A Survey of Flow Matching in Reinforcement Learning

arXiv:2610.16275v1 Announce Type: new Abstract: Flow Matching (FM) has recently emerged as a principled and efficient generative modeling framework for reinforcement learning (RL), enabling expressive, multimodal policy parameterizations via deterministic probability transport. Compared to diffusion-based policies that rely on stochastic denoising chains, FM uses sampling based on ordinary differential equations (ODEs), with learned velocity fields, which can substantially reduce inference latency and simplify the incorporation of RL objectives. As research in flow-based RL rapidly accelerates across offline continuous control, online fine-tuning, and foundation model alignment, the literature has become highly fragmented. In this survey, we provide a comprehensive taxonomy of flow-matching approaches in reinforcement learning. We organize the literature along two axes: the target distribution being modeled (e.g., action policies, value critics, transition dynamics) and the mechanism of RL signal integration (e.g., energy-weighted regression, flow-based policy gradients, and group relative policy optimization). Furthermore, we survey emerging frontiers such as discrete and non-Euclidean action spaces, provide a systematic comparative analysis against Gaussian and diffusion baselines, and outline critical open problems. Ultimately, this survey serves as a foundational roadmap for the next generation of generative reinforcement learning and alignment.

Related

• Binary Flow Matching: Prediction-Loss Space Alignment for Robust Learning
• Reverse Flow Matching: A Unified Framework for Online Reinforcement Learning with Diffusion and Flow Policies
• FM-IRL: Flow-Matching for Reward Modeling and Policy Regularization in Reinforcement Learning
• Flow Matching for Offline Reinforcement Learning with Discrete Actions

Source: arXiv cs.LG | 2026-10-14