Federated Distributional Reinforcement Learning with Distributional Critic Regularization

• URL: http://arxiv.org/abs/2603.17820v1
• Date: Wed, 18 Mar 2026 15:12:21 GMT
• Title: Federated Distributional Reinforcement Learning with Distributional Critic Regularization
• Abstract summary: Federated reinforcement learning typically aggregates value functions or policies by parameter averaging.<n>We formalizeFedDistRL, where clients parametrize quantile value function critics and federate these networks only.<n>We also propose TR-FedDistRL, which builds a per client, risk-aware Wasserstein barycenter over a temporal buffer.
• Score: 9.308789032903153
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Federated reinforcement learning typically aggregates value functions or policies by parameter averaging, which emphasizes expected return and can obscure statistical multimodality and tail behavior that matter in safety-critical settings. We formalize federated distributional reinforcement learning (FedDistRL), where clients parametrize quantile value function critics and federate these networks only. We also propose TR-FedDistRL, which builds a per client, risk-aware Wasserstein barycenter over a temporal buffer. This local barycenter provides a reference region to constrain the parameter averaged critic, ensuring necessary distributional information is not averaged out during the federation process. The distributional trust region is implemented as a shrink-squash step around this reference. Under fixed-policy evaluation, the feasibility map is nonexpansive and the update is contractive in a probe-set Wasserstein metric under evaluation. Experiments on a bandit, multi-agent gridworld, and continuous highway environment show reduced mean-smearing, improved safety proxies (catastrophe/accident rate), and lower critic/policy drift versus mean-oriented and non-federated baselines.

Related papers

• Robust Decentralized Personalized Federated Learning via Prediction-Constrained Neighborhood Collaboration [13.638928692851726]
  This paper proposes a robust decentralized personalized federated learning method R-DPFL.<n>It enables clients to reduce the impact of Byzantine attacks via robust neighborhood direction estimation and history-based update trend prediction.
  arXiv  Detail & Related papers  (2026-09-07T10:29:27Z)
• Conformal Changepoint Localization and Root Cause Analysis with Corrupted Observations [55.76952683833966]
  This paper proposes weighted CONCH (W-CONCH) and weighted CROC (W-CROC) to reduce confidence set size when data may be corrupted.<n>Experiments on image-based and real-world changepoint and root-cause benchmarks show that uncertainty-based weighting substantially reduces confidence set size.
  arXiv  Detail & Related papers  (2026-07-29T05:16:59Z)
• Rethinking the Divergence Regularization in LLM RL [56.952725733148746]
  Reinforcement learning (RL) has become a key component of post-training large language models (LLMs)<n>We propose Divergence Regularized Policy Optimization (DRPO), which replaces the hard mask with a smooth advantage-weighted quadratic regularizer on policy shift.<n>DRPO preserves the same trust-region geometry as DPPO while inducing bounded, continuous gradient weights.
  arXiv  Detail & Related papers  (2026-06-08T17:58:23Z)
• OmniISR: A Unified Framework for Centralized and Federated Learning via Intermediate Supervision and Regularization [58.03221830946145]
  We propose OmniISR, a unified framework that fuses pure CL, pure FL, and hybrid CL-FL training modes.<n>We show that OmniISR consistently improves model performance in both centralized and federated paradigms.
  arXiv  Detail & Related papers  (2026-05-19T04:13:27Z)
• Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training [50.86545293331458]
  Reinforcement learning is structurally harder than supervised learning because the policy changes the data distribution it learns from.<n>We present a simple yet effective batch-adaptive objective that replaces fixed clipping with the normalized effective sample size of the policy ratios.
  arXiv  Detail & Related papers  (2026-05-12T16:44:47Z)
• Improving Search Agent with One Line of Code [68.58667107354253]
  Tool-based Agentic Reinforcement Learning (TARL) has emerged as a promising paradigm for training search agents to interact with external tools.<n>We propose textbfSearch textbfAgent textbfPolicy textbfOptimization (textbfSAPO), which stabilizes training via a conditional token-level KL constraint.
  arXiv  Detail & Related papers  (2026-03-10T04:07:39Z)
• BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning [49.25750348525603]
  BandPO replaces canonical clipping with Band, a unified theoretical operator that projects trust regions into dynamic, probability-aware clipping intervals.<n>We show that BandPO consistently outperforms canonical clipping and Clip-Higher, while robustly mitigating entropy collapse.
  arXiv  Detail & Related papers  (2026-03-05T08:03:05Z)
• DFPO: Scaling Value Modeling via Distributional Flow towards Robust and Generalizable LLM Post-Training [94.568675548967]
  Training reinforcement learning (RL) systems in real-world environments remains challenging due to noisy supervision and poor out-of-domain generalization.<n>Recent distributional RL methods improve robustness by modeling values with multiple quantile points, but they still learn each quantile independently as a scalar.<n>We propose DFPO, a robust distributional RL framework that models values as continuous flows across time steps.
  arXiv  Detail & Related papers  (2026-02-05T17:07:42Z)
• FedGreed: A Byzantine-Robust Loss-Based Aggregation Method for Federated Learning [1.3853653640712935]
  Federated Learning (FL) enables collaborative model training across multiple clients while preserving data privacy by keeping local datasets on-device.<n>In this work, we address FL settings where clients may behave adversarially, exhibiting Byzantine attacks, while the central server is trusted and equipped with a reference dataset.<n>We propose FedGreed, a resilient aggregation strategy for federated learning that does not require any assumptions about the fraction of adversarial participants.
  arXiv  Detail & Related papers  (2025-08-25T14:20:19Z)
• Don't Reach for the Stars: Rethinking Topology for Resilient Federated Learning [1.3270838622986498]
  Federated learning (FL) enables collaborative model training across distributed clients while preserving data privacy by keeping data local.<n>Traditional FL approaches rely on a centralized, star-shaped topology, where a central server aggregates model updates from clients.<n>We propose a decentralized, peer-to-peer (P2P) FL framework to enable each client to identify and aggregate a personalized set of trustworthy and beneficial updates.
  arXiv  Detail & Related papers  (2025-08-07T10:10:37Z)
• Personalized Bayesian Federated Learning with Wasserstein Barycenter Aggregation [8.988135979947947]
  FedWBA is a novel PBFL method that enhances both local inference and global aggregation.<n>We provide local and global convergence guarantees for FedWBA.<n>Experiments show that FedWBA outperforms baselines in prediction accuracy, uncertainty calibration, and convergence rate.
  arXiv  Detail & Related papers  (2025-05-20T10:14:32Z)
• Off-Policy Evaluation in Markov Decision Processes under Weak Distributional Overlap [3.351714665243138]
  We re-visit the task of off-policy evaluation in Markov decision processes (MDPs) under a weaker notion of distributional overlap.<n>We introduce a class of truncated doubly robust (TDR) estimators which we find to perform well in this setting.<n>We find that, in our experiments, appropriate truncation plays a major role in enabling accurate off-policy evaluation when strong distributional overlap does not hold.
  arXiv  Detail & Related papers  (2024-02-13T03:55:56Z)
• Acceleration of Federated Learning with Alleviated Forgetting in Local Training [61.231021417674235]
  Federated learning (FL) enables distributed optimization of machine learning models while protecting privacy. We propose FedReg, an algorithm to accelerate FL with alleviated knowledge forgetting in the local training stage. Our experiments demonstrate that FedReg not only significantly improves the convergence rate of FL, especially when the neural network architecture is deep.
  arXiv  Detail & Related papers  (2022-03-05T02:31:32Z)
• Learning Calibrated Uncertainties for Domain Shift: A Distributionally Robust Learning Approach [150.8920602230832]
  We propose a framework for learning calibrated uncertainties under domain shifts. In particular, the density ratio estimation reflects the closeness of a target (test) sample to the source (training) distribution. We show that our proposed method generates calibrated uncertainties that benefit downstream tasks.
  arXiv  Detail & Related papers  (2020-10-08T02:10:54Z)
• Implicit Distributional Reinforcement Learning [61.166030238490634]
  implicit distributional actor-critic (IDAC) built on two deep generator networks (DGNs) Semi-implicit actor (SIA) powered by a flexible policy distribution. We observe IDAC outperforms state-of-the-art algorithms on representative OpenAI Gym environments.
  arXiv  Detail & Related papers  (2020-07-13T02:52:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.