Imagen de Portada

Reinforcement Learning for Flow-Matching Policies

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Pfrommer, Samuel, Huang, Yixiao, Sojoudi, Somayeh
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Spooky Action at a Distance: Normalization Layers Enable Side-Channel Spatial Communication
por: Pfrommer, Samuel, et al.
Publicado: (2025)

Transport of Algebraic Structure to Latent Embeddings
por: Pfrommer, Samuel, et al.
Publicado: (2024)

Pausing Policy Learning in Non-stationary Reinforcement Learning
por: Lee, Hyunin, et al.
Publicado: (2024)

Reinforcement Learning via Value Gradient Flow
por: Xu, Haoran, et al.
Publicado: (2026)

Approximately Gaussian Replicator Flows: Nonconvex Optimization as a Nash-Convergent Evolutionary Game
por: Anderson, Brendon G., et al.
Publicado: (2024)

Transformers Provably Learn to Internalize Chain-of-Thought
por: Huang, Yixiao, et al.
Publicado: (2026)

OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models
por: Cheng, Ziheng, et al.
Publicado: (2025)

Multi-Objective Learning for Diffusion Models: A Statistical Theory under Semi-Supervised Learning
por: Cheng, Ziheng, et al.
Publicado: (2026)

Infinite-Horizon Reach-Avoid Zero-Sum Games via Deep Reinforcement Learning
por: Li, Jingqi, et al.
Publicado: (2022)

Evolving Diffusion and Flow Matching Policies for Online Reinforcement Learning
por: Zhang, Chubin, et al.
Publicado: (2025)

Ranking Manipulation for Conversational Search Engines
por: Pfrommer, Samuel, et al.
Publicado: (2024)

Do Sparse Autoencoders Identify Reasoning Features in Language Models?
por: Ma, George, et al.
Publicado: (2026)

Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers
por: Huang, Yixiao, et al.
Publicado: (2025)

ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning
por: Zhang, Tonghe, et al.
Publicado: (2025)

Mixing Classifiers to Alleviate the Accuracy-Robustness Trade-Off
por: Bai, Yatong, et al.
Publicado: (2023)

Absence of spurious solutions far from ground truth: A low-rank analysis with high-order losses
por: Ma, Ziye, et al.
Publicado: (2024)

FM-IRL: Flow-Matching for Reward Modeling and Policy Regularization in Reinforcement Learning
por: Wan, Zhenglin, et al.
Publicado: (2025)

Towards Optimal Branching of Linear and Semidefinite Relaxations for Neural Network Robustness Certification
por: Anderson, Brendon G., et al.
Publicado: (2021)

Flow Matching for Offline Reinforcement Learning with Discrete Actions
por: Khan, Fairoz Nower, et al.
Publicado: (2026)

DRAGON: Distributional Rewards Optimize Diffusion Generative Models
por: Bai, Yatong, et al.
Publicado: (2025)

Reverse Flow Matching: A Unified Framework for Online Reinforcement Learning with Diffusion and Flow Policies
por: Li, Zeyang, et al.
Publicado: (2026)

Efficient Global Optimization of Two-Layer ReLU Networks: Quadratic-Time Algorithms and Adversarial Training
por: Bai, Yatong, et al.
Publicado: (2022)

Energy-Weighted Flow Matching for Offline Reinforcement Learning
por: Zhang, Shiyuan, et al.
Publicado: (2025)

PolicyFlow: Policy Optimization with Continuous Normalizing Flow in Reinforcement Learning
por: Yang, Shunpeng, et al.
Publicado: (2026)

ConsistencyTTA: Accelerating Diffusion-Based Text-to-Audio Generation with Consistency Distillation
por: Bai, Yatong, et al.
Publicado: (2023)

Riemannian Flow Matching Policy for Robot Motion Learning
por: Braun, Max, et al.
Publicado: (2024)

Flow Matching Policy Gradients
por: McAllister, David, et al.
Publicado: (2025)

Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models
por: Lyu, Mingyang, et al.
Publicado: (2025)

Controllable Flow Matching for Online Reinforcement Learning
por: Wang, Bin, et al.
Publicado: (2025)

Improving the Accuracy-Robustness Trade-Off of Classifiers via Adaptive Smoothing
por: Bai, Yatong, et al.
Publicado: (2023)

MixedNUTS: Training-Free Accuracy-Robustness Balance via Nonlinearly Mixed Classifiers
por: Bai, Yatong, et al.
Publicado: (2024)

Quantile-Coupled Flow Matching for Distributional Reinforcement Learning
por: Groom, Michael, et al.
Publicado: (2026)

FlowCritic: Bridging Value Estimation with Flow Matching in Reinforcement Learning
por: Zhong, Shan, et al.
Publicado: (2025)

Online Matching via Reinforcement Learning: An Expert Policy Orchestration Strategy
por: Mignacco, Chiara, et al.
Publicado: (2025)

Discrete Flow Matching for Offline-to-Online Reinforcement Learning
por: Khan, Fairoz Nower, et al.
Publicado: (2026)

Flow-Based Policy for Online Reinforcement Learning
por: Lv, Lei, et al.
Publicado: (2025)

Latent Spherical Flow Policy for Reinforcement Learning with Combinatorial Actions
por: Kong, Lingkai, et al.
Publicado: (2026)

Composite Flow Matching for Reinforcement Learning with Shifted-Dynamics Data
por: Kong, Lingkai, et al.
Publicado: (2025)

Flow Matching with Injected Noise for Offline-to-Online Reinforcement Learning
por: Shin, Yongjae, et al.
Publicado: (2026)

Max-Entropy Reinforcement Learning with Flow Matching and A Case Study on LQR
por: Zhang, Yuyang, et al.
Publicado: (2025)