Normalization

2 items

RESEARCHarXiv CS.LG·12d ago

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

The paper introduces a personalized observation normalization (PON) method for federated reinforcement learning (FedRL) to address challenges in heterogeneous environments. PON allows each agent to locally normalize state inputs, ensuring consistent scaling and improving performance in heterogeneous MuJoCo tasks.

reinforcement learning machine learning federated learning Normalization

RESEARCHDEV.to AI·4/28/2026

A Large-Scale Study on Regularization and Normalization in GANs

This large-scale study investigates the effectiveness of various regularization and normalization techniques in Generative Adversarial Networks (GANs). It aims to deepen the understanding of how these methods impact GAN training stability and quality.

GANs machine learning Normalization regularization