree Grantor
Type of Resource: text
Date Issued: 2019
Publisher: University of Central Florida
Language(s): English
Abstract/Description: Our society is increasingly interconnected, making it easy for cascades/epidemic (diseases, disinformation etc). Current epidemic control efforts are based on approximate network epidemic models, which often ignore the unique complexity and rich information embedded in the complex interconnections of real-world networks/populations.Deep reinforcement learning (RL) is a powerful tool at learning policies for these nonlinear, complex processes in high-dimension. To control an epidemic outbreak on a Susceptible-Infected-Susceptible network epidemic model, we design a RL framework with a custom reward structure using the node2vec embedding technique. Results indicate deep RL is able to determine and converge on an optimal intervention policy in a relatively short time.
Identifier: CFH2000580 (IID), ucf:45643 (fedora)
Note(s): 2019-08-01
B.S.
College of Engineering and Computer Science, Computer Science
Bachelors
This record was generated from author submitted information.
Persistent Link to This Record: http://purl.flvc.org/ucf/fd/CFH2000580
Restrictions on Access: public
Host Institution: UCF

In Collections