Unleashing Flow Policies with Distributional Critics

• URL: http://arxiv.org/abs/2509.23087v1
• Date: Sat, 27 Sep 2025 03:51:06 GMT
• Title: Unleashing Flow Policies with Distributional Critics
• Authors: Deshu Chen, Yuchen Liu, Zhijian Zhou, Chao Qu, Yuan Qi,
• Abstract summary: We introduce the Distributional Flow Critic (DFC), a novel critic architecture that learns the complete state-action return distribution.<n>DFC provides the expressive flow-based policy with a rich, distributional Bellman target, which offers a more stable and informative learning signal.
• Score: 15.149475517073258
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 these expressive actors is often bottlenecked by their critics, which typically learn a single, scalar estimate of the expected return. To address this limitation, we introduce the Distributional Flow Critic (DFC), a novel critic architecture that learns the complete state-action return distribution. Instead of regressing to a single value, DFC employs flow matching to model the distribution of return as a continuous, flexible transformation from a simple base distribution to the complex target distribution of returns. By doing so, DFC provides the expressive flow-based policy with a rich, distributional Bellman target, which offers a more stable and informative learning signal. Extensive experiments across D4RL and OGBench benchmarks demonstrate that our approach achieves strong performance, especially on tasks requiring multimodal action distributions, and excels in both offline and offline-to-online fine-tuning compared to existing methods.

Related papers

• Flow Actor-Critic for Offline Reinforcement Learning [20.074534038481666]
  We propose Flow Actor-Critic, a new actor-critic method for offline RL, based on recent flow policies.<n>We achieve new state-of-the-art performance for test datasets of offline RL including the D4RL and recent OGBench benchmarks.
  arXiv  Detail & Related papers  (2026-02-20T06:11:12Z)
• DFPO: Scaling Value Modeling via Distributional Flow towards Robust and Generalizable LLM Post-Training [94.568675548967]
  Training reinforcement learning (RL) systems in real-world environments remains challenging due to noisy supervision and poor out-of-domain generalization.<n>Recent distributional RL methods improve robustness by modeling values with multiple quantile points, but they still learn each quantile independently as a scalar.<n>We propose DFPO, a robust distributional RL framework that models values as continuous flows across time steps.
  arXiv  Detail & Related papers  (2026-02-05T17:07:42Z)
• Deep Leakage with Generative Flow Matching Denoiser [54.05993847488204]
  We introduce a new deep leakage (DL) attack that integrates a generative Flow Matching (FM) prior into the reconstruction process.<n>Our approach consistently outperforms state-of-the-art attacks across pixel-level, perceptual, and feature-based similarity metrics.
  arXiv  Detail & Related papers  (2026-01-21T14:51:01Z)
• Reverse Flow Matching: A Unified Framework for Online Reinforcement Learning with Diffusion and Flow Policies [4.249024052507976]
  We propose a unified framework, reverse flow matching (RFM), which rigorously addresses the problem of training diffusion and flow models without direct target samples.<n>By adopting a reverse inferential perspective, we formulate the training target as a posterior mean estimation problem given an intermediate noisy sample.<n>We show that existing noise-expectation and gradient-expectation methods are two specific instances within this broader class.
  arXiv  Detail & Related papers  (2026-01-13T01:58:24Z)
• Offline Meta-Reinforcement Learning with Flow-Based Task Inference and Adaptive Correction of Feature Overgeneralization [12.107082786676907]
  offline meta-reinforcement learning (OMRL) combines the strengths of learning from diverse datasets in offline RL with the adaptability to new tasks of meta-RL.<n>Existing research indicates that the generalization of the $Q$ network affects the extrapolation error in offline RL.<n>We propose FLORA, which identifies OOD samples by modeling feature distributions and estimating their uncertainties.
  arXiv  Detail & Related papers  (2026-01-12T03:16:07Z)
• Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach [78.4812458793128]
  We propose textbfTACO, a test-time-scaling framework that applies a lightweight pseudo-count estimator as a high-fidelity verifier of action chunks.<n>Our method resembles the classical anti-exploration principle in offline reinforcement learning (RL), and being gradient-free, it incurs significant computational benefits.
  arXiv  Detail & Related papers  (2025-12-02T14:42:54Z)
• 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)
• One-Step Flow Policy Mirror Descent [52.31612487608593]
  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.
  arXiv  Detail & Related papers  (2025-07-31T15:51:10Z)
• Flow-Based Single-Step Completion for Efficient and Expressive Policy Learning [0.0]
  We propose a generative policy trained with an augmented flow-matching objective to predict direct completion vectors from intermediate flow samples.<n>Our method scales effectively to offline, offline-to-online, and online RL settings, offering substantial gains in speed and adaptability.<n>We extend SSCP to goal-conditioned RL, enabling flat policies to exploit subgoal structures without explicit hierarchical inference.
  arXiv  Detail & Related papers  (2025-06-26T16:09:53Z)
• 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)
• Offline Multi-agent Reinforcement Learning via Score Decomposition [51.23590397383217]
  offline cooperative multi-agent reinforcement learning (MARL) faces unique challenges due to distributional shifts.<n>This work is the first work to explicitly address the distributional gap between offline and online MARL.
  arXiv  Detail & Related papers  (2025-05-09T11:42:31Z)
• Streetwise Agents: Empowering Offline RL Policies to Outsmart Exogenous Stochastic Disturbances in RTC [21.20874303316171]
  We propose a novel post-deployment shaping of policies conditioned on real-time characterization of out-of-distribution sub-spaces. Our experimental results on BWE and other standard offline RL benchmark environments demonstrate a significant improvement.
  arXiv  Detail & Related papers  (2024-11-11T09:22:09Z)
• Diffusion Policies for Out-of-Distribution Generalization in Offline Reinforcement Learning [1.7205106391379026]
  We propose a novel method that incorporates state reconstruction feature learning in the recent class of diffusion policies.<n>Our method promotes learning of generalizable state representation to alleviate the distribution shift caused by OOD states.
  arXiv  Detail & Related papers  (2023-07-10T17:34:23Z)
• Integrating Local Real Data with Global Gradient Prototypes for Classifier Re-Balancing in Federated Long-Tailed Learning [60.41501515192088]
  Federated Learning (FL) has become a popular distributed learning paradigm that involves multiple clients training a global model collaboratively. The data samples usually follow a long-tailed distribution in the real world, and FL on the decentralized and long-tailed data yields a poorly-behaved global model. In this work, we integrate the local real data with the global gradient prototypes to form the local balanced datasets.
  arXiv  Detail & Related papers  (2023-01-25T03:18:10Z)
• Exploration with Multi-Sample Target Values for Distributional Reinforcement Learning [20.680417111485305]
  We introduce multi-sample target values (MTV) for distributional RL, as a principled replacement for single-sample target value estimation. The improved distributional estimates lend themselves to UCB-based exploration. We evaluate our approach on a range of continuous control tasks and demonstrate state-of-the-art model-free performance on difficult tasks such as Humanoid control.
  arXiv  Detail & Related papers  (2022-02-06T03:27:05Z)
• COMBO: Conservative Offline Model-Based Policy Optimization [120.55713363569845]
  Uncertainty estimation with complex models, such as deep neural networks, can be difficult and unreliable. We develop a new model-based offline RL algorithm, COMBO, that regularizes the value function on out-of-support state-actions. We find that COMBO consistently performs as well or better as compared to prior offline model-free and model-based methods.
  arXiv  Detail & Related papers  (2021-02-16T18:50:32Z)
• Conservative Q-Learning for Offline Reinforcement Learning [106.05582605650932]
  We show that CQL substantially outperforms existing offline RL methods, often learning policies that attain 2-5 times higher final return. We theoretically show that CQL produces a lower bound on the value of the current policy and that it can be incorporated into a policy learning procedure with theoretical improvement guarantees.
  arXiv  Detail & Related papers  (2020-06-08T17:53:42Z)

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.