Adaptive Querying for Reward Learning from Human Feedback

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Anand, Yashwanthi, Nwagwu, Nnamdi, Sabbe, Kevin, Fitter, Naomi T., Saisubramanian, Sandhya
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909990526124032
author Anand, Yashwanthi
Nwagwu, Nnamdi
Sabbe, Kevin
Fitter, Naomi T.
Saisubramanian, Sandhya
author_facet Anand, Yashwanthi
Nwagwu, Nnamdi
Sabbe, Kevin
Fitter, Naomi T.
Saisubramanian, Sandhya
contents Learning from human feedback is a popular approach to train robots to adapt to user preferences and improve safety. Existing approaches typically consider a single querying (interaction) format when seeking human feedback and do not leverage multiple modes of user interaction with a robot. We examine how to learn a penalty function associated with unsafe behaviors using multiple forms of human feedback, by optimizing both the query state and feedback format. Our proposed adaptive feedback selection is an iterative, two-phase approach which first selects critical states for querying, and then uses information gain to select a feedback format for querying across the sampled critical states. The feedback format selection also accounts for the cost and probability of receiving feedback in a certain format. Our experiments in simulation demonstrate the sample efficiency of our approach in learning to avoid undesirable behaviors. The results of our user study with a physical robot highlight the practicality and effectiveness of adaptive feedback selection in seeking informative, user-aligned feedback that accelerate learning. Experiment videos, code and appendices are found on our website: https://tinyurl.com/AFS-learning.
format Preprint
id arxiv_https___arxiv_org_abs_2412_07990
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Adaptive Querying for Reward Learning from Human Feedback
Anand, Yashwanthi
Nwagwu, Nnamdi
Sabbe, Kevin
Fitter, Naomi T.
Saisubramanian, Sandhya
Robotics
Artificial Intelligence
Machine Learning
Learning from human feedback is a popular approach to train robots to adapt to user preferences and improve safety. Existing approaches typically consider a single querying (interaction) format when seeking human feedback and do not leverage multiple modes of user interaction with a robot. We examine how to learn a penalty function associated with unsafe behaviors using multiple forms of human feedback, by optimizing both the query state and feedback format. Our proposed adaptive feedback selection is an iterative, two-phase approach which first selects critical states for querying, and then uses information gain to select a feedback format for querying across the sampled critical states. The feedback format selection also accounts for the cost and probability of receiving feedback in a certain format. Our experiments in simulation demonstrate the sample efficiency of our approach in learning to avoid undesirable behaviors. The results of our user study with a physical robot highlight the practicality and effectiveness of adaptive feedback selection in seeking informative, user-aligned feedback that accelerate learning. Experiment videos, code and appendices are found on our website: https://tinyurl.com/AFS-learning.
title Adaptive Querying for Reward Learning from Human Feedback
topic Robotics
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2412.07990