Learning Reward Functions from Scale FeedbackDownload PDF

Published: 13 Sept 2021, Last Modified: 12 Mar 2024CoRL2021 PosterReaders: Everyone
Keywords: HRI, reward learning, learning from choice, active learning
Abstract: Today's robots are increasingly interacting with people and need to efficiently learn inexperienced user's preferences. A common framework is to iteratively query the user about which of two presented robot trajectories they prefer. While this minimizes the users effort, a strict choice does not yield any information on how much one trajectory is preferred. We propose scale feedback, where the user utilizes a slider to give more nuanced information. We introduce a probabilistic model on how users would provide feedback and derive a learning framework for the robot. We demonstrate the performance benefit of slider feedback in simulations, and validate our approach in two user studies suggesting that scale feedback enables more effective learning in practice.
Supplementary Material: zip
Poster: png
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/arxiv:2110.00284/code)
19 Replies