English
Related papers

Related papers: Noisy Data is Destructive to Reinforcement Learnin…

200 papers

Reinforcement learning (RL) training is inherently unstable due to factors such as moving targets and high gradient variance. Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning from AI Feedback (RLAIF) can…

Machine Learning · Computer Science 2025-06-24 Ju-Seung Byun , Andrew Perrault

Model-free reinforcement learning algorithms, such as Q-learning, perform poorly in the early stages of learning in noisy environments, because much effort is spent unlearning biased estimates of the state-action value function. The bias…

Machine Learning · Computer Science 2018-02-01 Roy Fox , Ari Pakman , Naftali Tishby

Large language models (LLMs) have shown impressive performance on downstream tasks by in-context learning (ICL), which heavily relies on the quality of demonstrations selected from a large set of annotated examples. Recent works claim that…

Computation and Language · Computer Science 2024-10-25 Hongfu Gao , Feipeng Zhang , Wenyu Jiang , Jun Shu , Feng Zheng , Hongxin Wei

In model-free deep reinforcement learning (RL) algorithms, using noisy value estimates to supervise policy evaluation and optimization is detrimental to the sample efficiency. As this noise is heteroscedastic, its effects can be mitigated…

Machine Learning · Computer Science 2022-05-04 Vincent Mai , Kaustubh Mani , Liam Paull

Reinforcement Learning (RL) for training Large Language Models is notoriously unstable. While recent studies attribute this to "training inference mismatch stemming" from inconsistent hybrid engines, standard remedies, such as Importance…

Machine Learning · Computer Science 2026-02-03 Yaxiang Zhang , Yingru Li , Jiacai Liu , Jiawei Xu , Ziniu Li , Qian Liu , Haoyuan Li

Data lies at the core of modern deep learning. The impressive performance of supervised learning is built upon a base of massive accurately labeled data. However, in some real-world applications, accurate labeling might not be viable;…

Deep learning has achieved remarkable success in numerous domains with help from large amounts of big data. However, the quality of data labels is a concern because of the lack of high-quality labels in many real-world scenarios. As noisy…

Machine Learning · Computer Science 2022-03-11 Hwanjun Song , Minseok Kim , Dongmin Park , Yooju Shin , Jae-Gil Lee

Reinforcement Learning (RL) agents require the specification of a reward signal for learning behaviours. However, introduction of corrupt or stochastic rewards can yield high variance in learning. Such corruption may be a direct result of…

Machine Learning · Computer Science 2018-11-09 Joshua Romoff , Peter Henderson , Alexandre Piché , Vincent Francois-Lavet , Joelle Pineau

Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a powerful paradigm for post-training large language models (LLMs), achieving state-of-the-art performance on tasks with structured, verifiable answers. Applying…

Computer Vision and Pattern Recognition · Computer Science 2025-06-06 Yiqing Liang , Jielin Qiu , Wenhao Ding , Zuxin Liu , James Tompkin , Mengdi Xu , Mengzhou Xia , Zhengzhong Tu , Laixi Shi , Jiacheng Zhu

Reinforcement Learning with Verifiable Rewards (RLVR) has markedly enhanced the reasoning abilities of large language models (LLMs). Its success, however, largely depends on strong base models with rich world knowledge, yielding only modest…

Artificial Intelligence · Computer Science 2025-08-19 Yongxin Guo , Wenbo Deng , Zhenglin Cheng , Xiaoying Tang

Reinforcement learning has emerged as a powerful paradigm for post-training large language models (LLMs) to improve reasoning. Approaches like Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning with Verifiable…

Machine Learning · Computer Science 2025-06-26 Yanzhi Zhang , Zhaoxi Zhang , Haoxiang Guan , Yilin Cheng , Yitong Duan , Chen Wang , Yue Wang , Shuxin Zheng , Jiyan He

The growing importance of massive datasets used for deep learning makes robustness to label noise a critical property for classifiers to have. Sources of label noise include automatic labeling, non-expert labeling, and label corruption by…

Machine Learning · Computer Science 2019-01-30 Dan Hendrycks , Mantas Mazeika , Duncan Wilson , Kevin Gimpel

When data is generated by multiple sources, conventional training methods update models assuming equal reliability for each source and do not consider their individual data quality. However, in many applications, sources have varied levels…

Machine Learning · Computer Science 2025-02-17 Alexander Capstick , Francesca Palermo , Tianyu Cui , Payam Barnaghi

Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for complex reasoning tasks with clear correctness signals such as math and coding. However, extending it to real-world reasoning tasks is challenging, as evaluation…

Machine Learning · Computer Science 2025-10-06 Anisha Gunjal , Anthony Wang , Elaine Lau , Vaskar Nath , Yunzhong He , Bing Liu , Sean Hendryx

Large language models (LLMs) trained for step-by-step reasoning often become excessively verbose, raising inference cost. Standard Reinforcement Learning with Verifiable Rewards (RLVR) pipelines filter out ``easy'' problems for training…

Supervised learning depends on annotated examples, which are taken to be the \emph{ground truth}. But these labels often come from noisy crowdsourcing platforms, like Amazon Mechanical Turk. Practitioners typically collect multiple labels…

Machine Learning · Computer Science 2018-05-22 Ashish Khetan , Zachary C. Lipton , Anima Anandkumar

Data corruption, including missing and noisy data, poses significant challenges in real-world machine learning. This study investigates the effects of data corruption on model performance and explores strategies to mitigate these effects…

Machine Learning · Computer Science 2025-05-22 Qi Liu , Wanjing Ma

Recently, reinforcement learning with verifiable rewards (RLVR) has been widely used for enhancing the reasoning abilities of large language models (LLMs). A core challenge in RLVR involves managing the exchange between entropy and…

Computation and Language · Computer Science 2025-08-05 Jia Deng , Jie Chen , Zhipeng Chen , Wayne Xin Zhao , Ji-Rong Wen

Reinforcement Learning with Verifiable Reward (RLVR) is empirically shown to notably enhance the reasoning performance of large language models (LLMs), particularly in mathematics and programming. However, the mechanistic role of Sample…

Artificial Intelligence · Computer Science 2026-05-28 Yue Cheng , Jiajun Zhang , Xiaohui Gao , Weiwei Xing , Zheng Wang , Zhanxing Zhu

Automatic speech recognition (ASR) systems play a key role in many commercial products including voice assistants. Typically, they require large amounts of clean speech data for training which gives an undue advantage to large organizations…

Audio and Speech Processing · Electrical Eng. & Systems 2019-11-21 Bhavya Ghai , Buvana Ramanan , Klaus Mueller