Related papers: From lecture to active learning: Rewards for all, …
We present a novel interactive learning protocol that enables training request-fulfilling agents by verbally describing their activities. Unlike imitation learning (IL), our protocol allows the teaching agent to provide feedback in a…
One of the leading university goals is to provide the students with the necessary skills for better functioning in their future studies. Gaining and developing skills, both technical and soft skills, are the critical building blocks for a…
"Math is not a spectator sport." "Lecturing is educational malpractice." Slogans like these rally some mathematicians to teach classes that feature "active learning", where lecturing is eschewed for student participation. Yet as much as I…
Learning about many things can provide numerous benefits to a reinforcement learning system. For example, learning many auxiliary value functions, in addition to optimizing the environmental reward, appears to improve both exploration and…
Conveying complex objectives to reinforcement learning (RL) agents can often be difficult, involving meticulous design of reward functions that are sufficiently informative yet easy enough to provide. Human-in-the-loop RL methods allow…
This paper presents a personalized lecture concept using educational blocks and its demonstrative application in a new university lecture. Higher education faces daily challenges: deep and specialized knowledge is available from everywhere…
Curriculum Learning for Reinforcement Learning is an increasingly popular technique that involves training an agent on a sequence of intermediate tasks, called a Curriculum, to increase the agent's performance and learning speed. This paper…
Active Learning (AL) methods seek to improve classifier performance when labels are expensive or scarce. We consider two central questions: Where does AL work? How much does it help? To address these questions, a comprehensive experimental…
The challenge of developing powerful and general Reinforcement Learning (RL) agents has received increasing attention in recent years. Much of this effort has focused on the single-agent setting, in which an agent maximizes a predefined…
Active learning is a proven pedagogical style that has demonstrated value by improving students' performance and classroom experience. In spite of the evidence, adoption of active learning in computer science remains relatively low. To…
Difficulty adjustment in practice exercises has been shown to be beneficial for learning. However, previous research has mostly investigated close-ended tasks, which do not offer the students multiple ways to reach a valid solution.…
We conduct a comprehensive evaluation of state-of-the-art deep active learning methods. Surprisingly, under general settings, no single-model method decisively outperforms entropy-based active learning, and some even fall short of random…
This paper discusses several linear algebra activities designed to help enhance students' skills in collaborating, exploring mathematics, and linking together abstract and visual ways of approaching mathematics. Most of these activities are…
Introductory artificial intelligence (AI) courses present significant learning challenges due to abstract concepts, mathematical complexity, and students' diverse technical backgrounds. While active and collaborative pedagogies are often…
Feedback has a powerful influence on learning, but it is also expensive to provide. In large classes, it may even be impossible for instructors to provide individualized feedback. Peer assessment has received attention lately as a way of…
Curriculum learning--ordering training examples in a sequence to aid machine learning--takes inspiration from human learning, but has not gained widespread acceptance. Static strategies for scoring item difficulty rely on indirect proxy…
In the rapidly evolving educational landscape, the integration of technology has shifted from an enhancement to a cornerstone of educational strategy worldwide. This transition is propelled by advancements in digital technology, especially…
In 2020, many instructors and students at colleges and universities were thrust into an unprecedented situation as a result of the COVID-19 pandemic disruptions. Even though they typically engage in in-person teaching and learning in brick…
This article describes how the author successfully adapted techniques drawn from the literature on active learning for use in a graduate-level course on quantum field theory. Students completed readings and online questions ahead of each…
Model of active and collaborative learning applied in training specific subject makes clear advantage due to the goals of knowledge, enhanced activeness, skills that students got to develop successful future job. Studying and applying the…