Markov Decision Processes (MDPs) are the de-facto formalism for studying sequential decision making problems with uncertainty, ranging from classical problems such as inventory control and path planning, to more complex problems such as reservoir control under rainfall uncertainty and emergency response optimization for fire and medical emergencies. Most prior research...
Data variations are prevalent in real-world applications. For example, software vendors have to handle numerous variations in the business requirements, conventions, and environmental settings of a software product. In database-backed software, the database of each version may have a different schema and content. As another example, data scientists often need...
Although deep reinforcement learning agents have produced impressive results in many domains, their decision making is difficult to explain to humans. To address this problem, past work has mainly focused on explaining why an action was chosen in a given state. A different type of explanation that is useful is...
Constructing a panorama from a set of videos is a long-standing problem in computer vision. A panorama represents an enhanced still-image representation of an entire scene captured in a set of videos, where each video shows only a part of the scene. Importantly, a panorama shows only the scene background,...
A fundamental problem in computer vision is to partition an image into meaningful segments. While image segmentation is required by many applications, the thesis focuses on segmentation of computed tomography (CT) images for analysis and quality control of composite materials. The key research contribution of this thesis is a novel...
We consider the problem of wireless spectrum management in cognitive wireless networks that maximizes the revenue for a spectrum operator. Specifically, we study the problem on how a wireless spectrum operator can optimally allocate its limited spectrum to various classes users/devices who pay differently for their spectrum per unit time....
In this dissertation, we present a user-in-the-loop method for the design of an interactive motion data structure that benefits from the advantages of both motion graphs and blend-based techniques. Our novel approach automatically analyzes a traditional motion graph built from labeled motion clips. The result is a more condensed, coarser...
Citizen Science is a paradigm in which volunteers from the general public participate in scientific studies, often by performing data collection. This paradigm is especially useful if the scope of the study is too broad to be performed by a limited number of trained scientists. Although citizen scientists can contribute...
A large number of sequential decision-making problems in uncertain environments
can be modeled as Markov Decision Processes (MDPs). In such settings, an agent
can observe at each time step the state of the environment and then executes an
action, causing a stochastic transition to a new state of the environment...
Reinforcement learning in real-world domains suffers from three curses of dimensionality: explosions in state and action spaces, and high
stochasticity or "outcome space" explosion. Multiagent domains are particularly susceptible to these problems. This thesis describes ways to mitigate these curses in several different multiagent domains, including real-time delivery of products...