Paper
5 May 2017 Capturing a Commander's decision making style
Eugene Santos Jr., Hien Nguyen, Jacob Russell, Keumjoo Kim, Luke Veenhuis, Ramnjit Boparai, Thomas Kristoffer Stautland
Author Affiliations +
Abstract
A Commander’s decision making style represents how he weighs his choices and evaluates possible solutions with regards to his goals. Specifically, in the naval warfare domain, it relates the way he processes a large amount of information in dynamic, uncertain environments, allocates resources, and chooses appropriate actions to pursue. In this paper, we describe an approach to capture a Commander’s decision style by creating a cognitive model that captures his decisionmaking process and evaluate this model using a set of scenarios using an online naval warfare simulation game. In this model, we use the Commander’s past behaviors and generalize Commander's actions across multiple problems and multiple decision making sequences in order to recommend actions to a Commander in a manner that he may have taken. Our approach builds upon the Double Transition Model to represent the Commander's focus and beliefs to estimate his cognitive state. Each cognitive state reflects a stage in a Commander’s decision making process, each action reflects the tasks that he has taken to move himself closer to a final decision, and the reward reflects how close he is to achieving his goal. We then use inverse reinforcement learning to compute a reward for each of the Commander's actions. These rewards and cognitive states are used to compare between different styles of decision making. We construct a set of scenarios in the game where rational, intuitive and spontaneous decision making styles will be evaluated.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Eugene Santos Jr., Hien Nguyen, Jacob Russell, Keumjoo Kim, Luke Veenhuis, Ramnjit Boparai, and Thomas Kristoffer Stautland "Capturing a Commander's decision making style", Proc. SPIE 10184, Sensors, and Command, Control, Communications, and Intelligence (C3I) Technologies for Homeland Security, Defense, and Law Enforcement Applications XVI, 1018412 (5 May 2017); https://doi.org/10.1117/12.2268452
Lens.org Logo
CITATIONS
Cited by 1 scholarly publication.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Cognitive modeling

Coastal modeling

Process modeling

Warfare

Fiber optic gyroscopes

Video

Computer science

Back to Top