Cover Image

ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Tonghe, Yu, Chao, Su, Sichang, Wang, Yu
Format:	Preprint
Published:	2025
Subjects:	Robotics Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential Modeling
by: Zhang, Yixian, et al.
Published: (2025)

Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models
by: Lyu, Mingyang, et al.
Published: (2025)

PolicyFlow: Policy Optimization with Continuous Normalizing Flow in Reinforcement Learning
by: Yang, Shunpeng, et al.
Published: (2026)

Flow Matching Policy Gradients
by: McAllister, David, et al.
Published: (2025)

Riemannian Flow Matching Policy for Robot Motion Learning
by: Braun, Max, et al.
Published: (2024)

VFP: Variational Flow-Matching Policy for Multi-Modal Robot Manipulation
by: Zhai, Xuanran, et al.
Published: (2025)

Quantile-Coupled Flow Matching for Distributional Reinforcement Learning
by: Groom, Michael, et al.
Published: (2026)

Translating Flow to Policy via Hindsight Online Imitation
by: Zheng, Yitian, et al.
Published: (2025)

ReinVBC: A Model-based Reinforcement Learning Approach to Vehicle Braking Controller
by: Lin, Haoxin, et al.
Published: (2026)

Flow with the Force Field: Learning 3D Compliant Flow Matching Policies from Force and Demonstration-Guided Simulation Data
by: Li, Tianyu, et al.
Published: (2025)

Fast and Robust Visuomotor Riemannian Flow Matching Policy
by: Ding, Haoran, et al.
Published: (2024)

FlowQ: Energy-Guided Flow Policies for Offline Reinforcement Learning
by: Alles, Marvin, et al.
Published: (2025)

Real-Time Generative Policy via Langevin-Guided Flow Matching for Autonomous Driving
by: Zhu, Tianze, et al.
Published: (2026)

$π_\texttt{RL}$: Online RL Fine-tuning for Flow-based Vision-Language-Action Models
by: Chen, Kang, et al.
Published: (2025)

Evolving Diffusion and Flow Matching Policies for Online Reinforcement Learning
by: Zhang, Chubin, et al.
Published: (2025)

SeFA-Policy: Fast and Accurate Visuomotor Policy Learning with Selective Flow Alignment
by: Xue, Rong, et al.
Published: (2025)

FocalPolicy: Frequency-Optimized Chunking and Locally Anchored Flow Matching for Coherent Visuomotor Policy
by: He, Qian, et al.
Published: (2026)

WarmPrior: Straightening Flow-Matching Policies with Temporal Priors
by: Kang, Sinjae, et al.
Published: (2026)

REFINE-DP: Diffusion Policy Fine-tuning for Humanoid Loco-manipulation via Reinforcement Learning
by: Gu, Zhaoyuan, et al.
Published: (2026)

FDPP: Fine-tune Diffusion Policy with Human Preference
by: Chen, Yuxin, et al.
Published: (2025)

FOSP: Fine-tuning Offline Safe Policy through World Models
by: Cao, Chenyang, et al.
Published: (2024)

Behavioral Mode Discovery for Fine-tuning Multimodal Generative Policies
by: Longhini, Alberta, et al.
Published: (2026)

Composite Gaussian Processes Flows for Learning Discontinuous Multimodal Policies
by: Wang, Shu-yuan, et al.
Published: (2025)

Online Planning for Multi-UAV Pursuit-Evasion in Unknown Environments Using Deep Reinforcement Learning
by: Chen, Jiayu, et al.
Published: (2024)

UniConFlow: A Unified Constrained Flow-Matching Framework for Certified Motion Planning
by: Yang, Zewen, et al.
Published: (2025)

Oracle-Guided Masked Contrastive Reinforcement Learning for Visuomotor Policies
by: Zhang, Yuhang, et al.
Published: (2025)

Flow-Opt: Scalable Centralized Multi-Robot Trajectory Optimization with Flow Matching and Differentiable Optimization
by: Idoko, Simon, et al.
Published: (2025)

FlowCorrect: Efficient Interactive Correction of Generative Flow Policies for Robotic Manipulation
by: Welte, Edgar, et al.
Published: (2026)

Causal Flow Q-Learning for Robust Offline Reinforcement Learning
by: Li, Mingxuan, et al.
Published: (2026)

Human Implicit Preference-Based Policy Fine-tuning for Multi-Agent Reinforcement Learning in USV Swarm
by: Kim, Hyeonjun, et al.
Published: (2025)

Dynamic Objects Relocalization in Changing Environments with Flow Matching
by: Argenziano, Francesco, et al.
Published: (2025)

Flow Matching Ergodic Coverage
by: Sun, Max Muchen, et al.
Published: (2025)

MOTO: Offline Pre-training to Online Fine-tuning for Model-based Robot Learning
by: Rafailov, Rafael, et al.
Published: (2024)

Flow-Based Single-Step Completion for Efficient and Expressive Policy Learning
by: Koirala, Prajwal, et al.
Published: (2025)

Multi-agent Coordination via Flow Matching
by: Lee, Dongsu, et al.
Published: (2025)

CRAFT: Counterfactual-to-Interactive Reinforcement Fine-Tuning for Driving Policies
by: Chen, Keyu, et al.
Published: (2026)

Latent Policy Steering through One-Step Flow Policies
by: Im, Hokyun, et al.
Published: (2026)

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows
by: Yang, Chenyu, et al.
Published: (2026)

HoRD: Robust Humanoid Control via History-Conditioned Reinforcement Learning and Online Distillation
by: Wang, Puyue, et al.
Published: (2026)

STRIDE: Structured Lagrangian and Stochastic Residual Dynamics via Flow Matching
by: Kotecha, Prakrut, et al.
Published: (2026)