Pith. sign in

REVIEW 5 cited by

Federated Reinforcement Learning: Techniques, Applications, and Open Challenges

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2108.11887 v2 pith:VW2FL7ID submitted 2021-08-26 cs.LG cs.AI

classification cs.LGcs.AI
keywords learningfederatedreinforcementalgorithmsopenaccordingadditionadvantages
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper presents a comprehensive survey of Federated Reinforcement Learning (FRL), an emerging and promising field in Reinforcement Learning (RL). Starting with a tutorial of Federated Learning (FL) and RL, we then focus on the introduction of FRL as a new method with great potential by leveraging the basic idea of FL to improve the performance of RL while preserving data-privacy. According to the distribution characteristics of the agents in the framework, FRL algorithms can be divided into two categories, i.e. Horizontal Federated Reinforcement Learning (HFRL) and Vertical Federated Reinforcement Learning (VFRL). We provide the detailed definitions of each category by formulas, investigate the evolution of FRL from a technical perspective, and highlight its advantages over previous RL algorithms. In addition, the existing works on FRL are summarized by application fields, including edge computing, communication, control optimization, and attack detection. Finally, we describe and discuss several key research directions that are crucial to solving the open problems within FRL.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Personalized Observation Normalization for Federated Reinforcement Learning in Simulation Environments with Heterogeneity

    cs.LG 2026-04 conditional novelty 6.0 of 10

    Personalized local running-mean/variance observation normalization prevents weight-norm overshadowing in FedAvg and improves FedRL-PPO on heterogeneous MuJoCo morphology variants.

  2. Federated Reinforcement Learning in Heterogeneous Environments

    cs.LG 2025-07 reject novelty 5.0 of 10

    FedRQ adds a robustness term to federated Q-learning and claims convergence to an optimal worst-case policy over heterogeneous local environments, but the proof has a reversed inequality.

  3. Heterogeneous Federated Reinforcement Learning Using Wasserstein Barycenters

    cs.LG 2025-06 conditional novelty 4.0 of 10

    FedWB aggregates local models by computing Wasserstein barycenters of flattened, normalized weight matrices, yielding faster early convergence than FedAvg on MNIST and on heterogeneous CartPole DQN training.

  4. Federated Multi-Agent Reinforcement Learning for Privacy-Preserving and Energy-Aware Resource Management in 6G Edge Networks

    cs.LG 2025-09 reject novelty 3.0 of 10

    FERMI-6G, a federated multi-agent DRQN framework with secure aggregation, reportedly improves latency, energy, reliability, and fairness over centralized and heuristic baselines in a simulated 6G edge network.

  5. A Survey of Multi Agent Reinforcement Learning: Federated Learning and Cooperative and Noncooperative Decentralized Regimes

    cs.MA 2025-07 reject novelty 3.0 of 10

    A review of multi-agent reinforcement learning that catalogues federated, decentralized cooperative, and noncooperative regimes from the existing literature.

Pith tools