State-of-the-art personal robots need to perform complex manipulation tasks to be viable in complex scenarios. However, many of these robots, like the PR2, use manipulators with high degrees of freedom. High degrees of freedom are desirable from a functionality standpoint, but make the learning task more difficult by adding a...
Air traffic flow management over the U.S. airpsace is a difficult problem. Current management approaches lead to hundreds of thousands of hours of delay, costing billions of dollars annually. Weather and airport conditions may instigate this delay, but routing decisions balancing delay with congestion contribute significantly to the propagation of...
As the fifth generation of mobile communication systems (5G) is being deployed, massive multiple-input multiple-output (MIMO) serves as one of its enabling technologies where reliable and ultra low latency communications are achieved while being power and spectrum efficient. This thesis studies the security aspect of massive MIMO system from the...
How should reinforcement learning (RL) agents explain themselves to humans not trained in AI? To gain insights into this question, we conducted a 124 participant, four-treatment experiment to compare participants’ mental models of an RL agent in the context of a simple Real-Time Strategy (RTS) game. The four treatments isolated...
The thesis focuses on model-based approximation methods for reinforcement
learning with large scale applications such as combinatorial optimization problems.
First, the thesis proposes two new model-based methods to stablize the
value–function approximation for reinforcement learning. The first one is the
BFBP algorithm, a batch-like reinforcement learning process which iterates between...
How can an agent generalize its knowledge to new circumstances? To learn
effectively an agent acting in a sequential decision problem must make intelligent action selection choices based on its available knowledge. This dissertation focuses on Bayesian methods of representing learned knowledge and develops novel algorithms that exploit the represented...
We took the back-propagation algorithms of Werbos for recurrent and feed-forward neural networks and implemented them on machines with graphics processing units (GPU). The parallelism of these units gave our implementations a 10 to 100 fold increase in speed. For nets with less than 20 neurons the machine performed faster...
A fully integrated CMOS GPS receiver RF front end optimized for low power operation is presented. The system operates with a supply voltage down to 250 mV. A prototype has been fabricated in a 0.13μm CMOS process and includes a low voltage LNA, quadrature oscillators, and quadrature mixers. It exhibits...
The problem of document classification has been widely studied in machine learning and data mining. In document classification, most of the popular algorithms are based on the bag-of-words representation. Due to the high dimensionality of the bag-of-words representation, significant research has been conducted to reduce the dimensionality via different approaches....