Related papers: User Modelling for Avoiding Overfitting in Interac…

When a robot learns from human examples, most approaches assume that the human partner provides examples of optimal behavior. However, there are applications in which the robot learns from non-expert humans. We argue that the robot should…

Search and recommendation are the two most common approaches used by people to obtain information. They share the same goal -- satisfying the user's information need at the right time. There are already a lot of Internet platforms and Apps…

Policies often fail due to distribution shift -- changes in the state and reward that occur when a policy is deployed in new environments. Data augmentation can increase robustness by making the model invariant to task-irrelevant changes in…

Understanding how humans evaluate robot behavior during human-robot interactions is crucial for developing socially aware robots that behave according to human expectations. While the traditional approach to capturing these evaluations is…

LLMs are now embedded in a wide range of everyday scenarios. However, their inherent hallucinations risk hiding misinformation in fluent responses, raising concerns about overreliance on AI. Detecting overreliance is challenging, as it…

We present a framework for learning human user models from joint-action demonstrations that enables the robot to compute a robust policy for a collaborative task with a human. The learning takes place completely automatically, without any…

Understanding the fundamentals of human reasoning is central to the development of any system built to closely interact with humans. Cognitive science pursues the goal of modeling human-like intelligence from a theory-driven perspective…

Human-computer interactive systems that rely on machine learning are becoming paramount to the lives of millions of people who use digital assistants on a daily basis. Yet, further advances are limited by the availability of data and the…

Human trust in automation plays an essential role in interactions between humans and automation. While a lack of trust can lead to a human's disuse of automation, over-trust can result in a human trusting a faulty autonomous system which…

Segmentation models achieve high accuracy on benchmarks but often fail in real-world domains by relying on spurious correlations instead of true object boundaries. We propose a human-in-the-loop interactive framework that enables…

Models play an essential role in the design process of cyber-physical systems. They form the basis for simulation and analysis and help in identifying design problems as early as possible. However, the construction of models that comprise…

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…

Bayesian optimal experiments that maximize the information gained from collected data are critical to efficiently identify behavioral models. We extend a seminal method for designing Bayesian optimal experiments by introducing two…

Our goal is for agents to optimize the right reward function, despite how difficult it is for us to specify what that is. Inverse Reinforcement Learning (IRL) enables us to infer reward functions from demonstrations, but it usually assumes…

Aligning machine learning systems with human expectations is mostly attempted by training with manually vetted human behavioral samples, typically explicit feedback. This is done on a population level since the context that is capturing the…

Behavioural cloning has been extensively used to train agents and is recognized as a fast and solid approach to teach general behaviours based on expert trajectories. Such method follows the supervised learning paradigm and it strongly…

Domain experts increasingly use automated data science tools to incorporate machine learning (ML) models in their work but struggle to "debug" these models when they are incorrect. For these experts, semantic interactions can provide an…

Observation of other people's choices can provide useful information in many circumstances. However, individuals may not utilize this information efficiently, i.e., they may make decision-making errors in social interactions. In this paper,…

Humans are talented with the ability to perform diverse interactions in the teaching process. However, when humans want to teach AI, existing interactive systems only allow humans to perform repetitive labeling, causing an unsatisfactory…

We often desire our models to be interpretable as well as accurate. Prior work on optimizing models for interpretability has relied on easy-to-quantify proxies for interpretability, such as sparsity or the number of operations required. In…