Federated Learning of Socially Appropriate Agent Behaviours in Simulated Home Environments

arXiv:2403.07586v1 Announce Type: new
Abstract: 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 …

abstract agent application arxiv become cs.ai cs.cy cs.lg cs.ro daily environments explore federated learning home learn life open-world robots social type world