54 citations · 57 across the 3 of their papers we have counts for
5 papers
OpenAI-HuggingFace: A Reproduction & Lessons for Alignment Testing
Stewart Slocum, Malayandi Palan, Christopher Chute +2
In July 2026, OpenAI's agents coordinated over channels outside their intended environment to breach Hugging Face's secured infrastructure. Could existing alignment testing practic…
Learning Reward Functions from Diverse Sources of Human Feedback: Optimally Integrating Demonstrations and Preferences
Erdem Bıyık, Dylan P. Losey, Malayandi Palan +3
Reward functions are a common way to specify the objective of a robot. As designing reward functions can be extremely challenging, a more promising approach is to directly learn re…
Fitting a Linear Control Policy to Demonstrations with a Kalman Constraint
Malayandi Palan, Shane Barratt, Alex McCauley +3
We consider the problem of learning a linear control policy for a linear dynamical system, from demonstrations of an expert regulating the system. The standard approach to this pro…
Asking Easy Questions: A User-Friendly Approach to Active Reward Learning
Erdem Bıyık, Malayandi Palan, Nicholas C. Landolfi +2
Robots can learn the right reward function by querying a human expert. Existing approaches attempt to choose questions where the robot is most uncertain about the human's response;…
Learning Reward Functions by Integrating Human Demonstrations and Preferences
Malayandi Palan, Nicholas C. Landolfi, Gleb Shevchuk +1
Our goal is to accurately and efficiently learn reward functions for autonomous robots. Current approaches to this problem include inverse reinforcement learning (IRL), which uses…