Multiagent learning offers a rich framework to address challenging real-world problems such as remote exploration and healthcare coordination, which require autonomous agents to express elaborate interactions. To be effective in such systems, agents must collectively reason about and pursue high-level, long-term, and possibly nebulous objectives while adapting their strategy to...
This dissertation delves into understanding, characterizing, and addressing dataset shift in deep learning, a pervasive issue for deployed machine learning systems. Integral aspects of the problem are examined: We start with the use of counterfactual explanations in order to characterize the behavior of deep reinforcement learning agents in visual input...
In recent years, model-free Deep Reinforcement Learning (RL) has become an increasingly popular alternative to more traditional model-based or optimization-based control methods in solving robotic legged locomotion. However, deploying RL in the real world can be a significant undertaking. Constructing reward functions which compel controllers to learn the desired behavior...
Consistent with its charge under Oregon House Bill 3543, the Oregon Climate Change Research Institute (OCCRI) conducts a biennial assessment of the state of climate change science, including biological, physical, and social science, as it relates to Oregon and the likely effects of climate change on Oregon. This sixth Oregon...
The focus of this thesis is to design, characterize, and apply novel computational methods and molecular systems to interrogate heterogeneous human gut microbiome-related phenomena. In Chapter 2, I design, implement, and characterize a method for embedding co-occurrence patterns derived from massive 16s amplicon datasets. I use this method to 1....
Learning latent space representations of high-dimensional world states has been at the core of recent rapid growth in reinforcement learning(RL). At the same time, RL algo- rithms have suffered from ignored uncertainties in the predicted estimates of model-free or model-based methods. In our work, we investigate both of these aspects...
Pesticides benefit agriculture by increasing crop yield, quality, and security. However, pesticides may inadvertently harm bees, which are valuable as pollinators. Thus, candidate pesticides in development pipelines must be assessed for toxicity to bees.
Leveraging a data set of 382 molecules with toxicity labels from honey bee exposure experiments, we...
Polyoxometalates (POMs) are anions consisting of three or more early transition metals ™ (Gr V and VI) oxoanions (in their highest oxidation state) linked together by a shared oxygen bond to form a 3D framework. Polyoxometalates (POMs) are a rapidly growing class of metal oxo clusters with a wide range...
For over two years, an exceptionally contagious new disease known as Coronavirus Disease 2019 (COVID-19) has spread around the globe and killed millions. Organizations such as the World Health Organization and the United Nations have suggested that universal healthcare could have helped countries currently lacking such mitigate the severity of...
When the Affordable Care Act was passed in 2010, eligibility for Medicaid was expanded to include people whose income was less than 138% of the federal poverty level. In 2012, the Supreme Court ruled that states could choose whether to expand their Medicaid programs or not. The objective of this...