Search Results for author:
Found 30 papers, 9 papers with code
Grounding Language Plans in Demonstrations Through Counterfactual Perturbations
Grounding the common-sense reasoning of Large Language Models in physical domains remains a pivotal yet unsolved problem for embodied AI.
Understanding Entrainment in Human Groups: Optimising Human-Robot Collaboration from Lessons Learned during Human-Human Collaboration
This paper contributes to the Human-Computer/Robot Interaction (HCI/HRI) literature using a human-centred approach to identify characteristics of entrainment during pair- and group-based collaboration.
An Information Bottleneck Characterization of the Understanding-Workload Tradeoff
This empirical link between human factors and information-theoretic concepts provides an important mathematical characterization of the workload-understanding tradeoff which enables user-tailored XAI design.
Diagnosis, Feedback, Adaptation: A Human-in-the-Loop Framework for Test-Time Policy Adaptation
Policies often fail due to distribution shift -- changes in the state and reward that occur when a policy is deployed in new environments.
Towards Collaborative Plan Acquisition through Theory of Mind Modeling in Situated Dialogue
To complete these tasks, agents need to engage in situated communication with their partners and coordinate their partial plans towards a complete plan to achieve a joint task goal.
Aligning Robot and Human Representations
To act in the world, robots rely on a representation of salient task aspects: for example, to carry a coffee mug, a robot may consider movement efficiency or mug orientation in its behavior.
Artificial Intelligence and Life in 2030: The One Hundred Year Study on Artificial Intelligence
In September 2016, Stanford's "One Hundred Year Study on Artificial Intelligence" project (AI100) issued the first report of its planned long-term periodic assessment of artificial intelligence (AI) and its impact on society.
Gathering Strength, Gathering Storms: The One Hundred Year Study on Artificial Intelligence (AI100) 2021 Study Panel Report
In September 2021, the "One Hundred Year Study on Artificial Intelligence" project (AI100) issued the second report of its planned long-term periodic assessment of artificial intelligence (AI) and its impact on society.
Towards Human-Agent Communication via the Information Bottleneck Principle
Emergent communication research often focuses on optimizing task-specific utility as a driver for communication.
Temporal Logic Imitation: Learning Plan-Satisficing Motion Policies from Demonstrations
In this work, we identify the roots of this challenge as the failure of a learned continuous policy to satisfy the discrete plan implicit in the demonstration.
Prototype Based Classification from Hierarchy to Fairness
Artificial neural nets can represent and classify many types of data but are often tailored to particular applications -- e. g., for "fair" or "hierarchical" classification.
The Solvability of Interpretability Evaluation Metrics
Feature attribution methods are popular for explaining neural network predictions, and they are often evaluated on metrics such as comprehensiveness and sufficiency.
ExSum: From Local Explanations to Model Understanding
Interpretability methods are developed to understand the working mechanisms of black-box models, which is crucial to their responsible deployment.
When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes
Recent causal probing literature reveals when language models and syntactic probes use similar representations.
Probe-Based Interventions for Modifying Agent Behavior
Neural nets are powerful function approximators, but the behavior of a given neural net, once trained, cannot be easily modified.
The Irrationality of Neural Rationale Models
We call for more rigorous and comprehensive evaluations of these models to ensure desired properties of interpretability are indeed achieved.
Explaining Reward Functions to Humans for Better Human-Robot Collaboration
One context where human understanding of agent reward functions is particularly beneficial is in the value alignment setting.
Emergent Discrete Communication in Semantic Spaces
Neural agents trained in reinforcement learning settings can learn to communicate among themselves via discrete tokens, accomplishing as a team what agents would be unable to do alone.
Supervised Bayesian Specification Inference from Demonstrations
When observing task demonstrations, human apprentices are able to identify whether a given task is executed correctly long before they gain expertise in actually performing that task.
Do Feature Attribution Methods Correctly Attribute Features?
Feature attribution methods are exceedingly popular in interpretable machine learning.
A Bayesian Approach to Identifying Representational Errors
Trained AI systems and expert decision makers can make errors that are often difficult to identify and understand.
Interactive Robot Training for Non-Markov Tasks
Defining sound and complete specifications for robots using formal languages is challenging, while learning formal specifications directly from demonstrations can lead to over-constrained task policies.
Bayes-TrEx: a Bayesian Sampling Approach to Model Transparency by Example
To address these challenges, we introduce a flexible model inspection framework: Bayes-TrEx.
Adversarially Guided Self-Play for Adopting Social Conventions
Robotic agents must adopt existing social conventions in order to be effective teammates.
Sampling Prediction-Matching Examples in Neural Networks: A Probabilistic Programming Approach
In this paper, we consider the problem of exploring the prediction level sets of a classifier using probabilistic programming.
Discovering Blind Spots in Reinforcement Learning
Agents trained in simulation may make errors in the real world due to mismatches between training and execution environments.
Human-Machine Collaborative Optimization via Apprenticeship Scheduling
We empirically demonstrate that this approach accurately learns multifaceted heuristics on a synthetic data set incorporating job-shop scheduling and vehicle routing problems, as well as on two real-world data sets consisting of demonstrations of experts solving a weapon-to-target assignment problem and a hospital resource allocation problem.
The Bayesian Case Model: A Generative Approach for Case-Based Reasoning and Prototype Classification
We present the Bayesian Case Model (BCM), a general framework for Bayesian case-based reasoning (CBR) and prototype classification and clustering.
Efficient Model Learning for Human-Robot Collaborative Tasks
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.
Inferring Robot Task Plans from Human Team Meetings: A Generative Modeling Approach with Logic-Based Prior
We present an algorithm that reduces this translation burden by inferring the final plan from a processed form of the human team's planning conversation.
