The creation of autonomous decision makers to handle potentially hazardous or logistically complicated tasks is desirable for the purpose of reducing human labor and exposure to risk, and for increasing the general performance of autonomous systems in a wide variety of environments. However, traditional autonomous decision makers perform poorly when...
This dissertation serves a threefold purpose: 1. identify the principles, practices and assumptions implicated in an academic theory of social justice; 2. continue moving towards articulating a theory of social justice judgment and decision making; and 3. develop a model of social justice judgment and decision making that will assist...
Writing a program that performs well in a complex environment is a challenging task. In such problems, a method of deterministic programming combined with reinforcement learning (RL) can be helpful. However, current systems either force developers to encode knowledge in very specific forms (e.g., state-action features), or assume advanced RL...
Research suggests that entrepreneurs tend to seek to maximize utility when considering whether to pursue a new venture opportunity. However, when choosing whether to persist with their current venture or not, utility maximization may not be of primary importance. Using a conjoint experiment, we examine the difference between policies in...
Research in the aviation domain, driving distractions, anesthesia
administration, and nuclear power plant control rooms show that Concurrent Task
Management (CTM) is a process that every human operator performs when
interacting with complex environments. The need for understanding concurrent task
management in a broader perspective more applicable and generalizable to...
Natural resource decisions require consideration at many levels, ranging from how one invertebrate will be affected by a nearby road, to how an entire watershed will be transformed by a massive clearcut. Considerations reach farther than just the local ecological community-human communities, economies, and future impacts on the communities and...
The decision sequences used for troubleshooting of complex electro-mechanical systems are often ad hoc and less than optimal. This research investigated Decision Analysis and Bayesian Networks for generating an optimal decision sequence for troubleshooting. The model that was used in this research was the bleed air control system of the...
Acting intelligently to efficiently solve sequential decision problems requires the ability to extract hierarchical structure from the underlying domain dynamics, exploit it for optimal or near-optimal decision-making, and transfer it to related problems instead of solving every problem in isolation. This dissertation makes three contributions toward this goal.
The first...
Concurrent Task Management (CTM) can be defined as the process that human operators of complex systems perform to allocate their attention among multiple, simultaneous tasks. A challenge of CTM research is to create an experimental environment which is complex enough to model a real world multitasking situation. Also, this system...
Many Departments of Transportation (DOTs) have done construction and maintenance work at night in order to minimize the disruption of daytime traffic, but nighttime operations produce a new set of concerns such as safety, public relations, productivity, and work quality. In addition, decision-making for using nighttime operations has been subjective...