English
Related papers

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

200 papers

Diffusion policy sampling enables reinforcement learning (RL) to represent multimodal action distributions beyond suboptimal unimodal Gaussian policies. However, existing diffusion-based RL methods primarily focus on offline settings for…

Machine Learning · Computer Science 2026-05-07 Xiaoyuan Cheng , Wenxuan Yuan , Boyang Li , Yuanchao Xu , Yiming Yang , Hao Liang , Bei Peng , Robert Loftin , Zhuo Sun , Yukun Hu

On-policy distillation (OPD), which samples trajectories from the student model and supervises them with a teacher at the token level, avoids relying solely on verifiable terminal rewards and can yield better generalization than off-policy…

Offline reinforcement learning (RL) can learn optimal policies from pre-collected offline datasets without interacting with the environment, but the sampled actions of the agent cannot often cover the action distribution under a given…

Machine Learning · Computer Science 2024-06-14 Xuemin Hu , Shen Li , Yingfen Xu , Bo Tang , Long Chen

Offline reinforcement learning (RL) aims to learn optimal policies from previously collected datasets. Recently, due to their powerful representational capabilities, diffusion models have shown significant potential as policy models for…

Machine Learning · Computer Science 2024-05-30 Tianle Zhang , Jiayi Guan , Lin Zhao , Yihang Li , Dongjiang Li , Zecui Zeng , Lei Sun , Yue Chen , Xuelong Wei , Lusong Li , Xiaodong He

In recent advancements in Multi-agent Reinforcement Learning (MARL), its application has extended to various safety-critical scenarios. However, most methods focus on online learning, which presents substantial risks when deployed in…

Artificial Intelligence · Computer Science 2024-10-01 Jianuo Huang

While reinforcement learning methods such as Group Relative Preference Optimization (GRPO) have significantly enhanced Large Language Models, adapting them to diffusion models remains challenging. In particular, GRPO demands a stochastic…

Machine Learning · Computer Science 2025-10-10 Yihong Luo , Tianyang Hu , Jing Tang

Diffusion policies, widely adopted in decision-making scenarios such as robotics, gaming and autonomous driving, are capable of learning diverse skills from demonstration data due to their high representation power. However, the sub-optimal…

Machine Learning · Computer Science 2025-09-30 Ningyuan Yang , Jiaxuan Gao , Feng Gao , Yi Wu , Chao Yu

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

Aligning generative diffusion models with human preferences via reinforcement learning (RL) is critical yet challenging. Most existing algorithms are often vulnerable to reward hacking, such as quality degradation, over-stylization, or…

Diffusion models, such as Stable Diffusion, have shown incredible performance on text-to-image generation. Since text-to-image generation often requires models to generate visual concepts with fine-grained details and attributes specified…

Computer Vision and Pattern Recognition · Computer Science 2024-04-26 Xuehai He , Weixi Feng , Tsu-Jui Fu , Varun Jampani , Arjun Akula , Pradyumna Narayana , Sugato Basu , William Yang Wang , Xin Eric Wang

Online reinforcement learning is becoming increasingly important for aligning diffusion models with non-differentiable objectives. However, existing methods still face limitations in assigning fine-grained credit along denoising…

Machine Learning · Computer Science 2026-05-28 Zhengyang Liang , Qihang Zhang , Ceyuan Yang

Diffusion models, praised for their success in generative tasks, are increasingly being applied to robotics, demonstrating exceptional performance in behavior cloning. However, their slow generation process stemming from iterative denoising…

We propose DiFFPO, Diffusion Fast and Furious Policy Optimization, a unified framework for training masked diffusion large language models (dLLMs) to reason not only better (furious), but also faster via reinforcement learning (RL). We…

Machine Learning · Computer Science 2026-01-13 Hanyang Zhao , Dawen Liang , Wenpin Tang , David Yao , Nathan Kallus

Online reinforcement learning (RL) has been central to post-training language models, but its extension to diffusion models remains challenging due to intractable likelihoods. Recent works discretize the reverse sampling process to enable…

Machine Learning · Computer Science 2026-02-17 Kaiwen Zheng , Huayu Chen , Haotian Ye , Haoxiang Wang , Qinsheng Zhang , Kai Jiang , Hang Su , Stefano Ermon , Jun Zhu , Ming-Yu Liu

Offline reinforcement learning struggles with distributional shift and constrained performance due to static dataset limitations, while online RL demands prohibitive environment interactions. The recent advent of hybrid offline-to-online…

Machine Learning · Computer Science 2026-05-19 Qisai Liu , Zhanhong Jiang , Joshua Russell Waite , Aditya Balu , Cody Fleming , Soumik Sarkar

Multimodal Large Language Models (MLLMs) still struggle with fine-grained visual understanding, where answers often depend on small but decisive evidence in the full image. We observe a regional-to-global perception gap: the same MLLM…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Qianhao Yuan , Jie Lou , Xing Yu , Hongyu Lin , Le Sun , Xianpei Han , Yaojie Lu

Diffusion Q-Learning (DQL) has established diffusion policies as a high-performing paradigm for offline reinforcement learning, but its reliance on multi-step denoising for action generation renders both training and inference slow and…

Machine Learning · Computer Science 2026-02-25 Thanh Nguyen , Chang D. Yoo

Reinforcement learning (RL) has emerged as a powerful tool for aligning diffusion models with human preferences, typically by optimizing a single reward function under a KL regularization constraint. In practice, however, human preferences…

Machine Learning · Computer Science 2026-04-17 Qi Zhang , Dawei Wang , Shaofeng Zou

This work introduces Variational Diffusion Distillation (VDD), a novel method that distills denoising diffusion policies into Mixtures of Experts (MoE) through variational inference. Diffusion Models are the current state-of-the-art in…

Machine Learning · Computer Science 2024-10-22 Hongyi Zhou , Denis Blessing , Ge Li , Onur Celik , Xiaogang Jia , Gerhard Neumann , Rudolf Lioutikov