Provably Robust Federated Reinforcement Learning

Abstract

Federated reinforcement learning (FRL) allows agents to jointly learn a global decision-making policy under the guidance of a central server. While FRL has advantages, its decentralized design makes it prone to poisoning attacks. To mitigate this, Byzantine-robust aggregation techniques tailored for FRL have been introduced. Yet, in our work, we reveal that these current Byzantine-robust techniques are not immune to our newly introduced Normalized attack. Distinct from previous attacks that targeted enlarging the distance of policy updates before and after an attack, our Normalized attack emphasizes on maximizing the angle of deviation between these updates. To counter these threats, we develop an ensemble FRL approach that is provably secure against both known and our newly proposed attacks. Our ensemble method involves training multiple global policies, where each is learnt by a group of agents using any foundational aggregation rule. These well-trained global policies then individua

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyfang2025provably

Related papers

• Local Environment Poisoning Attacks On Federated Reinforcement Learning (2023)0.00
• Global Convergence Guarantees For Federated Policy Gradient Methods With Adversaries (2024)0.00
• Fault-tolerant Federated Reinforcement Learning With Theoretical Guarantee (2021)0.00
• Federated Ensemble Model-based Reinforcement Learning In Edge Computing (2021)11.58
• Federated Offline Policy Optimization With Dual Regularization (2024)3.58
• Momentum For The Win: Collaborative Federated Reinforcement Learning Across Heterogeneous Environments (2024)0.00
• Multi-task Federated Reinforcement Learning With Adversaries (2021)0.00
• Fedhpd: Heterogeneous Federated Reinforcement Learning Via Policy Distillation (2025)2.26