Federated Learning of Socially Appropriate Agent Behaviours in Simulated Home Environments

1 code implementation • 12 Mar 2024 • Saksham Checker, Nikhil Churamani, Hatice Gunes

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.

Continual Learning Federated Learning