Andi Peng
Andi Peng
About
News
Publications
Pragmatic Feature Preferences: Learning Reward-Relevant Preferences from Human Feedback
Andi Peng
,
Yuying Sun
,
Tianmin Shu
,
David Abel
November 2024
Go to Project Site
Type
Conference Paper
Conference
Related
Learning with Language-Guided State Abstractions
Aligning Robot Representations with Humans
Conceptual Feasibility Study of the Hyperloop Vehicle for Next-Generation Transport
Diagnosis, Feedback, Adaptation: A Human-in-the-Loop Framework for Test-Time Policy Adaptation
Human-Guided Complexity-Controlled Abstractions
BibTeX
×