Kristofer S.J. Pister (Advisor)

Model-based reinforcement learning (MBRL) has often been touted for its potential to improve on the sample-efficiency, generalization, and safety of existing reinforcement learning algorithms. These model-based algorithms constrain the policy optimization during trial-and-error learning to include a structured representation of the environment dynamics. To date, the posited benefits have largely been left as directions for future work. This thesis attempts to illustrate the central mechanism in MBRL: how a learned dynamics model interacts with decision making. A better understanding of...

Despite the popularity and widespread demand for miniaturized electronic devices, limited advances have been made to design energy storage mechanisms that can satisfy their power and size requirements. We have developed a fabrication process to produce miniature Li-ion batteries by combining the stencil printing process to deposit thick high capacity electrodes and an adhesive based sealing method for battery packaging, with active areas as small as 1 mm2. The battery consists of printed anode and cathode layers based on graphite and lithium cobalt oxide (LCO) respectively. These...