mlsanityData to 14 Oct 2026

Exploration-Driven Personalized Federated Reinforcement Learning via Intrinsic Motivation

arXiv 2608.10499 ↗First posted 11 Aug 2026cs.LG cs.AIcited by 0

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

Abstract (arXiv)

Personalized Federated Reinforcement Learning (PFRL) takes a decentralized approach to storing and accessing information based on past experiences while keeping each client's data private during the learning of each client's policy. Many current methods for PFRL rely heavily on exploiting existing reinforcement learning reward signals to derive an optimal policy for each client, thereby neglecting exploration in non-stationary or sparse-reward environments. In this work, we introduce a new exploration-driven framework, Exploration-Driven Personalized Federated Reinforcement Learning via Intrinsic Motivation (EDPFRL-IM), that leverages an inherent curiosity-driven exploration at each client to promote local exploration and protect client privacy. Furthermore, to facilitate policy discovery via exploration in previously unexplored state spaces, clients add an intrinsic random network distillation (RND) signal to their extrinsic reward. Additionally, the server does not have access to clients' raw experiences or local gradient estimates; instead, the server sends global exploration priors and collects minimal novelty summaries from each client to enable both diverse and coordinated exploration among clients. Experiments in benchmark environments show that our framework outperforms average PFRL benchmarks in policy personalization and sample efficiency, primarily in delayed and sparse reward systems. Overall, EDPFRL-IM enables the integration of a flexible exploratory learning structure into federated reinforcement learning systems while preserving client privacy.

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 6 of its 11 references that are in the map. First posted on arXiv 11 Aug 2026.

Builds on

6 of 11 references.

References · 6

  1. 2020Personalized Federated Learning with Moreau Envelopescited by 618
  2. 2018Count-Based Exploration with the Successor Representationcited by 112
  3. 2022Partially Observable Markov Decision Processes in Robotics: A Surveycited by 86
  4. 2018CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learningcited by 79
  5. 2021Fault-Tolerant Federated Reinforcement Learning with Theoretical Guaranteecited by 54
  6. 2023Anti-Exploration by Random Network Distillationcited by 50

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations
  2. 2026Personalized Observation Normalization for Federated Reinforcement Learning in Simulation Environments with Heterogeneity
  3. 2024FedRLHF: A Convergence-Guaranteed Federated Framework for Privacy-Preserving and Personalized RLHF
  4. 2025FedHPD: Heterogeneous Federated Reinforcement Learning via Policy Distillation
  5. 2026Personalized Federated Reinforcement Learning via Model-Agnostic Meta-Learning: Convergence of Exact and Hessian-Free Meta-Policy Gradients
  6. 2026Can Optimal Transport Improve Federated Inverse Reinforcement Learning?
  7. 2024Individual Contributions as Intrinsic Exploration Scaffolds for Multi-agent Reinforcement Learning
  8. 2025Approximated Behavioral Metric-based State Projection for Federated Reinforcement Learning