Decentralized Federated Policy Gradient with Byzantine Fault-Tolerance and Provably Fast Convergence

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jordan, Philip, Grötschla, Florian, Fan, Flint Xiaofeng, Wattenhofer, Roger
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910289934417920
author Jordan, Philip
Grötschla, Florian
Fan, Flint Xiaofeng
Wattenhofer, Roger
author_facet Jordan, Philip
Grötschla, Florian
Fan, Flint Xiaofeng
Wattenhofer, Roger
contents In Federated Reinforcement Learning (FRL), agents aim to collaboratively learn a common task, while each agent is acting in its local environment without exchanging raw trajectories. Existing approaches for FRL either (a) do not provide any fault-tolerance guarantees (against misbehaving agents), or (b) rely on a trusted central agent (a single point of failure) for aggregating updates. We provide the first decentralized Byzantine fault-tolerant FRL method. Towards this end, we first propose a new centralized Byzantine fault-tolerant policy gradient (PG) algorithm that improves over existing methods by relying only on assumptions standard for non-fault-tolerant PG. Then, as our main contribution, we show how a combination of robust aggregation and Byzantine-resilient agreement methods can be leveraged in order to eliminate the need for a trusted central entity. Since our results represent the first sample complexity analysis for Byzantine fault-tolerant decentralized federated non-convex optimization, our technical contributions may be of independent interest. Finally, we corroborate our theoretical results experimentally for common RL environments, demonstrating the speed-up of decentralized federations w.r.t. the number of participating agents and resilience against various Byzantine attacks.
format Preprint
id arxiv_https___arxiv_org_abs_2401_03489
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Decentralized Federated Policy Gradient with Byzantine Fault-Tolerance and Provably Fast Convergence
Jordan, Philip
Grötschla, Florian
Fan, Flint Xiaofeng
Wattenhofer, Roger
Machine Learning
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
Multiagent Systems
In Federated Reinforcement Learning (FRL), agents aim to collaboratively learn a common task, while each agent is acting in its local environment without exchanging raw trajectories. Existing approaches for FRL either (a) do not provide any fault-tolerance guarantees (against misbehaving agents), or (b) rely on a trusted central agent (a single point of failure) for aggregating updates. We provide the first decentralized Byzantine fault-tolerant FRL method. Towards this end, we first propose a new centralized Byzantine fault-tolerant policy gradient (PG) algorithm that improves over existing methods by relying only on assumptions standard for non-fault-tolerant PG. Then, as our main contribution, we show how a combination of robust aggregation and Byzantine-resilient agreement methods can be leveraged in order to eliminate the need for a trusted central entity. Since our results represent the first sample complexity analysis for Byzantine fault-tolerant decentralized federated non-convex optimization, our technical contributions may be of independent interest. Finally, we corroborate our theoretical results experimentally for common RL environments, demonstrating the speed-up of decentralized federations w.r.t. the number of participating agents and resilience against various Byzantine attacks.
title Decentralized Federated Policy Gradient with Byzantine Fault-Tolerance and Provably Fast Convergence
topic Machine Learning
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
Multiagent Systems
url https://arxiv.org/abs/2401.03489