English
Related papers

Related papers: State Diversity Matters in Offline Behavior Distil…

200 papers

Pretraining a policy on offline data followed by fine-tuning through online interactions, known as Offline-to-Online Reinforcement Learning (O2O RL), has emerged as a promising paradigm for real-world RL deployment. However, both offline…

Machine Learning · Computer Science 2025-10-17 Longxiang He , Deheng Ye , Junbo Tan , Xueqian Wang , Li Shen

On-policy self-distillation (OPSD) improves the reasoning performance of large language models (LLMs) by providing dense token-level supervision for on-policy rollouts. However, existing OPSD methods often yield limited gains on in-domain…

Computation and Language · Computer Science 2026-05-28 Ziqi Zhao , Xinyu Ma , Liu Yang , Yujie Feng , Daiting Shi , Jingzhou He , Xin Xin , Zhaochun Ren , Xiao-Ming Wu

On-policy distillation (OPD) trains a student model on its own rollouts using dense feedback from a stronger teacher. Prior literature suggests that, provided teacher feedback is available, supervising the full sequence of response tokens…

Computation and Language · Computer Science 2026-05-26 Kaiyuan Liu , Ziyuan Zhuang , Yang Bai , Bing Wang , Rongxiang Weng , Jieping Ye

A key problem in off-policy Reinforcement Learning (RL) is the mismatch, or distribution shift, between the dataset and the distribution over states and actions visited by the learned policy. This problem is exacerbated in the fully offline…

Machine Learning · Computer Science 2023-11-28 Melrose Roderick , Gaurav Manek , Felix Berkenkamp , J. Zico Kolter

On-policy distillation (OPD) leverages dense teacher rewards to enhance reasoning models. However, scaling OPD to long-horizon tasks exposes a critical flaw: as the student's generated prefix inevitably diverges from the teacher's thought…

Machine Learning · Computer Science 2026-05-29 Zhicheng Yang , Zhijiang Guo , Yifan Song , Minrui Xu , Yongxin Wang , Yiwei Wang , Xiaodan Liang , Jing Tang

Dataset Distillation aims to compress a large dataset into a significantly more compact, synthetic one without compromising the performance of the trained models. To achieve this, existing methods use the agent model to extract information…

Dataset Distillation (DD) is designed to generate condensed representations of extensive image datasets, enhancing training efficiency. Despite recent advances, there remains considerable potential for improvement, particularly in…

Computer Vision and Pattern Recognition · Computer Science 2024-12-11 Bowen Yuan , Zijian Wang , Mahsa Baktashmotlagh , Yadan Luo , Zi Huang

Recent semi-supervised learning algorithms have demonstrated greater success with higher overall performance due to better-unlabeled data representations. Nonetheless, recent research suggests that the performance of the SSL algorithm can…

Machine Learning · Computer Science 2023-02-02 Xujiang Zhao , Killamsetty Krishnateja , Rishabh Iyer , Feng Chen

Recent advancements in large language models (LLMs) have exhibited promising performance in solving sequential decision-making problems. By imitating few-shot examples provided in the prompts (i.e., in-context learning), an LLM agent can…

Artificial Intelligence · Computer Science 2024-02-27 Yuchen Xiao , Yanchao Sun , Mengda Xu , Udari Madhushani , Jared Vann , Deepeka Garg , Sumitra Ganesh

In offline reinforcement learning, deriving an effective policy from a pre-collected set of experiences is challenging due to the distribution mismatch between the target policy and the behavioral policy used to collect the data, as well as…

Machine Learning · Computer Science 2024-12-10 Catalin E. Brita , Stephan Bongers , Frans A. Oliehoek

Dataset distillation enables the training of deep neural networks with comparable performance in significantly reduced time by compressing large datasets into small and representative ones. Although the introduction of generative models has…

Machine Learning · Computer Science 2025-05-27 Mingzhuo Li , Guang Li , Jiafeng Mao , Takahiro Ogawa , Miki Haseyama

The ultimate goal of Dataset Distillation is to synthesize a small synthetic dataset such that a model trained on this synthetic set will perform equally well as a model trained on the full, real dataset. Until now, no method of Dataset…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Ziyao Guo , Kai Wang , George Cazenavette , Hui Li , Kaipeng Zhang , Yang You

We consider the problem of learning the best possible policy from a fixed dataset, known as offline Reinforcement Learning (RL). A common taxonomy of existing offline RL works is policy regularization, which typically constrains the learned…

Machine Learning · Computer Science 2023-08-16 Yuhang Ran , Yi-Chen Li , Fuxiang Zhang , Zongzhang Zhang , Yang Yu

Data-Free Knowledge Distillation (DFKD) is a novel task that aims to train high-performance student models using only the pre-trained teacher network without original training data. Most of the existing DFKD methods rely heavily on…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Yuzheng Wang , Zhaoyu Chen , Jie Zhang , Dingkang Yang , Zuhao Ge , Yang Liu , Siao Liu , Yunquan Sun , Wenqiang Zhang , Lizhe Qi

Offline safe reinforcement learning (RL) aims to train a policy that satisfies constraints using a pre-collected dataset. Most current methods struggle with the mismatch between imperfect demonstrations and the desired safe and rewarding…

Machine Learning · Computer Science 2024-07-23 Yihang Yao , Zhepeng Cen , Wenhao Ding , Haohong Lin , Shiqi Liu , Tingnan Zhang , Wenhao Yu , Ding Zhao

Despite the perceived success of large-scale dataset distillation (DD) methods, recent evidence finds that simple random image baselines perform on-par with state-of-theart DD methods like SRe2L due to the use of soft labels during…

Machine Learning · Computer Science 2026-04-22 Priyam Dey , Aditya Sahdev , Sunny Bhati , Konda Reddy Mopuri , R. Venkatesh Babu

Dataset Distillation has emerged as a technique for compressing large datasets into smaller synthetic counterparts, facilitating downstream training tasks. In this paper, we study the impact of bias inside the original dataset on the…

Machine Learning · Computer Science 2024-07-11 Justin Cui , Ruochen Wang , Yuanhao Xiong , Cho-Jui Hsieh

Dataset distillation aims to synthesize a compact yet representative dataset that preserves the essential characteristics of the original data for efficient model training. Existing methods mainly focus on improving data-synthetic alignment…

Computer Vision and Pattern Recognition · Computer Science 2026-02-17 Jiacheng Cui , Zhaoyi Li , Xiaochen Ma , Xinyue Bi , Yaxin Luo , Zhiqiang Shen

Dataset distillation enables efficient training by distilling the information of large-scale datasets into significantly smaller synthetic datasets. Diffusion based paradigms have emerged in recent years, offering novel perspectives for…

Computer Vision and Pattern Recognition · Computer Science 2026-05-06 Qichao Wang , Yunhong Lu , Hengyuan Cao , Junyi Zhang , Min Zhang

We present a model-based offline reinforcement learning policy performance lower bound that explicitly captures dynamics model misspecification and distribution mismatch and we propose an empirical algorithm for optimal offline policy…

Machine Learning · Computer Science 2023-01-30 Kefan Dong , Yannis Flet-Berliac , Allen Nie , Emma Brunskill