English
Related papers

Related papers: DiffusionOPD: A Unified Perspective of On-Policy D…

200 papers

In this paper, we explore multi-task learning (MTL) as a second pretraining step to learn enhanced universal language representation for transformer language models. We use the MTL enhanced representation across several natural language…

Computation and Language · Computer Science 2021-03-17 Haytham ElFadeel , Stan Peshterliev

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

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) has become a core technique in the post-training of large language models, yet its training dynamics remain poorly understood. This paper provides a systematic investigation of OPD dynamics and mechanisms. We…

Machine Learning · Computer Science 2026-04-16 Yaxuan Li , Yuxin Zuo , Bingxiang He , Jinqian Zhang , Chaojun Xiao , Cheng Qian , Tianyu Yu , Huan-ang Gao , Wenkai Yang , Zhiyuan Liu , Ning Ding

Reinforcement learning (RL) has emerged as a central paradigm for post-training LLM agents, yet its trajectory-level reward signal provides only coarse supervision for long-horizon interaction. On-Policy Self-Distillation (OPSD) complements…

Machine Learning · Computer Science 2026-05-15 Zhengxi Lu , Zhiyuan Yao , Zhuowen Han , Zi-Han Wang , Jinyang Wu , Qi Gu , Xunliang Cai , Weiming Lu , Jun Xiao , Yueting Zhuang , Yongliang Shen

Removing various degradations from damaged documents greatly benefits digitization, downstream document analysis, and readability. Previous methods often treat each restoration task independently with dedicated models, leading to a…

Computer Vision and Pattern Recognition · Computer Science 2025-08-07 Fangmin Zhao , Weichao Zeng , Zhenhang Li , Dongbao Yang , Binbin Li , Xiaojun Bi , Yu Zhou

Diffusion models surpass previous generative models in sample quality and training stability. Recent works have shown the advantages of diffusion models in improving reinforcement learning (RL) solutions. This survey aims to provide an…

Machine Learning · Computer Science 2024-02-26 Zhengbang Zhu , Hanye Zhao , Haoran He , Yichao Zhong , Shenyu Zhang , Haoquan Guo , Tingting Chen , Weinan Zhang

Knowledge distillation (KD) is an effective model compression technique where a compact student network is taught to mimic the behavior of a complex and highly trained teacher network. In contrast, Mutual Learning (ML) provides an…

Computer Vision and Pattern Recognition · Computer Science 2021-10-25 Usma Niyaz , Deepti R. Bathula

With the great success of diffusion models (DMs) in generating realistic synthetic vision data, many researchers have investigated their potential in decision-making and control. Most of these works utilized DMs to sample directly from the…

Machine Learning · Computer Science 2026-05-19 Hanye Zhao , Xiaoshen Han , Zhengbang Zhu , Minghuan Liu , Yong Yu , De-Chuan Zhan , Weinan Zhang

Training vision-language models (VLMs) for complex reasoning remains a challenging task, i.a. due to the scarcity of high-quality image-text reasoning data. Conversely, text-based reasoning resources are abundant and scalable, but it is…

Computer Vision and Pattern Recognition · Computer Science 2025-10-29 Walid Bousselham , Hilde Kuehne , Cordelia Schmid

Diffusion-based stylization methods typically denoise from a specific partial noise state for image-to-image and video-to-video tasks. This multi-step diffusion process is computationally expensive and hinders real-world application. A…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Sijie Xu , Runqi Wang , Wei Zhu , Dejia Song , Nemo Chen , Xu Tang , Yao Hu

Training autonomous agents with sparse rewards is a long-standing problem in online reinforcement learning (RL), due to low data efficiency. Prior work overcomes this challenge by extracting useful knowledge from offline data, often…

Machine Learning · Computer Science 2024-06-07 Qianlan Yang , Yu-Xiong Wang

We propose Algorithm Distillation (AD), a method for distilling reinforcement learning (RL) algorithms into neural networks by modeling their training histories with a causal sequence model. Algorithm Distillation treats learning to…

Offline reinforcement learning (RL) presents distinct challenges as it relies solely on observational data. A central concern in this context is ensuring the safety of the learned policy by quantifying uncertainties associated with various…

Machine Learning · Computer Science 2025-07-03 Xiaocong Chen , Siyu Wang , Tong Yu , Lina Yao

Proximal Policy Optimization (PPO) is widely used in continuous control due to its robustness and stable training, yet it remains sample-inefficient in tasks with expensive interactions and high-dimensional action spaces. This paper…

Machine Learning · Computer Science 2025-12-16 Tianci Gao , Konstantin A. Neusypin , Dmitry D. Dmitriev , Bo Yang , Shengren Rao

Offline-to-online reinforcement learning (O2O-RL) has emerged as a promising paradigm for safe and efficient robotic policy deployment but suffers from two fundamental challenges: limited coverage of multimodal behaviors and distributional…

Robotics · Computer Science 2025-11-14 Haidong Huang , Haiyue Zhu. Jiayu Song , Xixin Zhao , Yaohua Zhou , Jiayi Zhang , Yuze Zhai , Xiaocong Li

We apply diffusion strategies to develop a fully-distributed cooperative reinforcement learning algorithm in which agents in a network communicate only with their immediate neighbors to improve predictions about their environment. The…

Multiagent Systems · Computer Science 2014-11-06 Sergio Valcarcel Macua , Jianshu Chen , Santiago Zazo , Ali H. Sayed

Massive reinforcement learning (RL) data are typically collected to train policies offline without the need for interactions, but the large data volume can cause training inefficiencies. To tackle this issue, we formulate offline behavior…

Machine Learning · Computer Science 2024-10-31 Shiye Lei , Sen Zhang , Dacheng Tao

Few-step diffusion models enable efficient high-resolution image synthesis but struggle to align with specific downstream objectives due to limitations of existing reinforcement learning (RL) methods in low-step regimes with limited state…

Machine Learning · Computer Science 2026-03-02 Ziyi Zhang , Li Shen , Sen Zhang , Deheng Ye , Yong Luo , Miaojing Shi , Dongjing Shan , Bo Du , Dacheng Tao

Diffusion distillation, exemplified by Distribution Matching Distillation (DMD), has shown great promise in few-step generation but often sacrifices quality for sampling speed. While integrating Reinforcement Learning (RL) into distillation…

Machine Learning · Computer Science 2026-04-22 Linwei Dong , Ruoyu Guo , Ge Bai , Zehuan Yuan , Yawei Luo , Changqing Zou