mlsanityData to 14 Oct 2026

Learning to Clean: Reinforcement Learning for Noisy Label Correction

arXiv 2511.19808 ↗First posted 25 Nov 2025cs.LG cs.AIcited by 0

On the map: Deep reinforcement learning methods → RL training of language and agent models

Abstract (arXiv)

The challenge of learning with noisy labels is significant in machine learning, as it can severely degrade the performance of prediction models if not addressed properly. This paper introduces a novel framework that conceptualizes noisy label correction as a reinforcement learning (RL) problem. The proposed approach, Reinforcement Learning for Noisy Label Correction (RLNLC), defines a comprehensive state space representing data and their associated labels, an action space that indicates possible label corrections, and a reward mechanism that evaluates the efficacy of label corrections. RLNLC learns a deep feature representation based policy network to perform label correction through reinforcement learning, utilizing an actor-critic method. The learned policy is subsequently deployed to iteratively correct noisy training labels and facilitate the training of the prediction model. The effectiveness of RLNLC is demonstrated through extensive experiments on multiple benchmark datasets, where it consistently outperforms existing state-of-the-art techniques for learning with noisy labels.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods. Builds on 34 of its 50 references that are in the map. First posted on arXiv 25 Nov 2025.

Builds on

34 of 50 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  6. 2017Deep reinforcement learning from human preferencescited by 3,912
  7. 2020Learning to summarize from human feedbackcited by 2,588
  8. 2019Fine-Tuning Language Models from Human Preferencescited by 2,150
  9. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
  10. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 997
  11. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 692
  12. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 665
22 more
  1. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 653
  2. 2023DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Modelscited by 450
  3. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
  4. 2017Decoupling "when to update" from "how to update"cited by 230
  5. 2017CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noisecited by 181
  6. 2022Causality Inspired Representation Learning for Domain Generalizationcited by 138
  7. 2019Deep Self-Learning From Noisy Labelscited by 122
  8. 2018Iterative Learning with Open-set Noisy Labelscited by 108
  9. 2021Learning with Feature-Dependent Label Noise: A Progressive Approachcited by 102
  10. 2020Error-Bounded Correction of Noisy Labelscited by 74
  11. 2021A Survey of Exploration Methods in Reinforcement Learningcited by 73
  12. 2020Confidence Scores Make Instance-dependent Label-noise Learning Possiblecited by 63
  13. 2021Instance-dependent Label-noise Learning under a Structural Causal Modelcited by 50
  14. 2022Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimationcited by 49
  15. 2021LongReMix: Robust Learning with High Confidence Samples in a Noisy Label Environmentcited by 40
  16. 2021Boosting Co-teaching with Compression Regularization for Label Noisecited by 31
  17. 2021Adaptive Sample Selection for Robust Learning under Label Noisecited by 21
  18. 2024SURE: SUrvey REcipes for building reliable and robust deep networkscited by 8
  19. 2023Optimizing Long-term Value for Auction-Based Recommender Systems via On-Policy Reinforcement Learningcited by 6
  20. 2025Goal Conditioned Reinforcement Learning for Photo Finishing Tuningcited by 6
  21. 2024Is Exploration All You Need? Effective Exploration Characteristics for Transfer in Reinforcement Learningcited by 3
  22. 2024Reinforcement Learning-Guided Semi-Supervised Learningcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Can LLMs Learn to Reason Robustly under Noisy Supervision?
  2. 2026Noisy Data is Destructive to Reinforcement Learning with Verifiable Rewards
  3. 2026Rewards as Labels: Revisiting RLVR from a Classification Perspective
  4. 2026Label-Free Reinforcement Learning via Cross-Model Entropy
  5. 2026When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable Rewards
  6. 2024Enhancing Reinforcement Learning with Label-Sensitive Reward for Natural Language Understanding
  7. 2026Forget or Fine-tune? A Comparative Study of Machine Unlearning Strategies for Noisy Label Correction
  8. 2025Noise-corrected GRPO: From Noisy Rewards to Unbiased Gradients