Reinforcement learning defines the problem facing agents that learn to make good decisions through action and observation alone. To be effective problem solvers, such agents …
This is an updated version of original (DOI: 10.26300/1pad-7574) that contains minor revisions (see page iv for list of revisions). Reinforcement learning defines the problem …
Designing Artificial Intelligence (AI) is still reserved for experts, and the existing design paradigm follows a data-driven approach: domain experts start with a hypothetical model, …
The digitization of the economy has had a revolutionary impact on society, and, today, people use digital web services to conduct essential daily activities, such …
Reinforcement learning (RL) techniques have led to remarkable results in challenging domains such as Atari games, Go, and Starcraft, suggesting that practical applications lie just …
Future collaborative robots must be capable of finding objects. As such a fundamental skill, we expect object search to eventually become an off-the-shelf capability for …
In this thesis, we first contribute to the empirical-game theoretic analysis (EGTA) literature both from a theoretical and a computational perspective. Theoretically, we present a …
In order to intuitively and efficiently collaborate with humans, robots must learn to complete tasks specified using natural language. Natural language instructions can have many …
Robotic perception often fails on reflective and transparent surfaces. We will describe a new method of passive RGB sensing which uses a calibrated camera located …
Conversational assistive robots have the potential to help human users accomplish a wide range of daily tasks, such as cooking meals, performing exercises, or operating …
Combinatorial optimization problems are fundamental in many real-world applications, where the goal is to find the optimal or near-optimal solution to a problem subject to …
While humans have physically and cognitively evolved to work alongside and communicate with each other, humans and robots cannot intuit each others behavior. We can …
Reinforcement learning (RL) is the study of the interaction between an environment and an artificial agent that learns to maximize reward through trial-and-error. Owing to …
Neural network models have grown in popularity to be the dominant artificial intelligence paradigm of our time, succeeding across a variety of challenging tasks despite …
Robotic perception is a key step in any autonomous robotic task including manipulation, localization and planning. The more precise the perception system is, the more …