Related papers: Time-on-Task Estimation with Log-Normal Mixture Mo…
Language models (LMs) have shown impressive performance on tasks within their training distribution, but often struggle with structurally novel tasks even when given a small number of in-context task examples. We investigate the…
Evaluating the real-world capabilities of AI systems requires grounding benchmark performance in human-interpretable measures of task difficulty. Existing approaches that rely on direct human task completion time annotations are costly,…
In this work, we investigate task planning for mobile robots under linear temporal logic (LTL) specifications. This problem is particularly challenging when robots navigate in continuous workspaces due to the high computational complexity…
Competitive non-cooperative online decision-making agents whose actions increase congestion of scarce resources constitute a model for widespread modern large-scale applications. To ensure sustainable resource behavior, we introduce a novel…
One of the questions that arises when designing models that learn to solve multiple tasks simultaneously is how much of the available training budget should be devoted to each individual task. We refer to any formalized approach to…
We propose a novel and robust online function-on-scalar regression technique via geometric median to learn associations between functional responses and scalar covariates based on massive or streaming datasets. The online estimation…
The aim of multi-task reinforcement learning is two-fold: (1) efficiently learn by training against multiple tasks and (2) quickly adapt, using limited samples, to a variety of new tasks. In this work, the tasks correspond to reward…
We study the problem of estimating an unknown parameter in a distributed and online manner. Existing work on distributed online learning typically either focuses on asymptotic analysis, or provides bounds on regret. However, these results…
It is commonly assumed that a specific testing occasion (task, design, procedure, etc.) provides insights that generalise beyond that occasion. This assumption is infrequently carefully tested in data. We develop a statistically principled…
Crowdsourcing is an online outsourcing mode which can solve the current machine learning algorithm's urge need for massive labeled data. Requester posts tasks on crowdsourcing platforms, which employ online workers over the Internet to…
The online homework system WeBWorK has been successfully used at several hundred colleges and universities. Despite its popularity, the WeBWorK system does not provide detailed metrics of student performance to instructors. In this article,…
We study offline multitask representation learning in reinforcement learning (RL), where a learner is provided with an offline dataset from different tasks that share a common representation and is asked to learn the shared representation.…
The search task and the system both affect the demand on cognitive resources during information search. In some situations, the demands may become too high for a person. This article has a three-fold goal. First, it presents and critiques…
Fluency is an important metric in Human-Robot Interaction (HRI) that describes the coordination with which humans and robots collaborate on a task. Fluency is inherently linked to the timing of the task, making temporal constraint networks…
Reinforcement learning (RL) has shown great promise with algorithms learning in environments with large state and action spaces purely from scalar reward signals. A crucial challenge for current deep RL algorithms is that they require a…
Prior work has developed a range of automated measures ("detectors") of student self-regulation and engagement from student log data. These measures have been successfully used to make discoveries about student learning. Here, we extend…
On-the-job learning consists in continuously learning while being used in production, in an open environment, meaning that the system has to deal on its own with situations and elements never seen before. The kind of systems that seem to be…
Multitask learning is a powerful framework that enables one to simultaneously learn multiple related tasks by sharing information between them. Quantifying uncertainty in the estimated tasks is of pivotal importance for many downstream…
Imitation learning is an approach in which an agent learns how to execute a task by trying to mimic how one or more teachers perform it. This learning approach offers a compromise between the time it takes to learn a new task and the effort…
The ability to accurately estimate job runtime properties allows a scheduler to effectively schedule jobs. State-of-the-art online cluster job schedulers use history-based learning, which uses past job execution information to estimate the…