Search
Now showing items 1-7 of 7
Managing learning interactions for collaborative robot learning
(Georgia Institute of Technology, 2019-09-11)
Robotic assistants should be able to actively engage their human partner(s) to generalize knowledge about relevant tasks within their shared environment. Yet a key challenge is not all human partners will be proficient at ...
Policy-based exploration for efficient reinforcement learning
(Georgia Institute of Technology, 2020-04-25)
Reinforcement Learning (RL) is the field of research focused on solving sequential decision-making tasks modeled as Markov Decision Processes. Researchers have shown RL to be successful at solving a variety of problems ...
Adaptive learning in lasso models
(Georgia Institute of Technology, 2015-08-20)
Regression with L1-regularization, Lasso, is a popular algorithm for recovering the sparsity pattern (also known as model selection) in linear models from observations contaminated by noise. We examine a scenario where a ...
Supporting cognitive engagement in a learning-by-doing learning environment: case studies of participant engagement and social configurations in kitchen science investigators
(Georgia Institute of Technology, 2011-08-29)
Learning-by-doing learning environments support a wealth of physical engagement in activities. However, there is also a lot of variability in what participants learn in each enactment of these types of environments. ...
Guided teaching interactions with robots: embodied queries and teaching heuristics
(Georgia Institute of Technology, 2012-05-17)
The vision of personal robot assistants continues to become more realistic with technological advances in robotics. The increase in the capabilities of robots, presents boundless opportunities for them to perform useful ...
New formulations for active learning
(Georgia Institute of Technology, 2014-01-10)
In this thesis, we provide computationally efficient algorithms with provable statistical guarantees, for the problem of active learning, by using ideas from sequential analysis. We provide a generic algorithmic framework ...
New insights on the power of active learning
(Georgia Institute of Technology, 2015-07-22)
Traditional supervised machine learning algorithms are expected to have access to a large corpus of labeled examples, but the massive amount of data available in the modern world has made unlabeled data much easier to ...