Federated Learning of Socially Appropriate Agent Behaviours in Simulated Home Environments

TL;DR

This paper introduces new federated learning benchmarks for social robots to learn socially appropriate behaviors across different environments, combining federated and continual learning techniques to improve adaptability.

Contribution

It presents novel federated learning benchmarks for social robot behavior, integrating continual learning to adapt across diverse contexts.

Findings

Federated Averaging (FedAvg) is a robust FL strategy.

Rehearsal-based FCL enables incremental learning of social behaviors.

The benchmarks facilitate evaluation of FL and CL methods in social robotics.

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 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.