Imagen de Portada

Noisy Data is Destructive to Reinforcement Learning with Verifiable Rewards

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhu, Yuxuan, Kang, Daniel
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning I.2.0
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Implicit Counterfactual Data Augmentation for Robust Learning
por: Zhou, Xiaoling, et al.
Publicado: (2023)

Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking
por: Singha, Disha
Publicado: (2026)

Carefully Structured Compression: Efficiently Managing StarCraft II Data
por: Ferenczi, Bryce, et al.
Publicado: (2024)

Detecting In-Person Conversations in Noisy Real-World Environments with Smartwatch Audio and Motion Sensing
por: Zhang, Alice, et al.
Publicado: (2025)

Prediction Instability in Machine Learning Ensembles
por: Kedziora, Jeremy
Publicado: (2024)

How Data Quality Affects Machine Learning Models for Credit Risk Assessment
por: Maurino, Andrea
Publicado: (2025)

Reward Machines for Deep RL in Noisy and Uncertain Environments
por: Li, Andrew C., et al.
Publicado: (2024)

Learning Can Converge Stably to the Wrong Belief under Latent Reliability
por: Zhang, Zhipeng, et al.
Publicado: (2026)

Efficiently Scanning and Resampling Spatio-Temporal Tasks with Irregular Observations
por: Ferenczi, Bryce, et al.
Publicado: (2024)

PCA- and SVM-Grad-CAM for Convolutional Neural Networks: Closed-form Jacobian Expression
por: Omae, Yuto
Publicado: (2025)

Deep Reinforcement Learning for Adverse Garage Scenario Generation
por: Li, Kai
Publicado: (2024)

Deep Learning-Based Intrusion Detection for Automotive Ethernet: Evaluating & Optimizing Fast Inference Techniques for Deployment on Low-Cost Platform
por: Carmo, Pedro R. X., et al.
Publicado: (2025)

Non-exchangeable Conformal Prediction for Temporal Graph Neural Networks
por: Wang, Tuo, et al.
Publicado: (2025)

Virtual Nodes based Heterogeneous Graph Convolutional Neural Network for Efficient Long-Range Information Aggregation
por: Yan, Ranhui, et al.
Publicado: (2025)

Meta Pattern Concern Score: A Novel Evaluation Measure with Human Values for Multi-classifiers
por: Wang, Yanyun, et al.
Publicado: (2022)

Normalized AOPC: Fixing Misleading Faithfulness Metrics for Feature Attribution Explainability
por: Edin, Joakim, et al.
Publicado: (2024)

Interpretable Clinical Classification with Kolmogorov-Arnold Networks
por: Almodóvar, Alejandro, et al.
Publicado: (2025)

A Capacity-Based Rationale for Multi-Head Attention
por: Adler, Micah
Publicado: (2025)

Empowering Decision Trees via Shape Function Branching
por: Upadhya, Nakul, et al.
Publicado: (2025)

Informal Safety Guarantees for Simulated Optimizers Through Extrapolation from Partial Simulations
por: Marks, Luke
Publicado: (2023)

Interpolation, Extrapolation, Hyperpolation: Generalising into new dimensions
por: Ord, Toby
Publicado: (2024)

CCDSReFormer: Traffic Flow Prediction with a Criss-Crossed Dual-Stream Enhanced Rectified Transformer Model
por: Shao, Zhiqi, et al.
Publicado: (2024)

FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data
por: Xiao, Zikai, et al.
Publicado: (2024)

Beyond validation loss: Clinically-tailored optimization metrics improve a model's clinical performance
por: Delahunt, Charles B., et al.
Publicado: (2026)

Feel-Good Thompson Sampling for Contextual Bandits: a Markov Chain Monte Carlo Showdown
por: Anand, Emile, et al.
Publicado: (2025)

Artificial Inductive Bias for Synthetic Tabular Data Generation in Data-Scarce Scenarios
por: Apellániz, Patricia A., et al.
Publicado: (2024)

ConciseRL: Conciseness-Guided Reinforcement Learning for Efficient Reasoning Models
por: Dumitru, Razvan-Gabriel, et al.
Publicado: (2025)

Intelligent Routing for Sparse Demand Forecasting: A Comparative Evaluation of Selection Strategies
por: Zhang, Qiwen
Publicado: (2025)

Synthetic Tabular Data Validation: A Divergence-Based Approach
por: Apellániz, Patricia A., et al.
Publicado: (2024)

Study of the Proper NNUE Dataset
por: Tan, Daniel, et al.
Publicado: (2024)

Dynamic Observation Policies in Observation Cost-Sensitive Reinforcement Learning
por: Bellinger, Colin, et al.
Publicado: (2023)

A Review of Nine Physics Engines for Reinforcement Learning Research
por: Kaup, Michael, et al.
Publicado: (2024)

Social Learning through Interactions with Other Agents: A Survey
por: Hillier, Dylan, et al.
Publicado: (2024)

Simulation-Driven Railway Delay Prediction: An Imitation Learning Approach
por: Elliker, Clément, et al.
Publicado: (2025)

TSFool: Crafting Highly-Imperceptible Adversarial Time Series through Multi-Objective Attack
por: Wang, Yanyun, et al.
Publicado: (2022)

An Efficient Gradient-Based Inference Attack for Federated Learning
por: Montaña-Fernández, Pablo, et al.
Publicado: (2025)

A Physics-embedded Deep Learning Framework for Cloth Simulation
por: Zhao, Zhiwei
Publicado: (2024)

A Comprehensive Sustainable Framework for Machine Learning and Artificial Intelligence
por: Pagliari, Roberto, et al.
Publicado: (2024)

Continuous Wavelet Transform and Siamese Network-Based Anomaly Detection in Multi-variate Semiconductor Process Time Series
por: Dey, Bappaditya, et al.
Publicado: (2025)

Graph Analysis Using a GPU-based Parallel Algorithm: Quantum Clustering
por: Wang, Zhe, et al.
Publicado: (2023)