paper-with-me

Papers

Q-Flow: Stable and Expressive Reinforcement Learning with Flow-Based Policy

2026-05-13 · JaeHyeok Doo, Byeongguk Jeon, Seonghyeon Ye, Kimin Lee, Minjoon Seo arxiv

There is growing interest in utilizing flow-based models as decision-making policies in reinforcement learning due to their high expressive capacity. However, effectively leveraging this expressivity for value maximization remains challenging, as naive gradient-based optimization requires backpropagating through numerical solvers and often leads to instability. Existing approaches typically address this issue by restricting the expressive capacity of flow-based policies, resulting in a trade-off between optimization stability and representational flexibility. To resolve this, we introduce Q-Flow, a framework that leverages the deterministic nature of flow dynamics to explicitly propagate terminal trajectory value to intermediate latent states along the policy-induced flow. This formulation enables stable policy optimization using intermediate value gradients without unrolling the numerical solver, effectively bridging the gap between stability and expressivity. We evaluate Q-Flow in the offline learning setting on the challenging OGBench suite, where it consistently outperforms state-of-the-art baselines by an average of 10.6 percentage points, while also enabling stable online adaptation within the same framework.

📄 PDF Abstract BibTeX arXiv:2605.13435

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Flow Q-Learning

2025-02-04 · Seohong Park, Qiyang Li, Sergey Levine

We present flow Q-learning (FQL), a simple and performant offline reinforcement learning (RL) method that leverages an expressive flow-matching policy to model arbitrarily complex action distributions in data. Training a…

Action GenerationD4RLOffline RLQ-Learning+1

PolicyFlow: Policy Optimization with Continuous Normalizing Flow in Reinforcement Learning

2026-02-01 · Shunpeng Yang, Ben Liu, Hua Chen arxiv

Among on-policy reinforcement learning algorithms, Proximal Policy Optimization (PPO) demonstrates is widely favored for its simplicity, numerical stability, and strong empirical performance. Standard PPO relies on surro…

Reinforcement Learning

One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlow

2025-11-17 · Zeyuan Wang, Da Li, Yulin Chen, Ye Shi 외 arxiv

We introduce a one-step generative policy for offline reinforcement learning that maps noise directly to actions via a residual reformulation of MeanFlow, making it compatible with Q-learning. While one-step Gaussian pol…

Reinforcement Learning

EXPO: Stable Reinforcement Learning with Expressive Policies

2025-07-10 · Perry Dong, Qiyang Li, Dorsa Sadigh, Chelsea Finn arxiv

We study the problem of training and fine-tuning expressive policies with online reinforcement learning (RL) given an offline dataset. Training expressive policy classes with online RL present a unique challenge of stabl…

Reinforcement Learning

SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential Modeling

2025-09-30 · Yixian Zhang, Shu'ang Yu, Tonghe Zhang, Mo Guang 외 arxiv

Training expressive flow-based policies with off-policy reinforcement learning is notoriously unstable due to gradient pathologies in the multi-step action sampling process. We trace this instability to a fundamental con…

Reinforcement LearningContinuous Control