English
Related papers

Related papers: Instructions are all you need: Self-supervised Rei…

200 papers

In many applications labeled data is not readily available, and needs to be collected via pain-staking human supervision. We propose a rule-exemplar method for collecting human supervision to combine the efficiency of rules with the quality…

Machine Learning · Computer Science 2020-05-18 Abhijeet Awasthi , Sabyasachi Ghosh , Rasna Goyal , Sunita Sarawagi

Reinforcement Learning with Verifiable Rewards (RLVR) has demonstrated promising gains in enhancing the reasoning capabilities of large language models. However, its dependence on domain-specific verifiers significantly restricts its…

Computation and Language · Computer Science 2026-01-22 Chongxuan Huang , Lei Lin , Xiaodong Shi , Wenping Hu , Ruiming Tang

Grounding the instruction in the environment is a key step in solving language-guided goal-reaching reinforcement learning problems. In automated reinforcement learning, a key concern is to enhance the model's ability to generalize across…

Machine Learning · Computer Science 2025-09-09 Armin Saghafian , Amirmohammad Izadi , Negin Hashemi Dijujin , Mahdieh Soleymani Baghshah

In semi-supervised learning, the paradigm of self-training refers to the idea of learning from pseudo-labels suggested by the learner itself. Across various domains, corresponding methods have proven effective and achieve state-of-the-art…

Machine Learning · Statistics 2023-06-12 Julian Lienen , Caglar Demir , Eyke Hüllermeier

Bilevel reinforcement learning (RL), which features intertwined two-level problems, has attracted growing interest recently. The inherent non-convexity of the lower-level RL problem is, however, to be an impediment to developing bilevel…

Optimization and Control · Mathematics 2025-02-28 Yan Yang , Bin Gao , Ya-xiang Yuan

Semi-supervised referring expression segmentation (SS-RES) aims to achieve precise pixel-level language grounding under limited annotation, yet suffers from limited supervision and unreliable pseudo-labels when exploiting unlabeled…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Runlong Cao , Ying Zang , Chuanwei Zhou , Tianrun Chen , Tong Zhang , Zhen Cui , Chunyan Xu

Reinforcement Learning (RL) is a promising approach for solving various control, optimization, and sequential decision making tasks. However, designing reward functions for complex tasks (e.g., with multiple objectives and safety…

Artificial Intelligence · Computer Science 2021-07-23 Xuan Zhao , Marcos Campos

Text classification is a widely studied problem and has broad applications. In many real-world problems, the number of texts for training classification models is limited, which renders these models prone to overfitting. To address this…

Computation and Language · Computer Science 2021-03-25 Meng Zhou , Zechen Li , Pengtao Xie

Learning to rank (LTR) plays a crucial role in various Information Retrieval (IR) tasks. Although supervised LTR methods based on fine-grained relevance labels (e.g., document-level annotations) have achieved significant success, their…

Information Retrieval · Computer Science 2025-08-21 Yiteng Tu , Zhichao Xu , Tao Yang , Weihang Su , Yujia Zhou , Yiqun Liu , Fen Lin , Qin Liu , Qingyao Ai

Reducing the amount of labels required to train convolutional neural networks without performance degradation is key to effectively reduce human annotation efforts. We propose Reliable Label Bootstrapping (ReLaB), an unsupervised…

Computer Vision and Pattern Recognition · Computer Science 2021-02-26 Paul Albert , Diego Ortego , Eric Arazo , Noel E. O'Connor , Kevin McGuinness

Semi-supervised learning leverages unlabeled data to enhance model performance, addressing the limitations of fully supervised approaches. Among its strategies, pseudo-supervision has proven highly effective, typically relying on one or…

Computer Vision and Pattern Recognition · Computer Science 2025-05-13 Negin Ghamsarian , Sahar Nasirihaghighi , Klaus Schoeffmann , Raphael Sznitman

Recent work has described neural-network-based agents that are trained with reinforcement learning (RL) to execute language-like commands in simulated worlds, as a step towards an intelligent agent or robot that can be instructed by human…

Computation and Language · Computer Science 2020-05-20 Felix Hill , Sona Mokra , Nathaniel Wong , Tim Harley

Large Language Models (LLMs) often produce plausible but poorly-calibrated answers, limiting their reliability on reasoning-intensive tasks. We present Reinforcement Learning from Self-Feedback (RLSF), a post-training stage that uses the…

Computation and Language · Computer Science 2025-07-30 Carel van Niekerk , Renato Vukovic , Benjamin Matthias Ruppik , Hsien-chin Lin , Milica Gašić

The development of Large Language Models (LLMs) often confronts challenges stemming from the heavy reliance on human annotators in the reinforcement learning with human feedback (RLHF) framework, or the frequent and costly external queries…

Computation and Language · Computer Science 2025-03-04 Shangding Gu , Alois Knoll , Ming Jin

Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable. Reinforcement learning (RL)-based fine-tuning is a key mechanism for improvement, but its effectiveness is…

Machine Learning · Computer Science 2026-02-11 Pei-Chi Pan , Yingbin Liang , Sen Lin

Reinforcement learning refers to a group of methods from artificial intelligence where an agent performs learning through trial and error. It differs from supervised learning, since reinforcement learning requires no explicit labels;…

Machine Learning · Computer Science 2018-10-02 Nicolas Pröllochs , Stefan Feuerriegel

Recent semi-supervised learning methods have shown to achieve comparable results to their supervised counterparts while using only a small portion of labels in image classification tasks thanks to their regularization strategies. In this…

Machine Learning · Computer Science 2020-09-25 Wei-Hong Li , Chuan-Sheng Foo , Hakan Bilen

Offline reinforcement learning (RL) enables learning control policies by utilizing only prior experience, without any online interaction. This can allow robots to acquire generalizable skills from large and diverse datasets, without any…

Machine Learning · Computer Science 2021-09-24 Aviral Kumar , Anikait Singh , Stephen Tian , Chelsea Finn , Sergey Levine

Offline reinforcement learning has become one of the most practical RL settings. However, most existing works on offline RL focus on the standard setting with scalar reward feedback. It remains unknown how to universally transfer the…

Machine Learning · Computer Science 2024-10-25 Yinglun Xu , David Zhu , Rohan Gumaste , Gagandeep Singh

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