mlsanityData to 7 Oct 2026

Multi-Task Federated Reinforcement Learning with Adversaries

arXiv 2103.06473 ↗First posted 11 Mar 2021cs.LG cs.AIcited by 13

Not on the map. Why?

Abstract (arXiv)

Reinforcement learning algorithms, just like any other Machine learning algorithm pose a serious threat from adversaries. The adversaries can manipulate the learning algorithm resulting in non-optimal policies. In this paper, we analyze the Multi-task Federated Reinforcement Learning algorithms, where multiple collaborative agents in various environments are trying to maximize the sum of discounted return, in the presence of adversarial agents. We argue that the common attack methods are not guaranteed to carry out a successful attack on Multi-task Federated Reinforcement Learning and propose an adaptive attack method with better attack performance. Furthermore, we modify the conventional federated reinforcement learning algorithm to address the issue of adversaries that works equally well with and without the adversaries. Experimentation on different small to mid-size reinforcement learning problems show that the proposed attack method outperforms other general attack methods and the proposed modification to federated reinforcement learning algorithm was able to achieve near-optimal policies in the presence of adversarial agents.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 30 of its 50 references that are in the map. First posted on arXiv 11 Mar 2021.

Builds on

30 of 50 references.

References · 30

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2013Intriguing properties of neural networkscited by 5,114
  3. 2016Adversarial examples in the physical worldcited by 1,762
  4. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  5. 2016Adversarial Machine Learning at Scalecited by 934
  6. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  7. 2019Towards Federated Learning at Scale: System Designcited by 826
  8. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  9. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
  10. 2017Robust Adversarial Reinforcement Learningcited by 439
  11. 2018Analyzing Federated Learning through an Adversarial Lenscited by 346
  12. 2017Adversarial Attacks on Neural Network Policiescited by 314
18 more
  1. 2018Feature Denoising for Improving Adversarial Robustnesscited by 312
  2. 2019Adversarial Policies: Attacking Deep Reinforcement Learningcited by 209
  3. 2018A Survey and Critique of Multiagent Deep Reinforcement Learningcited by 173
  4. 2019Action Robust Reinforcement Learning and Applications in Continuous Controlcited by 167
  5. 2017Tactics of Adversarial Attack on Deep Reinforcement Learning Agentscited by 163
  6. 2017Robust Deep Reinforcement Learning with Adversarial Attackscited by 152
  7. 2017Delving into adversarial attacks on deep policiescited by 104
  8. 2019Lifelong Federated Reinforcement Learning: A Learning Architecture for Navigation in Cloud Robotic Systemscited by 77
  9. 2019Policy Poisoning in Batch Reinforcement Learning and Controlcited by 70
  10. 2019Deceptive Reinforcement Learning Under Adversarial Manipulations on Cost Signalscited by 50
  11. 2017Lenient Multi-Agent Deep Reinforcement Learningcited by 35
  12. 2019Federated Deep Reinforcement Learningcited by 34
  13. 2020A Decentralized Policy Gradient Approach to Multi-task Reinforcement Learningcited by 24
  14. 2019Autonomous Navigation via Deep Reinforcement Learning for Resource Constraint Edge Nodes using Transfer Learningcited by 19
  15. 2018Security in Mobile Edge Caching with Reinforcement Learningcited by 9
  16. 2017Federated Control with Hierarchical Multi-Agent Deep Reinforcement Learningcited by 7
  17. 2018NAVREN-RL: Learning to fly in real environment via end-to-end deep reinforcement learning using monocular imagescited by 5
  18. 2018The Faults in Our Pi Stars: Security Issues and Open Challenges in Deep Reinforcement Learningcited by 5

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 2; 2023: 2; 2024: 2; 2025: 5.

13 papers.

Sort:

By area:

  1. 2021Federated Reinforcement Learning: Techniques, Applications, and Open Challengescited by 79
  2. 2021Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AIcited by 38
  3. 2023Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learningcited by 11
  4. 2023Local Environment Poisoning Attacks on Federated Reinforcement Learningcited by 6
  5. 2025Gap-Dependent Bounds for Federated Q-learningcited by 4
  6. 2025Regret-Optimal Q-Learning with Low Cost for Single-Agent and Federated Reinforcement Learningcited by 2
  7. 2022Personalized Federated Hypernetworks for Privacy Preservation in Multi-Task Reinforcement Learningcited by 1
  8. 2024Momentum-Based Federated Reinforcement Learning with Interaction and Communication Efficiencycited by 1
  9. 2024Federated Offline Policy Optimization with Dual Regularizationcited by 1
  10. 2025Adaptive Federated Learning Defences via Trust-Aware Deep Q-Networkscited by 1
  11. 2025Gradient Inversion in Federated Reinforcement Learningcited by 1
  12. 2022FRL-FI: Transient Fault Analysis for Federated Reinforcement Learning-Based Navigation Systemscited by 0
1 more
  1. 2025Approximated Behavioral Metric-based State Projection for Federated Reinforcement Learningcited by 0