This work aims to bridge the gap between noise and structure by aligning visualizations of planning states to the underlying state space structure. Work completed as part of my Master’s at Queen’s University.
We fully discretize DreamerV2 and evaluate the discrete representation learned by the model. This project was completed as part of my USRA in 2021.
Overview of the paper Graph Memory LSTMs: Learning Graph Relationships in Spatiotemporal Data for Time Series Forecasting. This project was completed as part of my USRA in 2020.
A comparison of methods for predicting taxi trip length with prediction intervals that convey the models condfidence. Presented and published in conference proceedings at AMMCS 2019. This project was completed as part of my USRA in 2019.