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

• URL: http://arxiv.org/abs/2505.22094v6
• Date: Fri, 31 Oct 2025 19:10:29 GMT
• Title: ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning
• Abstract summary: ReinFlow is an online reinforcement learning framework for continuous robotic control.<n>It injects learnable noise into a flow policy's deterministic path, converting the flow into a discrete-time Markov Process.<n>We benchmark ReinFlow in representative locomotion and manipulation tasks.
• Score: 7.452631636467998
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose ReinFlow, a simple yet effective online reinforcement learning (RL) framework that fine-tunes a family of flow matching policies for continuous robotic control. Derived from rigorous RL theory, ReinFlow injects learnable noise into a flow policy's deterministic path, converting the flow into a discrete-time Markov Process for exact and straightforward likelihood computation. This conversion facilitates exploration and ensures training stability, enabling ReinFlow to fine-tune diverse flow model variants, including Rectified Flow [35] and Shortcut Models [19], particularly at very few or even one denoising step. We benchmark ReinFlow in representative locomotion and manipulation tasks, including long-horizon planning with visual input and sparse reward. The episode reward of Rectified Flow policies obtained an average net growth of 135.36% after fine-tuning in challenging legged locomotion tasks while saving denoising steps and 82.63% of wall time compared to state-of-the-art diffusion RL fine-tuning method DPPO [43]. The success rate of the Shortcut Model policies in state and visual manipulation tasks achieved an average net increase of 40.34% after fine-tuning with ReinFlow at four or even one denoising step, whose performance is comparable to fine-tuned DDIM policies while saving computation time for an average of 23.20%. Project webpage: https://reinflow.github.io/

Related papers

• Reversal Q-Learning [57.43956630070019]
  Reversal Q-learning is an off-policy RL algorithm that trains a flow policy based on prior data.<n>We show that RQL leads to the best average offline RL performance compared to state-of-the-art flow-based offline RL algorithms.
  arXiv  Detail & Related papers  (2026-06-16T05:56:10Z)
• Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models [61.74572554094633]
  We argue that ratio clipping is structurally ill-suited for flow models.<n>We propose Flow-DPPO, which replaces ratio clipping with a divergence proximal constraint.<n> Experiments show that Flow-DPPO achieves higher rewards with better KL-proximal efficiency.
  arXiv  Detail & Related papers  (2026-06-09T15:59:57Z)
• Score-Based One-step MeanFlow Policy Optimization [4.94481688445056]
  MeanFlow offers a promising alternative by learning an average velocity field that maps noise to data in a single network evaluation.<n>We propose Score-Based One-step MeanFlow Policy Optimization (SOM), an actor-critic algorithm that resolves this by constructing the target velocity field directly from the Q-function.<n>SOM achieves state-of-the-art performance on locomotion tasks with a single generation step, while substantially reducing both training and inference time compared to prior diffusion- and flow-matching-based policies.
  arXiv  Detail & Related papers  (2026-05-22T08:28:51Z)
• ScoRe-Flow: Complete Distributional Control via Score-Based Reinforcement Learning for Flow Matching [14.421249343302028]
  Flow Matching (FM) policies have emerged as an efficient backbone for robotic control.<n>We propose ScoRe-Flow, a score-based RL fine-tuning method to achieve decoupled control over the mean and variance of transitions.
  arXiv  Detail & Related papers  (2026-04-13T03:56:37Z)
• EFlow: Fast Few-Step Video Generator Training from Scratch via Efficient Solution Flow [52.73538517981873]
  EFlow is an efficient few-step training framework for video diffusion transformers.<n> Gated Local-Global Attention is a token-droppable hybrid block.<n>Path-Drop Guided training replaces the expensive target with a computationally cheap, weak path.
  arXiv  Detail & Related papers  (2026-03-28T02:06:55Z)
• KAN We Flow? Advancing Robotic Manipulation with 3D Flow Matching via KAN & RWKV [15.840121055564405]
  KAN-We-Flow is a flow-matching policy that builds a lightweight backbone for 3D manipulation.<n>Our design reduces parameters by 86.8%, maintains fast runtime, and achieves state-of-the-art success rates on Adroit, Meta-World, and DexArt benchmarks.
  arXiv  Detail & Related papers  (2026-02-01T09:27:56Z)
• SuperFlow: Training Flow Matching Models with RL on the Fly [40.46209466164144]
  SuperFlow is an RL training framework for flow-based models that adjusts group sizes with variance-aware sampling.<n>It reaches promising performance while using only 5.4% to 56.3% of the original training steps.<n>It reduces training time by 5.2% to 16.7% without any architectural changes.
  arXiv  Detail & Related papers  (2025-12-17T02:44:11Z)
• Flow Straighter and Faster: Efficient One-Step Generative Modeling via MeanFlow on Rectified Trajectories [14.36205662558203]
  Rectified MeanFlow is a framework that models the mean velocity field along the rectified trajectory using only a single reflow step.<n>Experiments on ImageNet at 64, 256, and 512 resolutions show that Re-MeanFlow consistently outperforms prior one-step flow distillation and Rectified Flow methods in both sample quality and training efficiency.
  arXiv  Detail & Related papers  (2025-11-28T16:50:08Z)
• One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlow [56.13949180229929]
  We introduce a one-step generative policy for offline reinforcement learning that maps noise directly to actions via a residual reformulation of MeanFlow.<n>Our method achieves strong performance in both offline and offline-to-online reinforcement learning settings.
  arXiv  Detail & Related papers  (2025-11-17T06:34:17Z)
• Iterative Refinement of Flow Policies in Probability Space for Online Reinforcement Learning [56.47948583452555]
  We introduce the Stepwise Flow Policy (SWFP) framework, founded on the key insight that discretizing the flow matching inference process via a fixed-step Euler scheme aligns it with the variational Jordan-Kinderlehrer-Otto principle from optimal transport.<n>SWFP decomposes the global flow into a sequence of small, incremental transformations between proximate distributions.<n>This decomposition yields an efficient algorithm that fine-tunes pre-trained flows via a cascade of small flow blocks, offering significant advantages.
  arXiv  Detail & Related papers  (2025-10-17T07:43:51Z)
• SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential Modeling [9.936731043466699]
  Training expressive flow-based policies with off-policy reinforcement learning is notoriously unstable due to gradient pathologies in the multi-step action sampling process.<n>We trace this instability to a fundamental connection: the flow rollout is algebraically equivalent to a residual recurrent computation, making it susceptible to the same vanishing and exploding gradients as RNNs.<n>We develop a practical SAC-based algorithm, enabled by a noise-augmented rollout, that facilitates direct end-to-end training of these policies.
  arXiv  Detail & Related papers  (2025-09-30T04:21:20Z)
• Mean Flows for One-step Generative Modeling [64.4997821467102]
  We propose a principled and effective framework for one-step generative modeling.<n>A well-defined identity between average and instantaneous velocities is derived and used to guide neural network training.<n>Our method, termed the MeanFlow model, is self-contained and requires no pre-training, distillation, or curriculum learning.
  arXiv  Detail & Related papers  (2025-05-19T17:59:42Z)
• Flow-GRPO: Training Flow Matching Models via Online RL [75.70017261794422]
  We propose Flow-GRPO, the first method integrating online reinforcement learning (RL) into flow matching models.<n>Our approach uses two key strategies: (1) an ODE-to-SDE conversion that transforms a deterministic Ordinary Equation (ODE) into an equivalent Differential Equation (SDE) that matches the original model's marginal distribution at all timesteps; and (2) a Denoising Reduction strategy that reduces training denoising steps while retaining the original inference timestep number.
  arXiv  Detail & Related papers  (2025-05-08T17:58:45Z)
• FlowTS: Time Series Generation via Rectified Flow [67.41208519939626]
  FlowTS is an ODE-based model that leverages rectified flow with straight-line transport in probability space.<n>For unconditional setting, FlowTS achieves state-of-the-art performance, with context FID scores of 0.019 and 0.011 on Stock and ETTh datasets.<n>For conditional setting, we have achieved superior performance in solar forecasting.
  arXiv  Detail & Related papers  (2024-11-12T03:03:23Z)
• Improving the Training of Rectified Flows [14.652876697052156]
  Diffusion models have shown great promise for image and video generation, but sampling from state-of-the-art models requires expensive numerical integration of a generative ODE. One approach for tackling this problem is rectified flows, which iteratively learn smooth ODE paths that are less susceptible to truncation error. We propose improved techniques for training rectified flows, allowing them to compete with emphknowledge distillation methods even in the low NFE setting. Our improved rectified flow outperforms the state-of-the-art distillation methods such as consistency distillation and progressive distillation in both one-step and two
  arXiv  Detail & Related papers  (2024-05-30T17:56:04Z)
• PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator [73.80050807279461]
  Piecewise Rectified Flow (PeRFlow) is a flow-based method for accelerating diffusion models. PeRFlow achieves superior performance in a few-step generation.
  arXiv  Detail & Related papers  (2024-05-13T07:10:53Z)
• OptFlow: Fast Optimization-based Scene Flow Estimation without Supervision [6.173968909465726]
  We present OptFlow, a fast optimization-based scene flow estimation method. It achieves state-of-the-art performance for scene flow estimation on popular autonomous driving benchmarks.
  arXiv  Detail & Related papers  (2024-01-04T21:47:56Z)
• Context-Aware Iteration Policy Network for Efficient Optical Flow Estimation [19.077966606237897]
  We develop a Context-Aware Iteration Policy Network for efficient optical flow estimation. Our method maintains performance while reducing FLOPs by about 40%/20% for the Sintel/ KITTI datasets.
  arXiv  Detail & Related papers  (2023-12-12T11:27:13Z)
• Towards Understanding and Improving GFlowNet Training [71.85707593318297]
  We introduce an efficient evaluation strategy to compare the learned sampling distribution to the target reward distribution. We propose prioritized replay training of high-reward $x$, relative edge flow policy parametrization, and a novel guided trajectory balance objective.
  arXiv  Detail & Related papers  (2023-05-11T22:50:41Z)
• Normalizing flow neural networks by JKO scheme [22.320632565424745]
  We develop a neural ODE flow network called JKO-iFlow, inspired by the Jordan-Kinderleherer-Otto scheme. The proposed method stacks residual blocks one after another, allowing efficient block-wise training of the residual blocks. Experiments with synthetic and real data show that the proposed JKO-iFlow network achieves competitive performance.
  arXiv  Detail & Related papers  (2022-12-29T18:55:00Z)
• GMFlow: Learning Optical Flow via Global Matching [124.57850500778277]
  We propose a GMFlow framework for learning optical flow estimation. It consists of three main components: a customized Transformer for feature enhancement, a correlation and softmax layer for global feature matching, and a self-attention layer for flow propagation. Our new framework outperforms 32-iteration RAFT's performance on the challenging Sintel benchmark.
  arXiv  Detail & Related papers  (2021-11-26T18:59:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.