Reinforcement learning covers a broad category of control problems in which the learning agent interacts with the environment in order to learn to maximize the collected utility. Such exploratory interaction is often costly, encouraging sample-efficient algorithms to be used in…

The construction of accurate predictive models over sequence data is of fundamental importance in the pursuit of developing artificial agents that are capable of (near)-optimal sequential decision-making in disparate environments.If such predictive models are available, they can be exploited by…

This thesis explores the challenges involved in building autonomous exploration and monitoring systems, and makes contributions on four fronts: describing the semantic context of the collected data, summarizing this information, deciding where to collect this data, and making optimal online…

Authentication protocols aim to prevent agent impersonation: A is authenticated to B if B knows who A is. Many formal approaches have been used to verify authentication in distributed systems; however, although authentication is directly related to agent knowledge, it…

Decision-making under uncertainty has become critical as autonomous and semi-autonomous agents become more ubiquitious in our society. These agents must deal with uncertainty and ambiguity from the environment and still perform desired tasks robustly. Partially observable Markov decision processes (POMDPs)…

Data are produced in large quantities and in various forms around the globe everyday. Researchers advance their research depending on the availability of necessary data and the discovery of them. As people's demand to manage the data grows, however, three…

Spoken dialogue systems are gaining popularity with improvements in speech recognition technologies. Dialogue systems have been modeled effectively using Partially observable Markov decision processes (POMDPs), achieving improvements in robustness. However, past research on POMDP-based dialogue systems usually assumes that the…

This dissertation addresses the problem of sequential decision making under uncertainty in large systems. The formalisms used to study this problem are fully and partially observable Markov Decision Processes (MDPs and POMDPs, respectively). The first contribution of this dissertation is…