English
Related papers

Related papers: Mean Flow Policy Optimization

200 papers

Flow based generative models have charted an impressive path across multiple visual generation tasks by adhering to a simple principle: learning velocity representations of a linear interpolant. However, we observe that training velocity…

Computer Vision and Pattern Recognition · Computer Science 2025-09-04 Inkyu Shin , Chenglin Yang , Liang-Chieh Chen

Recent advances in hierarchical robot systems leverage a high-level planner to propose task plans and a low-level policy to generate robot actions. This design allows training the planner on action-free or even non-robot data sources (e.g.,…

Robotics · Computer Science 2026-02-13 Yitian Zheng , Zhangchen Ye , Weijun Dong , Shengjie Wang , Yuyang Liu , Chongjie Zhang , Chuan Wen , Yang Gao

Offline reinforcement learning (RL) methods harness previous experiences to derive an optimal policy, forming the foundation for pre-trained large-scale models (PLMs). When encountering tasks not seen before, PLMs often utilize several…

Machine Learning · Computer Science 2024-11-05 Shengchao Hu , Wanru Zhao , Weixiong Lin , Li Shen , Ya Zhang , Dacheng Tao

Reinforcement learning (RL) has become central to enhancing reasoning in large language models (LLMs). Yet on-policy algorithms such as Group Relative Policy Optimization (GRPO) often suffer in early training: noisy gradients from…

Machine Learning · Computer Science 2026-03-19 Ziyan Wang , Zheng Wang , Xingwei Qu , Qi Cheng , Jie Fu , Shengpu Tang , Minjia Zhang , Xiaoming Huo

Diffusion Large Language Models (dLLMs) introduce a new paradigm for language generation, which in turn presents new challenges for aligning them with human preferences. In this work, we aim to improve the policy optimization for dLLMs by…

Diffusion-based models are recognized for their effectiveness in using real-world driving data to generate realistic and diverse traffic scenarios. These models employ guided sampling to incorporate specific traffic preferences and enhance…

Machine Learning · Computer Science 2025-02-19 Seungjun Yu , Kisung Kim , Daejung Kim , Haewook Han , Jinhan Lee

Learning from expert demonstrations is a promising approach for training robotic manipulation policies from limited data. However, imitation learning algorithms require a number of design choices ranging from the input modality, training…

Robotics · Computer Science 2024-09-12 Eugenio Chisari , Nick Heppert , Max Argus , Tim Welschehold , Thomas Brox , Abhinav Valada

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…

Offline reinforcement learning methods hold the promise of learning policies from pre-collected datasets without the need to query the environment for new transitions. This setting is particularly well-suited for continuous control robotic…

Machine Learning · Computer Science 2022-03-18 Xi Chen , Ali Ghadirzadeh , Tianhe Yu , Yuan Gao , Jianhao Wang , Wenzhe Li , Bin Liang , Chelsea Finn , Chongjie Zhang

Reinforcement learning algorithms require a large amount of samples; this often limits their real-world applications on even simple tasks. Such a challenge is more outstanding in multi-agent tasks, as each step of operation is more costly…

Machine Learning · Computer Science 2022-09-05 Yali Du , Chengdong Ma , Yuchen Liu , Runji Lin , Hao Dong , Jun Wang , Yaodong Yang

Diffusion policies have emerged as a powerful approach for robotic control, demonstrating superior expressiveness in modeling multimodal action distributions compared to conventional policy networks. However, their integration with online…

Machine Learning · Computer Science 2026-02-10 Wonhyeok Choi , Shutong Ding , Minwoo Choi , Jungwan Woo , Kyumin Hwang , Jaeyeul Kim , Ye Shi , Sunghoon Im

Reinforcement learning (RL)-based fine-tuning has emerged as a powerful approach for aligning diffusion models with black-box objectives. Proximal policy optimization (PPO) is a popular choice of method for policy optimization. While…

Flow-based image generative models exhibit stable training and produce high quality samples when using multi-step sampling procedures. One-step generative models can produce high quality image samples but can be difficult to optimize as…

Machine Learning · Computer Science 2026-04-13 Chia-Hong Hsu , Frank Wood

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

Flow-based policies have recently emerged as a powerful tool in offline and offline-to-online reinforcement learning, capable of modeling the complex, multimodal behaviors found in pre-collected datasets. However, the full potential of…

Machine Learning · Computer Science 2025-09-30 Deshu Chen , Yuchen Liu , Zhijian Zhou , Chao Qu , Yuan Qi

On-policy reinforcement learning methods, like Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO), often demand extensive data per update, leading to sample inefficiency. This paper introduces Reflective Policy…

Machine Learning · Computer Science 2024-06-07 Yaozhong Gan , Renye Yan , Zhe Wu , Junliang Xing

Online off-policy reinforcement learning (RL) is shaped by two coupled choices: the policy class and the update rule. Gaussian policies are fast and have tractable entropy, but struggle with multimodal action distributions. Generative…

Machine Learning · Computer Science 2026-05-22 Zeyuan Wang , Da Li , Yulin Chen , Yuehu Gong , Yanming Guo , Ye Shi , Liang Bai , Tianyuan Yu , Yanwei Fu

We present DeFlow, a decoupled offline RL framework that leverages flow matching to faithfully capture complex behavior manifolds. Optimizing generative policies is computationally prohibitive, typically necessitating backpropagation…

Machine Learning · Computer Science 2026-01-21 Zhancun Mu

With the uptake of intelligent data-driven applications, edge computing infrastructures necessitate a new generation of admission control algorithms to maximize system performance under limited and highly heterogeneous resources. In this…

Networking and Internet Architecture · Computer Science 2024-07-01 A. Fox , F. De Pellegrini , F. Faticanti , E. Altman , F. Bronzino

Diffusion models produce high-fidelity speech but are inefficient for real-time use due to long denoising steps and challenges in modeling intonation and rhythm. To improve this, we propose Diffusion Loss-Guided Policy Optimization (DLPO),…

Sound · Computer Science 2025-08-06 Jingyi Chen , Ju Seung Byun , Micha Elsner , Pichao Wang , Andrew Perrault