English
Related papers

Related papers: Only Relevant Information Matters: Filtering Out N…

200 papers

Standard reinforcement learning methods aim to master one way of solving a task whereas there may exist multiple near-optimal policies. Being able to identify this collection of near-optimal policies can allow a domain expert to efficiently…

Machine Learning · Computer Science 2019-06-04 Muhammad A. Masood , Finale Doshi-Velez

Attributing the output of a neural network to the contribution of given input elements is a way of shedding light on the black-box nature of neural networks. Due to the complexity of current network architectures, current gradient-based…

Computer Vision and Pattern Recognition · Computer Science 2020-03-10 Ashkan Khakzar , Soroosh Baselizadeh , Saurabh Khanduja , Christian Rupprecht , Seong Tae Kim , Nassir Navab

This paper advocates privacy preserving requirements on collection of user data for recommender systems. The purpose of our study is twofold. First, we ask if restrictions on data collection will hurt test quality of RNN-based…

Information Retrieval · Computer Science 2021-06-22 Gustav Hertz , Sandhya Sachidanandan , Balázs Tóth , Emil S. Jørgensen , Martin Tegnér

Reinforcement learning (RL) using foundation models for policy approximations in multi-turn tasks remains challenging. We identify two main limitations related to sparse reward settings and policy gradient updates, based on which we…

Machine Learning · Computer Science 2025-11-14 Georgios Papoudakis , Thomas Coste , Jianye Hao , Jun Wang , Kun Shao

Reinforcement learning (RL) plays a central role in improving the reasoning and alignment of large language models, yet its efficiency critically depends on how training data are selected. Existing online selection strategies predominantly…

Machine Learning · Computer Science 2026-03-03 Xinyu Zhou , Boyu Zhu , Haotian Zhang , Huiming Wang , Zhijiang Guo

Data augmentation methods usually apply the same augmentation (or a mix of them) to all the training samples. For example, to perturb data with noise, the noise is sampled from a Normal distribution with a fixed standard deviation, for all…

Offline reinforcement learning (RL) aims to learn a policy that maximizes the expected return using a given static dataset of transitions. However, offline RL faces the distribution shift problem. The policy constraint offline RL method is…

Machine Learning · Computer Science 2025-12-24 Yuanhao Chen , Qi Liu , Pengbin Chen , Zhongjian Qiao , Yanjie Li

Datasets nowadays are generally constructed from multiple sources and using different synthetic techniques, making data de-noising and de-duplication crucial before being used for post-training. In this work, we propose to perform…

Computation and Language · Computer Science 2024-12-24 Qi Jia , Siyu Ren , Ziheng Qin , Fuzhao Xue , Jinjie Ni , Yang You

A common strategy in transfer learning is few shot fine-tuning, but its success is highly dependent on the quality of samples selected as training examples. Active learning methods such as uncertainty sampling and diversity sampling can…

Computation and Language · Computer Science 2026-04-23 Wei Han , David Martinez , Anna Khanina , Lawrence Cavedon , Karin Verspoor

Policy-gradient methods are widely used in reinforcement learning, yet training often becomes unstable or slows down as learning progresses. We study this phenomenon through the noise-to-signal ratio (NSR) of a policy-gradient estimator,…

Optimization and Control · Mathematics 2026-02-10 Haoyu Han , Heng Yang

While reinforcement learning (RL) methods that learn an internal model of the environment have the potential to be more sample efficient than their model-free counterparts, learning to model raw observations from high dimensional sensors…

Machine Learning · Computer Science 2023-06-27 Raj Ghugare , Homanga Bharadhwaj , Benjamin Eysenbach , Sergey Levine , Ruslan Salakhutdinov

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

Policy gradient methods are among the most effective methods for large-scale reinforcement learning, and their empirical success has prompted several works that develop the foundation of their global convergence theory. However, prior works…

Machine Learning · Computer Science 2020-12-25 Junzi Zhang , Jongho Kim , Brendan O'Donoghue , Stephen Boyd

Training data quality is one of the most important drivers of final model quality. In this work, we introduce a method for evaluating data integrity based on the assumption that low-quality input prompts result in high variance and low…

Computation and Language · Computer Science 2025-02-27 Ping Yu , Weizhe Yuan , Olga Golovneva , Tianhao Wu , Sainbayar Sukhbaatar , Jason Weston , Jing Xu

Learning from preference labels plays a crucial role in fine-tuning large language models. There are several distinct approaches for preference fine-tuning, including supervised learning, on-policy reinforcement learning (RL), and…

On-policy reinforcement learning (RL) methods widely used for language model post-training, like Group Relative Policy Optimization (GRPO), often suffer from limited exploration and early saturation due to low sampling diversity. While…

Computation and Language · Computer Science 2026-01-30 Lei Yang , Wei Bi , Chenxi Sun , Renren Jin , Deyi Xiong

Offline policy learning is aimed at learning decision-making policies using existing datasets of trajectories without collecting additional data. The primary motivation for using reinforcement learning (RL) instead of supervised learning…

Increasingly large datasets of robot actions and sensory observations are being collected to train ever-larger neural networks. These datasets are collected based on tasks and while these tasks may be distinct in their descriptions, many…

Robotics · Computer Science 2025-10-23 Basavasagar Patil , Sydney Belt , Jayjun Lee , Nima Fazeli , Bernadette Bucher

Recommender systems trained on implicit feedback data rely on negative sampling to distinguish positive items from negative items for each user. Since the majority of positive interactions come from a small group of active users, negative…

Information Retrieval · Computer Science 2025-11-12 Yueqing Xuan , Kacper Sokol , Mark Sanderson , Jeffrey Chan

Policies trained via Reinforcement Learning (RL) are often needlessly complex, making them difficult to analyse and interpret. In a run with $n$ time steps, a policy will make $n$ decisions on actions to take; we conjecture that only a…

Machine Learning · Computer Science 2021-10-27 Hadrien Pouget , Hana Chockler , Youcheng Sun , Daniel Kroening