Controls and Control Theory Commons^™

Utilizing Trajectory Optimization In The Training Of Neural Network Controllers, Nicholas Kimball

Master's Theses

Applying reinforcement learning to control systems enables the use of machine learning to develop elegant and efficient control laws. Coupled with the representational power of neural networks, reinforcement learning algorithms can learn complex policies that can be difficult to emulate using traditional control system design approaches. In this thesis, three different model-free reinforcement learning algorithms, including Monte Carlo Control, REINFORCE with baseline, and Guided Policy Search are compared in simulated, continuous action-space environments. The results show that the Guided Policy Search algorithm is able to learn a desired control policy much faster than the other algorithms. In the inverted pendulum …

Bridgeless Active Power Factor Correction Using A Current Fed Push Pull Converter, Jeramie Seth Bianchi

Master's Theses

ABSTRACT

Bridgeless Active Power Factor Correction

Using a Current Fed Push Pull Converter

Jeramie Seth Bianchi

Switched Mode Power Supplies have become increasingly popular for efficient methods of delivering power to an assortment of electronic devices. This thesis proposes a method of using a current fed push pull converter to provide active power factor correction and rectification in a single stage. While most AC-DC converters utilize a bridge rectifier to convert AC-DC and then perform DC-DC conversion, the proposed circuit will utilize its output diodes to perform rectification, thus eliminating the need for a bridge rectifier. This circuit will also …