APPLYING REINFORCEMENT LEARNING TO THE WEAPON ASSIGNMENT PROBLEM IN AIR DEFENCE

dc.creator	Herman Le Roux
dc.creator	Jan Roodt
dc.creator	Hildegarde Mouton
dc.date	2011-11-01T00:00:00Z
dc.date.accessioned	2015-07-20T20:09:59Z
dc.date.available	2015-07-20T20:09:59Z
dc.identifier	10.5787/39-2-115
dc.identifier	2224-0020
dc.identifier	https://doaj.org/article/031309c38d114a3fbcabb69e7db17f18
dc.identifier.uri	http://evidence.thinkportal.org/handle/123456789/9445
dc.identifier.uri	https://doaj.org/article/031309c38d114a3fbcabb69e7db17f18
dc.description	The modern battlefield is a fast-paced, information-rich environment, where discovery of intent, situation awareness and the rapid evolution of concepts of operation and doctrine are critical success factors. A combination of the techniques investigated and tested in this work, together with other techniques in Artificial Intelligence (AI) and modern computational techniques, may hold the key to relieving the burden of the decision-maker and aiding in better decision-making under pressure. The techniques investigated in this article were two methods from the machine-learning subfield of reinforcement learning (RL), namely a Monte Carlo (MC) control algorithm with exploring starts (MCES), and an off-policy temporal-difference (TD) learning-control algorithm, <em>Q</em>-learning. These techniques were applied to a simplified version of the weapon assignment (WA) problem in air defence. The MCES control algorithm yielded promising results when searching for an optimal shooting order. A greedy approach was taken in the <em>Q</em>-learning algorithm, but experimentation showed that the MCES-control algorithm still performed significantly better than the <em>Q</em>-learning algorithm, even though it was slower.
dc.language	English
dc.publisher	University of Stellenbosch. Faculty of Military Science (Military Academy)
dc.relation	http://scientiamilitaria.journals.ac.za/pub/article/view/115
dc.relation	https://doaj.org/toc/2224-0020
dc.source	Scientia Militaria : South African Journal of Military Studies, Vol 39, Iss 2 (2011)
dc.subject	Military Science
dc.subject	U
dc.subject	DOAJ:Military Science
dc.subject	DOAJ:Technology and Engineering
dc.subject	Military Science
dc.subject	U
dc.subject	DOAJ:Military Science
dc.subject	DOAJ:Technology and Engineering
dc.subject	Military Science
dc.subject	U
dc.subject	DOAJ:Military Science
dc.subject	DOAJ:Technology and Engineering
dc.subject	Military Science
dc.subject	U
dc.subject	DOAJ:Military Science
dc.subject	DOAJ:Technology and Engineering
dc.subject	Military Science
dc.subject	U
dc.subject	Military Science
dc.subject	U
dc.subject	Military Science
dc.subject	U
dc.title	APPLYING REINFORCEMENT LEARNING TO THE WEAPON ASSIGNMENT PROBLEM IN AIR DEFENCE
dc.type	Article