English
Related papers

Related papers: Robust Action Gap Increasing with Clipped Advantag…

200 papers

Semantic segmentation requires pixel-level annotation, which is time-consuming. Active Learning (AL) is a promising method for reducing data annotation costs. Due to the gap between aerial and natural images, the previous AL methods are not…

Computer Vision and Pattern Recognition · Computer Science 2024-05-29 Lianlei Shan , Weiqiang Wang , Ke Lv , Bin Luo

Action-constrained reinforcement learning (ACRL) is a generic framework for learning control policies with zero action constraint violation, which is required by various safety-critical and resource-constrained applications. The existing…

Machine Learning · Computer Science 2025-03-18 Wei Hung , Shao-Hua Sun , Ping-Chun Hsieh

Cloud analysis is a critical component of weather and climate science, impacting various sectors like disaster management. However, achieving fine-grained cloud analysis, such as cloud segmentation, in remote sensing remains challenging due…

Computer Vision and Pattern Recognition · Computer Science 2023-11-10 Jay Gala , Sauradip Nag , Huichou Huang , Ruirui Liu , Xiatian Zhu

Off-policy problems such as policy staleness and training--inference mismatch have become a major bottleneck for training stability and further exploration in LLM RL. The distribution gap between the inference and updated policies grows…

Machine Learning · Computer Science 2026-05-19 Chenlu Ye , Xuanchang Zhang , Yifan Hao , Zhou Yu , Ziji Zhang , Abhinav Gullapalli , Hao Chen , Jing Huang , Tong Zhang

Offline reinforcement learning aims to train agents from pre-collected datasets. However, this comes with the added challenge of estimating the value of behaviors not covered in the dataset. Model-based methods offer a potential solution by…

Machine Learning · Computer Science 2024-12-03 Anya Sims , Cong Lu , Jakob Foerster , Yee Whye Teh

Recent state-of-the-art active learning methods have mostly leveraged Generative Adversarial Networks (GAN) for sample acquisition; however, GAN is usually known to suffer from instability and sensitivity to hyper-parameters. In contrast to…

Computer Vision and Pattern Recognition · Computer Science 2022-02-15 Jae Won Cho , Dong-Jin Kim , Yunjae Jung , In So Kweon

Post-training with Reinforcement Learning (RL) has substantially improved reasoning in Large Language Models (LLMs) via test-time scaling. However, extending this paradigm to Multimodal LLMs (MLLMs) through verbose rationales yields limited…

Computation and Language · Computer Science 2026-02-16 Bangzheng Li , Jianmo Ni , Chen Qu , Ian Miao , Liu Yang , Xingyu Fu , Muhao Chen , Derek Zhiyuan Cheng

A major problem with Active Learning (AL) is high training costs since models are typically retrained from scratch after every query round. We start by demonstrating that standard AL on neural networks with warm starting fails, both to…

Machine Learning · Computer Science 2023-12-14 Arnav Das , Gantavya Bhatt , Megh Bhalerao , Vianne Gao , Rui Yang , Jeff Bilmes

This work presents an adaptive superfast proximal augmented Lagrangian (AS-PAL) method for solving linearly-constrained smooth nonconvex composite optimization problems. Each iteration of AS-PAL inexactly solves a possibly nonconvex…

Optimization and Control · Mathematics 2022-10-07 Arnesh Sujanani , Renato D. C. Monteiro

Active learning (AL) is a principled strategy to reduce annotation cost in data-hungry deep learning. However, existing AL algorithms focus almost exclusively on unimodal data, overlooking the substantial annotation burden in multimodal…

Machine Learning · Computer Science 2026-04-24 Jiancheng Zhang , Yinglun Zhu

Active learning (AL) aims to improve model performance within a fixed labeling budget by choosing the most informative data points to label. Existing AL focuses on the single-domain setting, where all data come from the same domain (e.g.,…

Machine Learning · Computer Science 2024-02-12 Guang-Yuan Hao , Hengguan Huang , Haotian Wang , Jie Gao , Hao Wang

Offline reinforcement learning (RL) enables policy learning from static data but often suffers from poor coverage of the state-action space and distributional shift problems. This problem can be addressed by allowing limited online…

Machine Learning · Computer Science 2026-02-03 Soumyadeep Roy , Shashwat Kushwaha , Ambedkar Dukkipati

We introduce Learning-Augmented Control (LAC), an approach that integrates untrusted machine learning predictions into the control of constrained, nonlinear dynamical systems. LAC is designed to achieve the "best-of-both-worlds" guarantees,…

Systems and Control · Electrical Eng. & Systems 2025-07-22 Tongxin Li

Machine learning models are increasingly being utilized across various fields and tasks due to their outstanding performance and strong generalization capabilities. Nonetheless, their success hinges on the availability of large volumes of…

Machine Learning · Computer Science 2024-11-26 Shreen Gul , Mohamed Elmahallawy , Sanjay Madria , Ardhendu Tripathy

Estimation of the Average Treatment Effect (ATE) is a core problem in causal inference with strong connections to Off-Policy Evaluation in Reinforcement Learning. This paper considers the problem of adaptively selecting the treatment…

Machine Learning · Statistics 2024-11-22 Ojash Neopane , Aaditya Ramdas , Aarti Singh

Offline reinforcement learning (RL) defines a sample-efficient learning paradigm, where a policy is learned from static and previously collected datasets without additional interaction with the environment. The major obstacle to offline RL…

Machine Learning · Computer Science 2022-11-16 Yunfan Zhou , Xijun Li , Qingyu Qu

Reinforcement learning has become a cornerstone technique for developing reasoning models in complex tasks, ranging from mathematical problem-solving to imaginary reasoning. The optimization of these models typically relies on policy…

Machine Learning · Computer Science 2026-02-11 Qingnan Ren , Shiting Huang , Zhen Fang , Zehui Chen , Lin Chen , Lijun Li , Feng Zhao

This article investigates the convergence properties of a relative-type inexact preconditioned proximal augmented Lagrangian method (rip$^2$ALM) for convex nonlinear programming, a fundamental class of optimization problems with broad…

Optimization and Control · Mathematics 2026-03-31 Lei Yang , Jiayi Zhu , Ling Liang , Kim-Chuan Toh

One of the major challenges in training deep architectures for predictive tasks is the scarcity and cost of labeled training data. Active Learning (AL) is one way of addressing this challenge. In stream-based AL, observations are…

Machine Learning · Computer Science 2019-09-05 Andreas Kvistad , Massimiliano Ruocco , Eliezer de Souza da Silva , Erlend Aune

We study tabular reinforcement learning problems with multiple steps of lookahead information. Before acting, the learner observes $\ell$ steps of future transition and reward realizations: the exact state the agent would reach and the…

Machine Learning · Computer Science 2026-01-16 Nadav Merlis