69 citations · 93 across the 11 of their papers we have counts for
11 papers
Policy-as-logic for robust reasoning over rules
Rahul Nair, Bastian Lipka, Elizabeth Daly
In many practical applications of generative AI systems, from tax rules to airline baggage allowance, responses to natural language queries must respect written policies or rules.…
Iterative Reward Shaping using Human Feedback for Correcting Reward Misspecification
Jasmina Gajcin, James McCarthy, Rahul Nair +3
A well-defined reward function is crucial for successful training of an reinforcement learning (RL) agent. However, defining a suitable reward function is a notoriously challenging…
Co-creating a globally interpretable model with human input
Rahul Nair
We consider an aggregated human-AI collaboration aimed at generating a joint interpretable model. The model takes the form of Boolean decision rules, where human input is provided…
Interpretable Differencing of Machine Learning Models
Swagatam Haldar, Diptikalyan Saha, Dennis Wei +2
Understanding the differences between machine learning (ML) models is of interest in scenarios ranging from choosing amongst a set of competing models, to updating a deployed model…
AutoDOViz: Human-Centered Automation for Decision Optimization
Daniel Karl I. Weidele, Shazia Afzal, Abel N. Valente +12
We present AutoDOViz, an interactive user interface for automated decision optimization (AutoDO) using reinforcement learning (RL). Decision optimization (DO) has classically being…
On the Safety of Interpretable Machine Learning: A Maximum Deviation Approach
Dennis Wei, Rahul Nair, Amit Dhurandhar +3
Interpretable and explainable machine learning has seen a recent surge of interest. We focus on safety as a key motivation behind the surge and make the relationship between interp…
Boolean Decision Rules for Reinforcement Learning Policy Summarisation
James McCarthy, Rahul Nair, Elizabeth Daly +2
Explainability of Reinforcement Learning (RL) policies remains a challenging research problem, particularly when considering RL in a safety context. Understanding the decisions and…
User Driven Model Adjustment via Boolean Rule Explanations
Elizabeth M. Daly, Massimiliano Mattetti, Öznur Alkan +1
AI solutions are heavily dependant on the quality and accuracy of the input training data, however the training data may not always fully reflect the most up-to-date policy landsca…
FROTE: Feedback Rule-Driven Oversampling for Editing Models
Öznur Alkan, Dennis Wei, Massimiliano Mattetti +3
Machine learning models may involve decision boundaries that change over time due to updates to rules and regulations, such as in loan approvals or claims management. However, in s…
Contrastive Explanations for Comparing Preferences of Reinforcement Learning Agents
Jasmina Gajcin, Rahul Nair, Tejaswini Pedapati +3
In complex tasks where the reward function is not straightforward and consists of a set of objectives, multiple reinforcement learning (RL) policies that perform task adequately, b…
Neo: Generalizing Confusion Matrix Visualization to Hierarchical and Multi-Output Labels
Jochen Görtler, Fred Hohman, Dominik Moritz +5
The confusion matrix, a ubiquitous visualization for helping people evaluate machine learning models, is a tabular layout that compares predicted class labels against actual class…