English
Related papers

Related papers: Positive-Unlabeled Reward Learning

200 papers

Self-supervised pretraining on unlabeled data followed by supervised fine-tuning on labeled data is a popular paradigm for learning from limited labeled examples. We extend this paradigm to the classical positive unlabeled (PU) setting,…

Machine Learning · Computer Science 2024-04-01 Anish Acharya , Sujay Sanghavi , Li Jing , Bhargav Bhushanam , Dhruv Choudhary , Michael Rabbat , Inderjit Dhillon

We consider a setting for Inverse Reinforcement Learning (IRL) where the learner is extended with the ability to actively select multiple environments, observing an agent's behavior on each environment. We first demonstrate that if the…

Artificial Intelligence · Computer Science 2016-01-26 Kareem Amin , Satinder Singh

Reinforcement learning (RL) is a central problem in artificial intelligence. This problem consists of defining artificial agents that can learn optimal behaviour by interacting with an environment -- where the optimal behaviour is defined…

Positive-unlabeled learning (PU learning) is known as a special case of semi-supervised binary classification where only a fraction of positive examples are labeled. The challenge is then to find the correct classifier despite this lack of…

Statistics Theory · Mathematics 2022-01-19 Olivier Coudray , Christine Keribin , Pascal Massart , Patrick Pamphile

Positive-unlabeled learning (PUL) aims at learning a binary classifier from only positive and unlabeled training data. Even though real-world applications often involve imbalanced datasets where the majority of examples belong to one class,…

Machine Learning · Statistics 2024-03-12 Emilio Dorigatti , Jann Goschenhofer , Benjamin Schubert , Mina Rezaei , Bernd Bischl

PU learning refers to the classification problem in which only part of positive samples are labeled. Existing PU learning methods treat unlabeled samples equally. However, in many real tasks, from common sense or domain knowledge, some…

Machine Learning · Computer Science 2024-05-06 Puning Zhao , Jintao Deng , Xu Cheng

People learn to discriminate between classes without explicit exposure to negative examples. On the contrary, traditional machine learning algorithms often rely on negative examples, otherwise the model would be prone to collapse and…

Machine Learning · Computer Science 2020-05-08 Chenhao Xie , Qiao Cheng , Jiaqing Liang , Lihan Chen , Yanghua Xiao

Deep Reinforcement Learning (RL) has emerged as a powerful paradigm to solve a range of complex yet specific control tasks. Yet training generalist agents that can quickly adapt to new tasks remains an outstanding challenge. Recent advances…

Machine Learning · Computer Science 2021-10-29 Michael Laskin , Denis Yarats , Hao Liu , Kimin Lee , Albert Zhan , Kevin Lu , Catherine Cang , Lerrel Pinto , Pieter Abbeel

Inverse Reinforcement Learning (IRL) techniques deal with the problem of deducing a reward function that explains the behavior of an expert agent who is assumed to act optimally in an underlying unknown task. In several problems of…

Machine Learning · Computer Science 2024-01-09 Riccardo Poiani , Gabriele Curti , Alberto Maria Metelli , Marcello Restelli

In this study, we propose a method for identifying potential customers in targeted marketing by applying learning from positive and unlabeled data (PU learning). We consider a scenario in which a company sells a product and can observe only…

Machine Learning · Computer Science 2025-06-10 Masahiro Kato , Yuki Ikeda , Kentaro Baba , Takashi Imai , Ryo Inokuchi

Many imitation learning (IL) algorithms employ inverse reinforcement learning (IRL) to infer the intrinsic reward function that an expert is implicitly optimizing for based on their demonstrated behaviors. However, in practice, IRL-based IL…

Machine Learning · Computer Science 2024-02-08 Weichao Zhou , Wenchao Li

Automated code vulnerability detection has gained increasing attention in recent years. The deep learning (DL)-based methods, which implicitly learn vulnerable code patterns, have proven effective in vulnerability detection. The performance…

Software Engineering · Computer Science 2023-08-22 Xin-Cheng Wen , Xinchen Wang , Cuiyun Gao , Shaohua Wang , Yang Liu , Zhaoquan Gu

How can a reinforcement learning (RL) agent prepare to solve downstream tasks if those tasks are not known a priori? One approach is unsupervised skill discovery, a class of algorithms that learn a set of policies without access to a reward…

Machine Learning · Computer Science 2021-10-07 Benjamin Eysenbach , Ruslan Salakhutdinov , Sergey Levine

This paper defines a positive and unlabeled classification problem for standard GANs, which then leads to a novel technique to stabilize the training of the discriminator in GANs. Traditionally, real data are taken as positive while…

Machine Learning · Computer Science 2020-02-26 Tianyu Guo , Chang Xu , Jiajun Huang , Yunhe Wang , Boxin Shi , Chao Xu , Dacheng Tao

Despite advances in Preference Alignment (PA) for Large Language Models (LLMs), mainstream methods like Reinforcement Learning with Human Feedback (RLHF) face notable challenges. These approaches require high-quality datasets of positive…

Machine Learning · Computer Science 2025-04-10 Xiaohua Feng , Yuyuan Li , Huwei Ji , Jiaming Zhang , Li Zhang , Tianyu Du , Chaochao Chen

In Reward Learning (ReL), we are given feedback on an unknown target reward, and the goal is to use this information to recover it in order to carry out some downstream application, e.g., planning. When the feedback is not informative…

Machine Learning · Computer Science 2025-09-16 Filippo Lazzati , Alberto Maria Metelli

We consider a problem of learning a binary classifier only from positive data and unlabeled data (PU learning) and estimating the class-prior in unlabeled data under the case-control scenario. Most of the recent methods of PU learning…

Machine Learning · Computer Science 2018-09-18 Masahiro Kato , Liyuan Xu , Gang Niu , Masashi Sugiyama

Domain Adaptation methodologies have shown to effectively generalize from a labeled source domain to a label scarce target domain. Previous research has either focused on unlabeled domain adaptation without any target supervision or…

Machine Learning · Computer Science 2022-02-14 Jonas Sonntag , Gunnar Behrens , Lars Schmidt-Thieme

Motivated by applications in protein function prediction, we consider a challenging supervised classification setting in which positive labels are scarce and there are no explicit negative labels. The learning algorithm must thus select…

Machine Learning · Computer Science 2019-01-28 Marco Frasca , Nicolò Cesa-Bianchi

Model-free reinforcement learning algorithms have exhibited great potential in solving single-task sequential decision-making problems with high-dimensional observations and long horizons, but are known to be hard to generalize across…

Machine Learning · Computer Science 2023-05-30 Boyuan Chen , Chuning Zhu , Pulkit Agrawal , Kaiqing Zhang , Abhishek Gupta