Saved in:
Bibliographic Details
Main Authors: Checker, Saksham, Churamani, Nikhil, Gunes, Hatice
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.07586
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909134753890304
author Checker, Saksham
Churamani, Nikhil
Gunes, Hatice
author_facet Checker, Saksham
Churamani, Nikhil
Gunes, Hatice
contents As social robots become increasingly integrated into daily life, ensuring their behaviours align with social norms is crucial. For their widespread open-world application, it is important to explore Federated Learning (FL) settings where individual robots can learn about their unique environments while also learning from each others' experiences. In this paper, we present a novel FL benchmark that evaluates different strategies, using multi-label regression objectives, where each client individually learns to predict the social appropriateness of different robot actions while also sharing their learning with others. Furthermore, splitting the training data by different contexts such that each client incrementally learns across contexts, we present a novel Federated Continual Learning (FCL) benchmark that adapts FL-based methods to use state-of-the-art Continual Learning (CL) methods to continually learn socially appropriate agent behaviours under different contextual settings. Federated Averaging (FedAvg) of weights emerges as a robust FL strategy while rehearsal-based FCL enables incrementally learning the social appropriateness of robot actions, across contextual splits.
format Preprint
id arxiv_https___arxiv_org_abs_2403_07586
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Federated Learning of Socially Appropriate Agent Behaviours in Simulated Home Environments
Checker, Saksham
Churamani, Nikhil
Gunes, Hatice
Machine Learning
Artificial Intelligence
Computers and Society
Robotics
As social robots become increasingly integrated into daily life, ensuring their behaviours align with social norms is crucial. For their widespread open-world application, it is important to explore Federated Learning (FL) settings where individual robots can learn about their unique environments while also learning from each others' experiences. In this paper, we present a novel FL benchmark that evaluates different strategies, using multi-label regression objectives, where each client individually learns to predict the social appropriateness of different robot actions while also sharing their learning with others. Furthermore, splitting the training data by different contexts such that each client incrementally learns across contexts, we present a novel Federated Continual Learning (FCL) benchmark that adapts FL-based methods to use state-of-the-art Continual Learning (CL) methods to continually learn socially appropriate agent behaviours under different contextual settings. Federated Averaging (FedAvg) of weights emerges as a robust FL strategy while rehearsal-based FCL enables incrementally learning the social appropriateness of robot actions, across contextual splits.
title Federated Learning of Socially Appropriate Agent Behaviours in Simulated Home Environments
topic Machine Learning
Artificial Intelligence
Computers and Society
Robotics
url https://arxiv.org/abs/2403.07586