English
Related papers

Related papers: One-Step Flow Policy Mirror Descent

200 papers

Reinforcement learning has emerged as a powerful tool for improving diffusion-based text-to-image models, but existing methods are largely limited to single-task optimization. Extending RL to multiple tasks is challenging: joint…

Machine Learning · Computer Science 2026-05-15 Quanhao Li , Junqiu Yu , Kaixun Jiang , Yujie Wei , Zhen Xing , Pandeng Li , Ruihang Chu , Shiwei Zhang , Yu Liu , Zuxuan Wu

We introduce Discrete flow Matching policy Optimization (DoMinO), a unified framework for Reinforcement Learning (RL) fine-tuning Discrete Flow Matching (DFM) models under a broad class of policy gradient methods. Our key idea is to view…

Machine Learning · Computer Science 2026-04-09 Maojiang Su , Po-Chung Hsieh , Weimin Wu , Mingcheng Lu , Jiunhau Chen , Jerry Yao-Chieh Hu , Han Liu

Few-step diffusion or flow-based generative models typically distill a velocity-predicting teacher into a student that predicts a shortcut towards denoised data. This format mismatch has led to complex distillation procedures that often…

Machine Learning · Computer Science 2026-02-20 Hansheng Chen , Kai Zhang , Hao Tan , Leonidas Guibas , Gordon Wetzstein , Sai Bi

This research gauges the ability of deep reinforcement learning (DRL) techniques to assist the optimization and control of fluid mechanical systems. It combines a novel, "degenerate" version of the proximal policy optimization (PPO)…

Optimization and Control · Mathematics 2021-05-19 H. Ghraieb , J. Viquerat , A. Larcher , P. Meliga , E. Hachem

Generative models, particularly diffusion model, have emerged as powerful tools for sequential recommendation. However, accurately modeling user preferences remains challenging due to the noise perturbations inherent in the forward and…

Information Retrieval · Computer Science 2025-05-23 Feng Liu , Lixin Zou , Xiangyu Zhao , Min Tang , Liming Dong , Dan Luo , Xiangyang Luo , Chenliang Li

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

Policy Mirror Descent (PMD) is a powerful and theoretically sound methodology for sequential decision-making. However, it is not directly applicable to Reinforcement Learning (RL) due to the inaccessibility of explicit action-value…

Machine Learning · Computer Science 2024-11-01 Pietro Novelli , Marco Pratticò , Massimiliano Pontil , Carlo Ciliberto

Generative models, particularly diffusion models, have achieved remarkable success in density estimation for multimodal data, drawing significant interest from the reinforcement learning (RL) community, especially in policy modeling in…

Machine Learning · Computer Science 2024-12-03 Jinouwen Zhang , Rongkun Xue , Yazhe Niu , Yun Chen , Jing Yang , Hongsheng Li , Yu Liu

Generative models such as diffusion and flow-matching offer expressive policies for offline reinforcement learning (RL) by capturing rich, multimodal action distributions, but their iterative sampling introduces high inference costs and…

Machine Learning · Computer Science 2026-02-26 Prajwal Koirala , Cody Fleming

Reinforcement learning (RL) has been effective for post-training autoregressive (AR) language models, but extending these methods to diffusion language models (DLMs) is challenging due to intractable sequence-level likelihoods. Existing…

Visual-motor policy learning has advanced with architectures like diffusion-based policies, known for modeling complex robotic trajectories. However, their prolonged inference times hinder high-frequency control tasks requiring real-time…

Robotics · Computer Science 2024-12-20 Bofang Jia , Pengxiang Ding , Can Cui , Mingyang Sun , Pengfang Qian , Siteng Huang , Zhaoxin Fan , Donglin Wang

Diffusion-based visuomotor policies excel at learning complex robotic tasks by effectively combining visual data with high-dimensional, multi-modal action distributions. However, diffusion models often suffer from slow inference due to…

Robotics · Computer Science 2025-08-08 Haoran Ding , Noémie Jaquier , Jan Peters , Leonel Rozo

Diffusion models (DMs) have significantly advanced the development of real-world image super-resolution (Real-ISR), but the computational cost of multi-step diffusion models limits their application. One-step diffusion models generate…

Computer Vision and Pattern Recognition · Computer Science 2025-02-13 Jianze Li , Jiezhang Cao , Yong Guo , Wenbo Li , Yulun Zhang

Distillation addresses the slow sampling problem in diffusion models by creating models with smaller size or fewer steps that approximate the behavior of high-step teachers. In this work, we propose a reinforcement learning based…

Machine Learning · Computer Science 2025-12-30 Amirhossein Tighkhorshid , Zahra Dehghanian , Gholamali Aminian , Chengchun Shi , Hamid R. Rabiee

We propose a new policy gradient method, named homotopic policy mirror descent (HPMD), for solving discounted, infinite horizon MDPs with finite state and action spaces. HPMD performs a mirror descent type policy update with an additional…

Machine Learning · Computer Science 2022-11-30 Yan Li , Guanghui Lan , Tuo Zhao

The wide application of flow-matching methods has greatly promoted the development of robot imitation learning. However, these methods all face the problem of high inference time. To address this issue, researchers have proposed…

Robotics · Computer Science 2025-10-23 Yu Fang , Xinyu Wang , Xuehe Zhang , Wanli Xue , Mingwei Zhang , Shengyong Chen , Jie Zhao

We consider the problem of solving robust Markov decision process (MDP), which involves a set of discounted, finite state, finite action space MDPs with uncertain transition kernels. The goal of planning is to find a robust policy that…

Machine Learning · Computer Science 2023-06-13 Yan Li , Guanghui Lan , Tuo Zhao

The use of guidance to steer sampling toward desired outcomes has been widely explored within diffusion models, especially in applications such as image and trajectory generation. However, incorporating guidance during training remains…

Machine Learning · Computer Science 2025-05-21 Marvin Alles , Nutan Chen , Patrick van der Smagt , Botond Cseke

Real-time robotic control demands fast action generation. However, existing generative policies based on diffusion and flow matching require multi-step sampling, fundamentally limiting deployment in time-critical scenarios. We propose…

Robotics · Computer Science 2026-01-29 Guowei Zou , Haitao Wang , Hejun Wu , Yukun Qian , Yuhang Wang , Weibing Li

Offline Reinforcement Learning (RL) learns optimal policies from fixed datasets, training a policy once and deploying it at inference time without further refinement. Inspired by model predictive control (MPC), we introduce an inference…

Machine Learning · Computer Science 2026-05-21 Rohan Deb , Stephen J. Wright , Arindam Banerjee