2022/12/19 by Alane Suhr, Yoav Artzi, Suhr, Alane +1 · 1 voice
Computer Science · #Intelligent Tutoring Systems and Adaptive Learning #Machine Learning and Algorithms #Online Learning and Analytics #cs.AI #cs.CL #cs.LG
paper · pdf · doi:10.48550/arxiv.2212.09710
openalex publication_date 2022/12/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We propose and deploy an approach to continually train an instruction-following agent from feedback provided by users during collaborative interactions. During interaction, human users instruct an agent using natural language, and provide realtime binary feedback as they observe the agent following their instructions. We design a contextual bandit learning approach, converting user feedback to immediate reward. We evaluate through thousands of human-agent interactions, demonstrating 15.4% absolute improvement in instruction execution accuracy over time. We also show our approach is robust to several design variations, and that the feedback signal is roughly equivalent to the learning signal of supervised demonstration data.