English
Related papers

Related papers: Stochastic MeanFlow Policies: One-Step Generative …

200 papers

We introduce a one-step generative policy for offline reinforcement learning that maps noise directly to actions via a residual reformulation of MeanFlow, making it compatible with Q-learning. While one-step Gaussian policies enable fast…

Machine Learning · Computer Science 2025-11-18 Zeyuan Wang , Da Li , Yulin Chen , Ye Shi , Liang Bai , Tianyuan Yu , Yanwei Fu

Maximum entropy reinforcement learning (MaxEnt RL) has become a standard framework for sequential decision making, yet its standard Gaussian policy parameterization is inherently unimodal, limiting its ability to model complex multimodal…

Machine Learning · Computer Science 2026-04-13 Xubin Zhou , Yipeng Yang , Zhan Li

Diffusion policies have achieved great success in online reinforcement learning (RL) due to their strong expressive capacity. However, the inference of diffusion policy models relies on a slow iterative sampling process, which limits their…

Machine Learning · Computer Science 2025-10-17 Tianyi Chen , Haitong Ma , Na Li , Kai Wang , Bo Dai

Classical on-policy algorithms such as PPO and mirror descent policy optimization provide stable proximal policy updates through tractable action likelihoods, but are typically instantiated with simple Gaussian policies whose expressiveness…

Machine Learning · Computer Science 2026-05-29 Yuehu Gong , Zeyuan Wang , Yulin Chen , Shutong Ding , Qingyuan Zhou , Yanwei Fu

Robot manipulation has increasingly adopted data-driven generative policy frameworks, yet the field faces a persistent trade-off: diffusion models suffer from high inference latency, while flow-based methods often require complex…

Robotics · Computer Science 2026-01-30 Han Fang , Yize Huang , Yuheng Zhao , Paul Weng , Xiao Li , Yutong Ban

One-step generative modeling seeks to generate high-quality data samples in a single function evaluation, significantly improving efficiency over traditional diffusion or flow-based models. In this work, we introduce Modular MeanFlow (MMF),…

Machine Learning · Computer Science 2025-08-26 Haochen You , Baojing Liu , Hongyang He

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

Generative flow and diffusion models provide the continuous, multimodal action distributions needed for high-precision robotic policies. However, their reliance on iterative sampling introduces severe inference latency, degrading control…

Robotics · Computer Science 2026-03-16 Shaolong Li , Lichao Sun , Yongchao Chen

Diffusion and flow matching have emerged as expressive policy classes in reinforcement learning, but their reliance on multi-step denoising imposes substantial computational overhead at inference time, which is particularly problematic in…

Machine Learning · Computer Science 2026-05-25 Kyungyoon Kim , Donghyeon Ki , Hee-Jun Ahn , Byung-Jun Lee

Real-world fine-tuning of dexterous manipulation policies remains challenging due to limited real-world interaction budgets and highly multimodal action distributions. Diffusion-based policies, while expressive, do not permit conservative…

Robotics · Computer Science 2026-04-07 Chenyu Yang , Denis Tarasov , Davide Liconti , Hehui Zheng , Robert K. Katzschmann

We propose Drifting Field Policy (DFP), a non-ODE one-step generative policy built on the drifting model paradigm. We frame the policy update as a reverse-KL Wasserstein-2 gradient flow toward a soft target policy, so that each DFP update…

Machine Learning · Computer Science 2026-05-11 Juil Koo , Mingue Park , Jiwon Choi , Yunhong Min , Minhyuk Sung

The ability to learn multi-modal action distributions is indispensable for robotic manipulation policies to perform precise and robust control. Flow-based generative models have recently emerged as a promising solution to learning…

Robotics · Computer Science 2025-10-10 Guowei Zou , Haitao Wang , Hejun Wu , Yukun Qian , Yuhang Wang , Weibing Li

Offline reinforcement learning often relies on behavior regularization that enforces policies to remain close to the dataset distribution. However, such approaches fail to distinguish between high-value and low-value actions in their…

Diffusion policies are expressive yet incur high inference latency. Flow Matching (FM) enables one-step generation, but integrating it into Maximum Entropy Reinforcement Learning (MaxEnt RL) is challenging: the optimal policy is an…

Machine Learning · Computer Science 2026-02-03 Zeqiao Li , Yijing Wang , Haoyu Wang , Zheng Li , Zhiqiang Zuo

Recent works in Reinforcement Learning (RL) combine model-free (Mf)-RL algorithms with model-based (Mb)-RL approaches to get the best from both: asymptotic performance of Mf-RL and high sample-efficiency of Mb-RL. Inspired by these works,…

Machine Learning · Computer Science 2021-10-26 Soumya Rani Samineni

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

In recent years, generative models have shown remarkable capabilities across diverse fields, including images, videos, language, and decision-making. By applying powerful generative models such as flow-based models to reinforcement…

Machine Learning · Computer Science 2025-05-28 Jifeng Hu , Sili Huang , Siyuan Guo , Zhaogeng Liu , Li Shen , Lichao Sun , Hechang Chen , Yi Chang , Dacheng Tao

While behavior cloning with flow/diffusion policies excels at learning complex skills from demonstrations, it remains vulnerable to distributional shift, and standard RL methods struggle to fine-tune these models due to their iterative…

Machine Learning · Computer Science 2025-10-20 Mingyang Sun , Pengxiang Ding , Weinan Zhang , Donglin Wang

Generative policies based on expressive model classes, such as diffusion and flow matching, are well-suited to complex control problems with highly multimodal action distributions. Their expressivity, however, comes at a significant…

Machine Learning · Computer Science 2026-05-13 Christos Ziakas , Alessandra Russo , Avishek Joey Bose

A policy in deep reinforcement learning (RL), either deterministic or stochastic, is commonly parameterized as a Gaussian distribution alone, limiting the learned behavior to be unimodal. However, the nature of many practical…

Machine Learning · Computer Science 2025-08-20 SM Mazharul Islam , Manfred Huber
‹ Prev 1 2 3 10 Next ›