mlsanityData to 14 Oct 2026

Approximated Behavioral Metric-based State Projection for Federated Reinforcement Learning

arXiv 2505.09959 ↗First posted 15 May 2025cs.LGcited by 0

On the map: Deep reinforcement learning methods → RL for energy, networks and operations

Abstract (arXiv)

Federated reinforcement learning (FRL) methods usually share the encrypted local state or policy information and help each client to learn from others while preserving everyone's privacy. In this work, we propose that sharing the approximated behavior metric-based state projection function is a promising way to enhance the performance of FRL and concurrently provides an effective protection of sensitive information. We introduce FedRAG, a FRL framework to learn a computationally practical projection function of states for each client and aggregating the parameters of projection functions at a central server. The FedRAG approach shares no sensitive task-specific information, yet provides information gain for each client. We conduct extensive experiments on the DeepMind Control Suite to demonstrate insightful results.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods. Builds on 33 of its 47 references that are in the map. First posted on arXiv 15 May 2025.

Builds on

33 of 47 references.

References · 33

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  4. 2016Deep Learning with Differential Privacycited by 2,728
  5. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  6. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,240
  7. 2020Adaptive Federated Optimizationcited by 1,046
  8. 2019Deep Leakage from Gradientscited by 1,021
  9. 2018DeepMind Control Suitecited by 956
  10. 2021Model-Contrastive Federated Learningcited by 766
  11. 2020Personalized Federated Learning with Moreau Envelopescited by 618
  12. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 541
21 more
  1. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 536
  2. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 459
  3. 2020Learning Invariant Representations for Reinforcement Learning without Reconstructioncited by 436
  4. 2019A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protectioncited by 374
  5. 2020Think Locally, Act Globally: Federated Learning with Local and Global Representationscited by 325
  6. 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 210
  7. 2020Threats to Federated Learning: A Surveycited by 178
  8. 2022Federated Learning from Pre-Trained Models: A Contrastive Learning Approachcited by 142
  9. 2019Scalable methods for computing state similarity in deterministic Markov Decision Processescited by 133
  10. 2021Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learningcited by 123
  11. 2020Federated Unsupervised Representation Learningcited by 93
  12. 2021Federated Reinforcement Learning: Techniques, Applications, and Open Challengescited by 81
  13. 2022Federated Reinforcement Learning with Environment Heterogeneitycited by 63
  14. 2021Fault-Tolerant Federated Reinforcement Learning with Theoretical Guaranteecited by 54
  15. 2021Towards Robust Bisimulation Metric Learningcited by 49
  16. 2021MICo: Improved representations via sampling-based state similarity for Markov decision processescited by 43
  17. 2022No Free Lunch Theorem for Security and Utility in Federated Learningcited by 39
  18. 2019Federated Deep Reinforcement Learningcited by 35
  19. 2021Multi-Task Federated Reinforcement Learning with Adversariescited by 13
  20. 2024TurboSVM-FL: Boosting Federated Learning through SVM Aggregation for Lazy Clientscited by 7
  21. 2023FedHQL: Federated Heterogeneous Q-Learningcited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024FedRLHF: A Convergence-Guaranteed Federated Framework for Privacy-Preserving and Personalized RLHF
  2. 2025FedHPD: Heterogeneous Federated Reinforcement Learning via Policy Distillation
  3. 2026FedQHD: Closed-Form Function-Space Federated Reinforcement Learning
  4. 2025Federated Reinforcement Learning in Heterogeneous Environments
  5. 2025Collaborative Value Function Estimation Under Model Mismatch: A Federated Temporal Difference Analysis
  6. 2024Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning
  7. 2026Provably Efficient Federated Reinforcement Learning with Linear Function Approximation and Logarithmic Communication Cost
  8. 2024Momentum for the Win: Collaborative Federated Reinforcement Learning across Heterogeneous Environments