Path selection in disaster response management based on Q-learning

Authors:
Zhao-Pin Su;Jian-Guo Jiang;Chang-Yong Liang;Guo-Fu Zhang
Affiliations:
Key Laboratory of Special Display Technology (Hefei University of Technology), Ministry of Education, Hefei, PRC 230009 and School of Computer and Information, Hefei University of Technology, Hefe ...;Key Laboratory of Special Display Technology (Hefei University of Technology), Ministry of Education, Hefei, PRC 230009 and School of Computer and Information, Hefei University of Technology, Hefe ...;School of Computer and Information, Hefei University of Technology, Hefei, PRC 230009 and Postdoctoral Research Station for Management Science and Engineering, Hefei University of Technology, Hefe ...;Key Laboratory of Special Display Technology (Hefei University of Technology), Ministry of Education, Hefei, PRC 230009 and School of Computer and Information, Hefei University of Technology, Hefe ...
Venue:
International Journal of Automation and Computing
Year:
2011

Citing 9
Cited 0

Technical Note: \cal Q-Learning

Machine Learning
Q-Learning for Risk-Sensitive Control

Mathematics of Operations Research
Agent-based systems for disaster management

Communications of the ACM - Emergency response information systems: emerging trends and technologies
Greedy Neighborhood Search for Disaster Relief and Evacuation Logistics

IEEE Intelligent Systems
Path selection model and algorithm for emergency logistics management

Computers and Industrial Engineering
Reinforcement learning: a survey

Journal of Artificial Intelligence Research
Using SDI and web-based system to facilitate disaster management

Computers & Geosciences
Improving communication for mobile devices in disaster response

MobileResponse'07 Proceedings of the 1st international conference on Mobile information technology for emergency response
Can agents acquire human-like behaviors in a sequential bargaining game?: comparison of Roth's and Q-learning agents

MABS'06 Proceedings of the 2006 international conference on Multi-agent-based simulation VII

Quantified Score

Hi-index	0.00

Visualization

Abstract

Suitable rescue path selection is very important to rescue lives and reduce the loss of disasters, and has been a key issue in the field of disaster response management. In this paper, we present a path selection algorithm based on Q-learning for disaster response applications. We assume that a rescue team is an agent, which is operating in a dynamic and dangerous environment and needs to find a safe and short path in the least time. We first propose a path selection model for disaster response management, and deduce that path selection based on our model is a Markov decision process. Then, we introduce Q-learning and design strategies for action selection and to avoid cyclic path. Finally, experimental results show that our algorithm can find a safe and short path in the dynamic and dangerous environment, which can provide a specific and significant reference for practical management in disaster response applications.