English
Related papers

Related papers: State Diversity Matters in Offline Behavior Distil…

200 papers

On-policy distillation (OPD) has emerged as an efficient post-training paradigm for large language models. However, existing studies largely attribute this advantage to denser and more stable supervision, while the parameter-level…

Computation and Language · Computer Science 2026-05-22 Yuchen Cai , Ding Cao , Liang Lin , Chunxi Luo , Xin Xu , Kai Yang , Weijie Liu , Saiyong Yang , Tianxiang Zhao , Guangzhong Sun , Guiquan Liu , Junfeng Fang

On-policy distillation (OPD) trains a student on its own trajectories under token-level teacher supervision, but existing methods are capped by a single-teacher capability ceiling: when the teacher errs, the student inherits the error. OPD…

Computation and Language · Computer Science 2026-05-05 Jianze Wang , Ying Liu , Jinlong Chen , Xuchun Hu , Qilong Zhang , Yu Cao , Jun Wang , Hua Yang , Yong Xie , Qianglong Chen

On-policy self-distillation (OPSD) is an emerging LLM post-training paradigm in which the model serves as its own teacher: conditioned on privileged information such as a reference trace or hint, the same policy provides dense token-level…

Machine Learning · Computer Science 2026-05-22 Hongbin Zhang , Chaozheng Wang , Kehai Chen , Youcheng Pan , Yang Xiang , Jinpeng Wang , Min Zhang

Deep Reinforcement Learning (RL) methods rely on experience replay to approximate the minibatched supervised learning setting; however, unlike supervised learning where access to lots of training data is crucial to generalization,…

Machine Learning · Computer Science 2021-02-24 Brett Daley , Cameron Hickert , Christopher Amato

Offline reinforcement learning (RL) aims to learn a policy that maximizes the expected return using a given static dataset of transitions. However, offline RL faces the distribution shift problem. The policy constraint offline RL method is…

Machine Learning · Computer Science 2025-12-24 Yuanhao Chen , Qi Liu , Pengbin Chen , Zhongjian Qiao , Yanjie Li

Reinforcement learning for multi-turn agents suffers from a credit-assignment mismatch: rewards are sparse and trajectory-level, while success often hinges on a few local decisions. Existing online policy distillation (OPD) provides denser…

Artificial Intelligence · Computer Science 2026-05-27 Yanfei Zhang , Xu Lin , Chenglin Wu

On-Policy Distillation (OPD) has emerged as a dominant post-training paradigm for large language models, especially for reasoning domains. However, OPD remains unstable in practice due to the high gradient variance of its single-sample…

Machine Learning · Computer Science 2026-05-11 Minjae Oh , Sangjun Song , Gyubin Choi , Yunho Choi , Yohan Jo

When applying offline reinforcement learning (RL) in healthcare scenarios, the out-of-distribution (OOD) issues pose significant risks, as inappropriate generalization beyond clinical expertise can result in potentially harmful…

Machine Learning · Computer Science 2025-05-23 Runze Yan , Xun Shen , Akifumi Wachi , Sebastien Gros , Anni Zhao , Xiao Hu

Large language models (LLMs) are increasingly adapted to proprietary and domain-specific corpora that contain sensitive information, creating a tension between formal privacy guarantees and efficient deployment through model compression.…

Machine Learning · Computer Science 2026-04-07 Fatemeh Khadem , Sajad Mousavi , Yi Fang , Yuhong Liu

Reinforcement learning (RL) has been widely used to train LLM agents for multi-turn interactive tasks, but its sample efficiency is severely limited by sparse rewards and long horizons. On-policy self-distillation (OPSD) alleviates this by…

Machine Learning · Computer Science 2026-04-14 Hao Wang , Guozhi Wang , Han Xiao , Yufeng Zhou , Yue Pan , Jichao Wang , Ke Xu , Yafei Wen , Xiaohu Ruan , Xiaoxin Chen , Honggang Qi

Offline reinforcement learning (RL) learns exclusively from static datasets, without further interaction with the environment. In practice, such datasets vary widely in quality, often mixing expert, suboptimal, and even random trajectories.…

Machine Learning · Computer Science 2025-10-15 Arip Asadulaev , Fakhri Karray , Martin Takac

Adapting large language models (LLMs) to long-context tasks requires post-training methods that remain accurate and coherent over thousands of tokens. Existing approaches are limited in several ways: 1) off-policy methods such as supervised…

Computation and Language · Computer Science 2026-05-13 Miguel Moura Ramos , Duarte M. Alves , André F. T. Martins

Dataset distillation creates a small distilled set that enables efficient training by capturing key information from the full dataset. While existing dataset distillation methods perform well on balanced datasets, they struggle under…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Xiao Cui , Yulei Qin , Xinyue Li , Wengang Zhou , Hongsheng Li , Houqiang Li

Dataset Distillation (DD) compresses large datasets into compact synthetic ones that maintain training performance. However, current methods mainly target sample reduction, with limited consideration of data precision and its impact on…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 My H. Dinh , Aditya Sant , Akshay Malhotra , Keya Patani , Shahab Hamidi-Rad

Sequential decision making algorithms often struggle to leverage different sources of unstructured offline interaction data. Imitation learning (IL) methods based on supervised learning are robust, but require optimal demonstrations, which…

Machine Learning · Computer Science 2023-04-28 Joey Hejna , Jensen Gao , Dorsa Sadigh

Transfer learning is devised to leverage knowledge from pre-trained models to solve new tasks with limited data and computational resources. Meanwhile, dataset distillation has emerged to synthesize a compact dataset that preserves critical…

Cryptography and Security · Computer Science 2026-03-06 Yuchen Shi , Huajie Chen , Heng Xu , Zhiquan Liu , Jialiang Shen , Chi Liu , Shuai Zhou , Tianqing Zhu , Wanlei Zhou

Offline reinforcement learning (RL) learns policies entirely from static datasets, thereby avoiding the challenges associated with online data collection. Practical applications of offline RL will inevitably require learning from datasets…

Machine Learning · Computer Science 2022-11-22 Anikait Singh , Aviral Kumar , Quan Vuong , Yevgen Chebotar , Sergey Levine

In offline reinforcement learning, a policy learns to maximize cumulative rewards with a fixed collection of data. Towards conservative strategy, current methods choose to regularize the behavior policy or learn a lower bound of the value…

Machine Learning · Computer Science 2021-03-02 Hongchang Zhang , Jianzhun Shao , Yuhang Jiang , Shuncheng He , Xiangyang Ji

In offline reinforcement learning (RL), addressing the out-of-distribution (OOD) action issue has been a focus, but we argue that there exists an OOD state issue that also impairs performance yet has been underexplored. Such an issue…

Machine Learning · Computer Science 2024-11-04 Yixiu Mao , Qi Wang , Chen Chen , Yun Qu , Xiangyang Ji

The recent success of supervised learning methods on ever larger offline datasets has spurred interest in the reinforcement learning (RL) field to investigate whether the same paradigms can be translated to RL algorithms. This research…

Machine Learning · Computer Science 2021-02-12 Mengjiao Yang , Ofir Nachum