3 citations · 4 across the 6 of their papers we have counts for
7 papers
AI Safety via Debate is Compromised by Cognitive Biases
Gefei Liu, Sonya Rashkovan, Sophia Lloyd George +2
Reinforcement learning from human feedback (RLHF) has played a central role in making large language models responsive to human instructions. However, human evaluators often favor…
How Users Understand Robot Foundation Model Performance through Task Success Rates and Beyond
Isaac Sheidlower, Jindan Huang, James Staley +4
Robot Foundation Models (RFMs) represent a promising approach to developing general-purpose home robots. Given the broad capabilities of RFMs, users will inevitably ask an RFM-base…
On the Effect of Robot Errors on Human Teaching Dynamics
Jindan Huang, Isaac Sheidlower, Reuben M. Aronson +1
Human-in-the-loop learning is gaining popularity, particularly in the field of robotics, because it leverages human knowledge about real-world tasks to facilitate agent learning. W…
Online Behavior Modification for Expressive User Control of RL-Trained Robots
Isaac Sheidlower, Mavis Murdock, Emma Bethel +2
Reinforcement Learning (RL) is an effective method for robots to learn tasks. However, in typical RL, end-users have little to no control over how the robot does the task after the…
Towards Interpretable Foundation Models of Robot Behavior: A Task Specific Policy Generation Approach
Isaac Sheidlower, Reuben Aronson, Elaine Schaertl Short
Foundation models are a promising path toward general-purpose and user-friendly robots. The prevalent approach involves training a generalist policy that, like a reinforcement lear…
Imagining In-distribution States: How Predictable Robot Behavior Can Enable User Control Over Learned Policies
Isaac Sheidlower, Emma Bethel, Douglas Lilly +2
It is crucial that users are empowered to take advantage of the functionality of a robot and use their understanding of that functionality to perform novel and creative tasks. Give…
Modifying RL Policies with Imagined Actions: How Predictable Policies Can Enable Users to Perform Novel Tasks
Isaac Sheidlower, Reuben Aronson, Elaine Short
It is crucial that users are empowered to use the functionalities of a robot to creatively solve problems on the fly. A user who has access to a Reinforcement Learning (RL) based r…