Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee

TL;DR

This paper introduces a fault-tolerant federated reinforcement learning framework with proven convergence guarantees, capable of handling system failures and adversarial attacks, validated through empirical experiments.

Contribution

It is the first FRL framework with theoretical convergence guarantees that is resilient to system failures and adversarial attacks.

Findings

Sample efficiency improves with more agents.

Framework tolerates less than half of agents failing or attacking.

Empirical results confirm theoretical guarantees.

Abstract

The growing literature of Federated Learning (FL) has recently inspired Federated Reinforcement Learning (FRL) to encourage multiple agents to federatively build a better decision-making policy without sharing raw trajectories. Despite its promising applications, existing works on FRL fail to I) provide theoretical analysis on its convergence, and II) account for random system failures and adversarial attacks. Towards this end, we propose the first FRL framework the convergence of which is guaranteed and tolerant to less than half of the participating agents being random system failures or adversarial attackers. We prove that the sample efficiency of the proposed framework is guaranteed to improve with the number of agents and is able to account for such potential failures or attacks. All theoretical results are empirically verified on various RL benchmark tasks.