notesum.ai

Published at December 6

Maximizing Alignment with Minimal Feedback: Efficiently Learning Rewards for Visuomotor Robot Policy Alignment

cs.RO
cs.AI
cs.CV
cs.LG

Released Date: December 6, 2024

Authors: Ran Tian1, Yilin Wu2, Chenfeng Xu, Masayoshi Tomizuka, Jitendra Malik, Andrea Bajcsy

Aff.: 1UC Berkeley; 2Carnegie Mellon University

Arxiv: http://arxiv.org/pdf/2412.04835v1