Cover Image

When Learning Rates Go Wrong: Early Structural Signals in PPO Actor-Critic

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fernández-Hernández, Alberto, Pérez-Corral, Cristian, Mestre, Jose I., Dolz, Manuel F., Duato, Jose, Quintana-Ortí, Enrique S.
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

OUI as a Structural Observable: Towards an Activation-Centric View of Neural Network Training
by: Fernández-Hernández, Alberto, et al.
Published: (2026)

OUIDecay: Adaptive Layer-wise Weight Decay for CNNs Using Online Activation Patterns
by: Fernández-Hernández, Alberto, et al.
Published: (2026)

FedOUI: OUI-Guided Client Weighting for Federated Aggregation
by: Fernández-Hernández, Alberto, et al.
Published: (2026)

GLAI: GreenLightningAI for Accelerated Training through Knowledge Decoupling
by: Mestre, Jose I., et al.
Published: (2025)

Regime Change Hypothesis: Foundations for Decoupled Dynamics in Neural Network Training
by: Pérez-Corral, Cristian, et al.
Published: (2026)

FedSQ: Optimized Weight Averaging via Fixed Gating
by: Pérez-Corral, Cristian, et al.
Published: (2026)

OUI Need to Talk About Weight Decay: A New Perspective on Overfitting Detection
by: Fernández-Hernández, Alberto, et al.
Published: (2025)

Sinusoidal Initialization, Time for a New Start
by: Fernández-Hernández, Alberto, et al.
Published: (2025)

Refresh-Scaling the Memory of Balanced Adam
by: Fernández-Hernández, Alberto, et al.
Published: (2026)

$λ$-GELU: Learning Gating Hardness for Controlled ReLU-ization in Deep Networks
by: Pérez-Corral, Cristian, et al.
Published: (2026)

StableGrad: Backward Scale Control without Batch Normalization
by: Mestre, Jose I., et al.
Published: (2026)

Why Adam Works Better with $β_1 = β_2$: The Missing Gradient Scale Invariance Principle
by: Fernández-Hernández, Alberto, et al.
Published: (2026)

Detecting Atypical Clients in Federated Learning via Representation-Level Divergence
by: Pérez-Corral, Cristian, et al.
Published: (2026)

The Actor-Critic Update Order Matters for PPO in Federated Reinforcement Learning
by: Xie, Zhijie, et al.
Published: (2025)

Mapping Parallel Matrix Multiplication in GotoBLAS2 to the AMD Versal ACAP for Deep Learning
by: Lei, Jie, et al.
Published: (2024)

Performance Analysis of Matrix Multiplication for Deep Learning on the Edge
by: Ramírez, Cristian, et al.
Published: (2024)

The Wrong Way to Go.
by: Wright, H. Curtis
Published: (1979)

Go/NoGo training improves executive functions in an 8-year-old child born preterm
by: Cristian Pérez-Fernández
Published: (2017)

When PINNs Go Wrong: Pseudo-Time Stepping Against Spurious Solutions
by: Wang, Sifan, et al.
Published: (2026)

Post‐Artesunate Delayed Hemolysis: Anything That Can Go Wrong Will Go Wrong—Murphy's Law
by: Beliza Chemutai, et al.
Published: (2024)

Fast Truncated SVD of Sparse and Dense Matrices on Graphics Processors
by: Tomas, Andres E., et al.
Published: (2024)

"Why Girls Go Wrong": Advising Female Teen Readers in the Early Twentieth Century
by: Pierce, Jennifer Burek
Published: (2007)

Implementing Basic Arithmetic in $\mathbb{F}_p$ via $\mathbb{F}_2$, and Its Application for Computing the Hamming Distance of Linear Codes
by: Hernando, Fernando, et al.
Published: (2026)

Taxa de contaminação de testes hematológicos e seus fatores determinantes
by: José Enrique De La Rubia-Ortí
Published: (2014)

When Prompts Go Wrong: Evaluating Code Model Robustness to Ambiguous, Contradictory, and Incomplete Task Descriptions
by: Larbi, Maya, et al.
Published: (2025)

Exploiting nested task-parallelism in the $\mathcal{H}-LU$ factorization
by: Carratalá-Sáez, Rocío, et al.
Published: (2019)

Chapter (When) Is Adblocking Wrong?
by: Douglas, Thomas
Published: (2022)

When Abundance Goes Wrong
by: Lee Skallerup Bessette
Published: (2024)

Actor-Critic without Actor
by: Ki, Donghyeon, et al.
Published: (2025)

ExeChecker: Where Did I Go Wrong?
by: Gu, Yiwen, et al.
Published: (2024)

What Can Go Wrong During Caplet Stripping ?
by: Floc'h, Fabien Le
Published: (2026)

Universidad abierta en periodos POSTCOVID-19. Experiencia colaborativa en la formación de maestras: Estudio de caso
by: José Antonio Ortí-Martínez
Published: (2023)

DMRlib: Easy-coding and Efficient Resource Management for Job Malleability
by: Iserte, Sergio, et al.
Published: (2026)

The Cambrian Explosion of Mixed-Precision Matrix Multiplication for Quantized Deep Learning Inference
by: Martínez, Héctor, et al.
Published: (2025)

Un acercamiento a la Teoría del Actor Red (TAR) desde América Latina
by: Héctor Noé Hernández Quintana
Published: (2023)

Relational Object-Centric Actor-Critic
by: Ugadiarov, Leonid, et al.
Published: (2023)

When Information Abundance Goes Wrong
by: Lee Skallerup Bessette
Published: (2024)

Actor-Critic with Active Importance Sampling
by: Molaei, Majid, et al.
Published: (2026)

When Patients Go to "Dr. Google" Before They Go to the Emergency Department
by: Grasso, Michael A, et al.
Published: (2025)

Adaptive Ensemble Aggregation for Actor-Critics
by: Werge, Nicklas, et al.
Published: (2025)