One-Step Flow Policy Mirror Descent

• URL: http://arxiv.org/abs/2507.23675v2
• Date: Thu, 16 Oct 2025 00:28:10 GMT
• Title: One-Step Flow Policy Mirror Descent
• Authors: Tianyi Chen, Haitong Ma, Na Li, Kai Wang, Bo Dai,
• Abstract summary: Flow Policy Mirror Descent (FPMD) is an online RL algorithm that enables 1-step sampling during flow policy inference.<n>Our approach exploits a theoretical connection between the distribution variance and the discretization error of single-step sampling in straight flow matching models.
• Score: 52.31612487608593
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 responsiveness. To overcome this limitation, we propose Flow Policy Mirror Descent (FPMD), an online RL algorithm that enables 1-step sampling during flow policy inference. Our approach exploits a theoretical connection between the distribution variance and the discretization error of single-step sampling in straight interpolation flow matching models, and requires no extra distillation or consistency training. We present two algorithm variants based on rectified flow policy and MeanFlow policy, respectively. Extensive empirical evaluations on MuJoCo and visual DeepMind Control Suite benchmarks demonstrate that our algorithms show strong performance comparable to diffusion policy baselines while requiring orders of magnitude less computational cost during inference.

Related papers

• Coverage Improvement and Fast Convergence of On-policy Preference Learning [67.36750525893514]
  Online on-policy preference learning algorithms for language model alignment can significantly outperform their offline counterparts.<n>We analyze how the sampling policy's coverage evolves throughout on-policy training.<n>We develop principled on-policy schemes for reward distillation in the general function class setting.
  arXiv  Detail & Related papers  (2026-01-13T10:46:06Z)
• Contractive Diffusion Policies: Robust Action Diffusion via Contractive Score-Based Sampling with Differential Equations [19.77729438305312]
  Contractive Diffusion Policies (CDPs) induce contractive behavior in the diffusion sampling dynamics.<n>CDPs often outperform baseline policies, with pronounced benefits under data scarcity.
  arXiv  Detail & Related papers  (2026-01-02T23:33:59Z)
• 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)
• Decision Flow Policy Optimization [53.825268058199825]
  We show that generative models can effectively model complex multi-modal action distributions and achieve superior robotic control in continuous action spaces.<n>Previous methods usually adopt the generative models as behavior models to fit state-conditioned action distributions from datasets.<n>We propose Decision Flow, a unified framework that integrates multi-modal action distribution modeling and policy optimization.
  arXiv  Detail & Related papers  (2025-05-26T03:42:20Z)
• Efficient Online Reinforcement Learning for Diffusion Policy [38.39095131927252]
  We generalize the conventional denoising score matching by reweighting the loss function.<n>The resulting Reweighted Score Matching (RSM) preserves the optimal solution and low computational cost.<n>We introduce two practical algorithms named Diffusion Policy Mirror Descent (DPMD) and Soft Diffusion Actor-Critic (SDAC)
  arXiv  Detail & Related papers  (2025-02-01T07:55:06Z)
• Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization [55.97310586039358]
  Diffusion models have garnered widespread attention in Reinforcement Learning (RL) for their powerful expressiveness and multimodality.<n>We propose a novel model-free diffusion-based online RL algorithm, Q-weighted Variational Policy Optimization (QVPO)<n>Specifically, we introduce the Q-weighted variational loss, which can be proved to be a tight lower bound of the policy objective in online RL under certain conditions.<n>We also develop an efficient behavior policy to enhance sample efficiency by reducing the variance of the diffusion policy during online interactions.
  arXiv  Detail & Related papers  (2024-05-25T10:45:46Z)
• Diffusion Actor-Critic with Entropy Regulator [32.79341490514616]
  We propose an online RL algorithm termed diffusion actor-critic with entropy regulator (DACER)<n>This algorithm conceptualizes the reverse process of the diffusion model as a novel policy function.<n>Experiments on MuJoCo benchmarks and a multimodal task demonstrate that the DACER algorithm achieves state-of-the-art (SOTA) performance.
  arXiv  Detail & Related papers  (2024-05-24T03:23:27Z)
• Improved off-policy training of diffusion samplers [93.66433483772055]
  We study the problem of training diffusion models to sample from a distribution with an unnormalized density or energy function.<n>We benchmark several diffusion-structured inference methods, including simulation-based variational approaches and off-policy methods.<n>Our results shed light on the relative advantages of existing algorithms while bringing into question some claims from past work.
  arXiv  Detail & Related papers  (2024-02-07T18:51:49Z)
• DiffCPS: Diffusion Model based Constrained Policy Search for Offline Reinforcement Learning [11.678012836760967]
  Constrained policy search is a fundamental problem in offline reinforcement learning. We propose a novel approach, $textbfDiffusion-based Constrained Policy Search$ (dubbed DiffCPS)
  arXiv  Detail & Related papers  (2023-10-09T01:29:17Z)
• Policy Representation via Diffusion Probability Model for Reinforcement Learning [67.56363353547775]
  We build a theoretical foundation of policy representation via the diffusion probability model. We present a convergence guarantee for diffusion policy, which provides a theory to understand the multimodality of diffusion policy. We propose the DIPO which is an implementation for model-free online RL with DIffusion POlicy.
  arXiv  Detail & Related papers  (2023-05-22T15:23:41Z)
• Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning [70.20191211010847]
  Offline reinforcement learning (RL) aims to learn an optimal policy using a previously collected static dataset. We introduce Diffusion Q-learning (Diffusion-QL) that utilizes a conditional diffusion model to represent the policy. We show that our method can achieve state-of-the-art performance on the majority of the D4RL benchmark tasks.
  arXiv  Detail & Related papers  (2022-08-12T09:54:11Z)

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.