Related papers: "Stop replacing salt with sugar!'': Towards Intuit…

This paper extends recent work in interactive machine learning (IML) focused on effectively incorporating human feedback. We show how control and feedback signals complement each other in systems which model human reward. We demonstrate…

Adaptive user interfaces (UIs) automatically change an interface to better support users' tasks. Recently, machine learning techniques have enabled the transition to more powerful and complex adaptive UIs. However, a core challenge for…

We are interested in how to design reinforcement learning agents that provably reduce the sample complexity for learning new tasks by transferring knowledge from previously-solved ones. The availability of solutions to related problems…

Agent learning from human interaction often relies on explicit signals, but implicit social cues, such as prosody in speech, could provide valuable information for more effective learning. This paper advocates for the integration of prosody…

AI approaches are progressing besting humans at game-related tasks (e.g. chess). The next stage is expected to be Human-AI collaboration; however, the research on this subject has been mixed and is in need of additional data points. We add…

AI agents are being developed to support high stakes decision-making processes from driving cars to prescribing drugs, making it increasingly important for human users to understand their behavior. Policy summarization methods aim to convey…

The recent rapid advancement of machine learning has been driven by increasingly powerful models with the growing availability of training data and computational resources. However, real-time decision-making tasks with limited time and…

Recent work has shown that, in classification tasks, it is possible to design decision support systems that do not require human experts to understand when to cede agency to a classifier or when to exercise their own agency to achieve…

Behavioral skills or policies for autonomous agents are conventionally learned from reward functions, via reinforcement learning, or from demonstrations, via imitation learning. However, both modes of task specification have their…

Human annotator simulation (HAS) serves as a cost-effective substitute for human evaluation such as data annotation and system assessment. Human perception and behaviour during human evaluation exhibit inherent variability due to diverse…

Imitation learning is a popular paradigm to teach robots new tasks, but collecting robot demonstrations through teleoperation or kinesthetic teaching is tedious and time-consuming. In contrast, directly demonstrating a task using our human…

LLM-based autonomous agents perform well on general reasoning tasks but still struggle to reliably use task structure, key constraints, and prior experience in complex real-world settings. We propose a case-based learning framework that…

A common way of learning to perform a task is to observe how it is carried out by experts. However, it is well known that for most tasks there is no unique way to perform them. This is especially noticeable the more complex the task is…

Imitation learning has shown success in many tasks by learning from expert demonstrations. However, most existing work relies on large-scale demonstrations from technical professionals and close monitoring of the training process. These are…

In many, if not every realistic sequential decision-making task, the decision-making agent is not able to model the full complexity of the world. The environment is often much larger and more complex than the agent, a setting also known as…

Imitation learning aims to mimic the behavior of experts without explicit reward signals. Passive imitation learning methods which use static expert datasets typically suffer from compounding error, low sample efficiency, and high…

Consider a natural language sentence describing a specific step in a food recipe. In such instructions, recognizing actions (such as press, bake, etc.) and the resulting changes in the state of the ingredients (shape molded, custard cooked,…

This paper contributes a first study into how different human users deliver simultaneous control and feedback signals during human-robot interaction. As part of this work, we formalize and present a general interactive learning framework…

Collaborative decision-making with artificial intelligence (AI) agents presents opportunities and challenges. While human-AI performance often surpasses that of individuals, the impact of such technology on human behavior remains…

A core tension in models of concept learning is that the model must carefully balance the tractability of inference against the expressivity of the hypothesis class. Humans, however, can efficiently learn a broad range of concepts. We…