Search Results for author:
Found 2 papers, 0 papers with code
Concept Alignment as a Prerequisite for Value Alignment
Value alignment is essential for building AI systems that can safely and reliably interact with people.
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.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
