Fast and Highly Expressive Policy Learning for Offline Reinforcement Learning via Bootstrapped Flow Q-Learning

• URL: http://arxiv.org/abs/2606.10613v1
• Date: Tue, 09 Jun 2026 09:12:12 GMT
• Title: Fast and Highly Expressive Policy Learning for Offline Reinforcement Learning via Bootstrapped Flow Q-Learning
• Abstract summary: Bootstrapped Flow Q-Learning (BFQ) is a novel framework that enables accurate single-step action generation during both training and inference.<n>It eliminates multi-step denoising, resulting in a learning procedure that is substantially faster, simpler, and more robust.<n>Extensive D4RL evaluations show that BFQ improves performance while significantly reducing computational cost.
• Score: 27.992471782191014
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion-based Q-learning has emerged as a powerful paradigm for offline reinforcement learning, but its reliance on multi-step denoising makes both training and inference computationally expensive and brittle. Recent efforts to accelerate diffusion Q-learning toward single-step action generation typically introduce auxiliary networks, policy distillation, or multi-phase training, which frequently compromise simplicity, stability, or performance. To address these limitations, we introduce Bootstrapped Flow Q-Learning (BFQ), a novel framework that enables accurate single-step action generation during both training and inference, without auxiliary networks or distillation procedures. BFQ adopts a divide-and-conquer view of the displacement vector along the flow path: it begins by learning short-range displacements that can be accurately estimated from the Flow Matching marginal velocity, and bootstraps these components to directly learn a noise-to-action mapping in a single step. This formulation eliminates multi-step denoising, resulting in a learning procedure that is substantially faster, simpler, and more robust. Extensive D4RL evaluations show that BFQ improves performance while significantly reducing computational cost compared to multi-step diffusion baselines, demonstrating that single-step action generation suffices for high-performance offline Reinforcement Learning.

Related papers

• IR-Flow: Bridging Discriminative and Generative Image Restoration via Rectified Flow [46.532530550015736]
  We propose IR-Flow, a novel image restoration method based on Rectified Flow.<n>We first construct multilevel data distribution flows, which expand the ability of models to learn from and adapt to various levels of degradation.<n>We show that directly establishing a linear transport flow between degraded and clean image domains not only enables fast inference but also improves adaptability to out-of-distribution degradations.
  arXiv  Detail & Related papers  (2026-04-21T16:58:14Z)
• 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)
• Squeezing More from the Stream : Learning Representation Online for Streaming Reinforcement Learning [14.799267729619428]
  In streaming Reinforcement Learning (RL), transitions are observed and discarded immediately after a single update.<n>We propose extending Self-Predictive Representations (SPR) to the streaming pipeline to maximize the utility of every observed frame.<n>We show that our method learns significantly richer representations, bridging the performance gap caused by the absence of a replay buffer.
  arXiv  Detail & Related papers  (2026-02-10T04:06:32Z)
• Euphonium: Steering Video Flow Matching via Process Reward Gradient Guided Stochastic Dynamics [49.242224984144904]
  We propose Euphonium, a novel framework that steers generation via process reward gradient guided dynamics.<n>Our key insight is to formulate the sampling process as a theoretically principled algorithm that explicitly incorporates the gradient of a Process Reward Model.<n>We derive a distillation objective that internalizes the guidance signal into the flow network, eliminating inference-time dependency on the reward model.
  arXiv  Detail & Related papers  (2026-02-04T08:59:57Z)
• Q-learning with Adjoint Matching [58.78551025170267]
  We propose Q-learning with Adjoint Matching (QAM), a novel TD-based reinforcement learning (RL) algorithm.<n>QAM sidesteps two challenges by leveraging adjoint matching, a recently proposed technique in generative modeling.<n>It consistently outperforms prior approaches on hard, sparse reward tasks in both offline and offline-to-online RL.
  arXiv  Detail & Related papers  (2026-01-20T18:45:34Z)
• 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)
• 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)
• MeanFlowSE: one-step generative speech enhancement via conditional mean flow [13.437825847370442]
  MeanFlowSE is a conditional generative model that learns the average velocity over finite intervals along a trajectory.<n>On VoiceBank-DEMAND, the single-step model achieves strong intelligibility, fidelity, and perceptual quality with substantially lower computational cost than multistep baselines.
  arXiv  Detail & Related papers  (2025-09-18T11:24:47Z)
• Revisiting Diffusion Q-Learning: From Iterative Denoising to One-Step Action Generation [34.007490094198424]
  Diffusion Q-Learning (DQL) has established diffusion policies as a high-performing paradigm for offline reinforcement learning.<n>Current efforts to accelerate DQL toward one-step denoising rely on auxiliary modules or policy distillation.<n>One-Step Flow Q-Learning (OFQL) enables effective one-step action generation during both training and inference.
  arXiv  Detail & Related papers  (2025-08-19T15:05:55Z)
• Accelerating Diffusion Models in Offline RL via Reward-Aware Consistency Trajectory Distillation [88.4955839930215]
  We propose a novel approach to consistency distillation for offline reinforcement learning.<n>Our method enables single-step generation while maintaining higher performance and simpler training.
  arXiv  Detail & Related papers  (2025-06-09T14:48:19Z)
• Online Convolutional Re-parameterization [51.97831675242173]
  We present online convolutional re- parameterization (OREPA), a two-stage pipeline, aiming to reduce the huge training overhead by squeezing the complex training-time block into a single convolution. Compared with the state-of-the-art re-param models, OREPA is able to save the training-time memory cost by about 70% and accelerate the training speed by around 2x. We also conduct experiments on object detection and semantic segmentation and show consistent improvements on the downstream tasks.
  arXiv  Detail & Related papers  (2022-04-02T09:50:19Z)

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.