English
Related papers

Related papers: $\pi$-Play: Multi-Agent Self-Play via Privileged S…

200 papers

Training-time privileged information (PI) can enable language models to succeed on tasks they would otherwise fail, making it a powerful tool for reinforcement learning in hard, long-horizon settings. However, transferring capabilities…

Machine Learning · Computer Science 2026-02-17 Emiliano Penaloza , Dheeraj Vattikonda , Nicolas Gontier , Alexandre Lacoste , Laurent Charlin , Massimo Caccia

On-policy self-distillation, where a student is pulled toward a copy of itself conditioned on privileged context (e.g., a verified solution or feedback), offers a promising direction for advancing reasoning capability without a stronger…

Machine Learning · Computer Science 2026-05-13 Guobin Shen , Xiang Cheng , Chenxiao Zhao , Lei Huang , Jindong Li , Dongcheng Zhao , Xing Yu

Deep audio representation learning using multi-modal audio-visual data often leads to a better performance compared to uni-modal approaches. However, in real-world scenarios both modalities are not always available at the time of inference,…

Sound · Computer Science 2023-02-07 Amirhossein Hajavi , Ali Etemad

Using privileged information during training can improve the sample efficiency and performance of machine learning systems. This paradigm has been applied to reinforcement learning (RL), primarily in the form of distillation or auxiliary…

Machine Learning · Computer Science 2020-05-20 Pierre-Alexandre Kamienny , Kai Arulkumaran , Feryal Behbahani , Wendelin Boehmer , Shimon Whiteson

Population-population generalization is a challenging problem in multi-agent reinforcement learning (MARL), particularly when agents encounter unseen co-players. However, existing self-play-based methods are constrained by the limitation of…

Machine Learning · Computer Science 2025-05-19 Lang Feng , Jiahao Lin , Dong Xing , Li Zhang , De Ma , Gang Pan

We study how to exploit dense simulator-defined rewards in vision-based autonomous driving without inheriting their misalignment with deployment metrics. In realistic simulators such as CARLA, privileged state (e.g., lane geometry,…

Robotics · Computer Science 2025-12-30 Feeza Khan Khanzada , Jaerock Kwon

Distilling knowledge from a large teacher model to a lightweight one is a widely successful approach for generating compact, powerful models in the semi-supervised learning setting where a limited amount of labeled data is available. In…

Machine Learning · Computer Science 2023-02-07 Cenk Baykal , Khoa Trinh , Fotis Iliopoulos , Gaurav Menghani , Erik Vee

Learning Using Privileged Information is a particular type of knowledge distillation where the teacher model benefits from an additional data representation during training, called privileged information, improving the student model, which…

Computation and Language · Computer Science 2024-08-20 Rafael-Edy Menadil , Mariana-Iuliana Georgescu , Radu Tudor Ionescu

In supervised machine learning, privileged information (PI) is information that is unavailable at inference, but is accessible during training time. Research on learning using privileged information (LUPI) aims to transfer the knowledge…

Machine Learning · Computer Science 2024-08-28 Danil Provodin , Bram van den Akker , Christina Katsimerou , Maurits Kaptein , Mykola Pechenizkiy

We adopt a multi-view approach for analyzing two knowledge transfer settings---learning using privileged information (LUPI) and distillation---in a common framework. Under reasonable assumptions about the complexities of hypothesis spaces,…

Machine Learning · Computer Science 2019-03-12 Weiran Wang

Recent work on distilling Whisper's knowledge into small models using pseudo-labels shows promising performance while reducing the size by up to 50%. This results in small, efficient, and dedicated models. However, a critical step of…

Computation and Language · Computer Science 2025-05-16 Abdul Waheed , Karima Kadaoui , Bhiksha Raj , Muhammad Abdul-Mageed

On-policy distillation is an efficient alternative to reinforcement learning, offering dense token-level training signals. However, its reliance on a stronger external teacher has driven recent work on on-policy self-distillation, where the…

Machine Learning · Computer Science 2026-05-07 Xin Yu , Liuchen Liao , Yiwen Zhang , Yingchen Yu , Lingzhou Xue , Qinzhen Guo

Multi-agent reinforcement learning has shown promise in learning cooperative behaviors in team-based environments. However, such methods often demand extensive training time. For instance, the state-of-the-art method TiZero takes 40 days to…

Machine Learning · Computer Science 2025-03-18 Amir Baghi , Jens Sjölund , Joakim Bergdahl , Linus Gisslén , Alessandro Sestini

Self-play is an unsupervised training procedure which enables the reinforcement learning agents to explore the environment without requiring any external rewards. We augment the self-play setting by providing an external memory where the…

Machine Learning · Computer Science 2018-06-04 Shagun Sodhani , Vardaan Pahuja

Self-distillation enables language models to learn on-policy from their own trajectories by using the same model as both student and teacher, with the teacher being conditioned on privileged information unavailable to the student. Such…

Unlike machines, humans learn through rapid, abstract model-building. The role of a teacher is not simply to hammer home right or wrong answers, but rather to provide intuitive comments, comparisons, and explanations to a pupil. This is…

Machine Learning · Computer Science 2018-05-30 John Lambert , Ozan Sener , Silvio Savarese

Dataset Condensation (DC) seeks to select or distill samples from large datasets into smaller subsets while preserving performance on target tasks. Existing methods primarily focus on pruning or synthesizing data in the same format as the…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Shaobo Wang , Youxin Jiang , Tianle Niu , Yantai Yang , Ruiji Zhang , Shuhao Hu , Shuaiyu Zhang , Chenghao Sun , Weiya Li , Conghui He , Xuming Hu , Linfeng Zhang

Acquiring a diverse repertoire of general-purpose skills remains an open challenge for robotics. In this work, we propose self-supervising control on top of human teleoperated play data as a way to scale up skill learning. Play has two…

Robotics · Computer Science 2019-12-23 Corey Lynch , Mohi Khansari , Ted Xiao , Vikash Kumar , Jonathan Tompson , Sergey Levine , Pierre Sermanet

Deep learning models can achieve high inference accuracy by extracting rich knowledge from massive well-annotated data, but may pose the risk of data privacy leakage in practical deployment. In this paper, we present an effective…

Machine Learning · Computer Science 2024-09-20 Bochao Liu , Jianghu Lu , Pengju Wang , Junjie Zhang , Dan Zeng , Zhenxing Qian , Shiming Ge

Making sophisticated, robust, and safe sequential decisions is at the heart of intelligent systems. This is especially critical for planning in complex multi-agent environments, where agents need to anticipate other agents' intentions and…

Robotics · Computer Science 2020-01-29 Yichuan Charlie Tang
‹ Prev 1 2 3 10 Next ›