Copertina

Evolving Diffusion and Flow Matching Policies for Online Reinforcement Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhang, Chubin, Wan, Zhenglin, Chen, Feng, Yang, Fuchao, Feng, Lang, Zhou, Yaxin, Yu, Xingrui, You, Yang, Tsang, Ivor, An, Bo
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

Adversarial Dual On-Policy Distillation from Expressive Teacher
di: Wan, Zhenglin, et al.
Pubblicazione: (2026)

Letting Trajectories Spread: Quality-Preserving Control for Diverse Flow Matching
di: Wu, Jingxuan, et al.
Pubblicazione: (2025)

HBVLA: Pushing 1-Bit Post-Training Quantization for Vision-Language-Action Models
di: Yan, Xin, et al.
Pubblicazione: (2026)

Time-Annealed Perturbation Sampling: Diverse Generation for Diffusion Language Models
di: Wu, Jingxuan, et al.
Pubblicazione: (2026)

AgentOCR: Reimagining Agent History via Optical Self-Compression
di: Feng, Lang, et al.
Pubblicazione: (2026)

SA-VLA: Spatially-Aware Flow-Matching for Vision-Language-Action Reinforcement Learning
di: Pan, Xu, et al.
Pubblicazione: (2026)

Imitation from Diverse Behaviors: Wasserstein Quality Diversity Imitation Learning with Single-Step Archive Exploration
di: Yu, Xingrui, et al.
Pubblicazione: (2024)

Diversifying Policy Behaviors with Extrinsic Behavioral Curiosity
di: Wan, Zhenglin, et al.
Pubblicazione: (2024)

Flow-Factory: A Unified Framework for Reinforcement Learning in Flow-Matching Models
di: Ping, Bowen, et al.
Pubblicazione: (2026)

Advancing Analytic Class-Incremental Learning through Vision-Language Calibration
di: Zhao, Binyu, et al.
Pubblicazione: (2026)

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

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

Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration
di: Zhao, Heyang, et al.
Pubblicazione: (2025)

Mitigating Mismatch within Reference-based Preference Optimization
di: Yuan, Suqin, et al.
Pubblicazione: (2026)

Efficient Online Reinforcement Learning for Diffusion Policy
di: Ma, Haitong, et al.
Pubblicazione: (2025)

Reinforcement Learning for Flow-Matching Policies
di: Pfrommer, Samuel, et al.
Pubblicazione: (2025)

FlowRL: A Taxonomy and Modular Framework for Reinforcement Learning with Diffusion Policies
di: Gao, Chenxiao, et al.
Pubblicazione: (2026)

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

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

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

Towards Backdoor-Based Ownership Verification for Vision-Language-Action Models
di: Sun, Ming, et al.
Pubblicazione: (2026)

Fast Direct: Query-Efficient Online Black-box Guidance for Diffusion-model Target Generation
di: Tan, Kim Yong, et al.
Pubblicazione: (2025)

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

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

Policy Regularization on Globally Accessible States in Cross-Dynamics Reinforcement Learning
di: Xue, Zhenghai, et al.
Pubblicazione: (2025)

Truncated Rectified Flow Policy for Reinforcement Learning with One-Step Sampling
di: Zhou, Xubin, et al.
Pubblicazione: (2026)

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

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

Learning Discretized Neural Networks under Ricci Flow
di: Chen, Jun, et al.
Pubblicazione: (2023)

Flow Matching Policy Gradients
di: McAllister, David, et al.
Pubblicazione: (2025)

Do You Trust the Process?: Modeling Institutional Trust for Community Adoption of Reinforcement Learning Policies
di: Balepur, Naina, et al.
Pubblicazione: (2025)

Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning
di: Liu, Xu-Hui, et al.
Pubblicazione: (2024)

Balanced Image Stylization with Style Matching Score
di: Jiang, Yuxin, et al.
Pubblicazione: (2025)

PolicyEvol-Agent: Evolving Policy via Environment Perception and Self-Awareness with Theory of Mind
di: Yu, Yajie, et al.
Pubblicazione: (2025)

Uncover and Unlearn Nuisances: Agnostic Fully Test-Time Adaptation
di: Srey, Ponhvoan, et al.
Pubblicazione: (2025)

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

Mastering Continual Reinforcement Learning through Fine-Grained Sparse Network Allocation and Dormant Neuron Exploration
di: Zheng, Chengqi, et al.
Pubblicazione: (2025)

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field
di: Tan, Kim Yong, et al.
Pubblicazione: (2026)

Policy Dispersion in Non-Markovian Environment
di: Qu, Bohao, et al.
Pubblicazione: (2023)