Copertina

WarmPrior: Straightening Flow-Matching Policies with Temporal Priors

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kang, Sinjae, Kim, Chanyoung, Wang, Kaixin, Zhao, Li, Lee, Kimin
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence Robotics
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Safe Exploration via Policy Priors
di: Wendl, Manuel, et al.
Pubblicazione: (2026)

DEAS: DEtached value learning with Action Sequence for Scalable Offline RL
di: Kim, Changyeon, et al.
Pubblicazione: (2025)

Quality over Quantity: Demonstration Curation via Influence Functions for Data-Centric Robot Learning
di: Lee, Haeone, et al.
Pubblicazione: (2026)

Automated Skill Discovery for Language Agents through Exploration and Iterative Feedback
di: Yang, Yongjin, et al.
Pubblicazione: (2025)

Q-Guided Stein Variational Model Predictive Control via RL-informed Policy Prior
di: Cai, Shizhe, et al.
Pubblicazione: (2025)

Multi-agent Coordination via Flow Matching
di: Lee, Dongsu, et al.
Pubblicazione: (2025)

Generalized Animal Imitator: Agile Locomotion with Versatile Motion Prior
di: Yang, Ruihan, et al.
Pubblicazione: (2023)

Mobile-TeleVision: Predictive Motion Priors for Humanoid Whole-Body Control
di: Lu, Chenhao, et al.
Pubblicazione: (2024)

A KL-regularization Framework for Learning to Plan with Adaptive Priors
di: Serra-Gomez, Álvaro, et al.
Pubblicazione: (2025)

PUMA: Perception-driven Unified Foothold Prior for Mobility Augmented Quadruped Parkour
di: Wang, Liang, et al.
Pubblicazione: (2026)

Reinforcement Learning with Foundation Priors: Let the Embodied Agent Efficiently Learn on Its Own
di: Ye, Weirui, et al.
Pubblicazione: (2023)

Trust Region Q Adjoint Matching
di: Dong, Yonghoon, et al.
Pubblicazione: (2026)

Flow Matching Ergodic Coverage
di: Sun, Max Muchen, et al.
Pubblicazione: (2025)

Redefining Data Pairing for Motion Retargeting Leveraging a Human Body Prior
di: Figuera, Xiyana, et al.
Pubblicazione: (2024)

UniConFlow: A Unified Constrained Flow-Matching Framework for Certified Motion Planning
di: Yang, Zewen, et al.
Pubblicazione: (2025)

ImitDiff: Transferring Foundation-Model Priors for Distraction Robust Visuomotor Policy
di: Dong, Yuhang, et al.
Pubblicazione: (2025)

Leveraging Object Priors for Point Tracking
di: Boote, Bikram, et al.
Pubblicazione: (2024)

Exploiting Hybrid Policy in Reinforcement Learning for Interpretable Temporal Logic Manipulation
di: Zhang, Hao, et al.
Pubblicazione: (2024)

FlowQ: Energy-Guided Flow Policies for Offline Reinforcement Learning
di: Alles, Marvin, et al.
Pubblicazione: (2025)

Flowette: Flow Matching with Graphette Priors for Graph Generation
di: Wijesinghe, Asiri, et al.
Pubblicazione: (2026)

Robot Policy Learning with Temporal Optimal Transport Reward
di: Fu, Yuwei, et al.
Pubblicazione: (2024)

ESP: Exploiting Symmetry Prior for Multi-Agent Reinforcement Learning
di: Yu, Xin, et al.
Pubblicazione: (2023)

P3-PO: Prescriptive Point Priors for Visuo-Spatial Generalization of Robot Policies
di: Levy, Mara, et al.
Pubblicazione: (2024)

AsyncVLA: Asynchronous Flow Matching for Vision-Language-Action Models
di: Jiang, Yuhua, et al.
Pubblicazione: (2025)

Real-Time Execution of Action Chunking Flow Policies
di: Black, Kevin, et al.
Pubblicazione: (2025)

Drifting Field Policy: A One-Step Generative Policy via Wasserstein Gradient Flow
di: Koo, Juil, et al.
Pubblicazione: (2026)

Q-Flow: Stable and Expressive Reinforcement Learning with Flow-Based Policy
di: Doo, JaeHyeok, et al.
Pubblicazione: (2026)

Encoding Temporal Statistical-space Priors via Augmented Representation
di: Choi, Insu, et al.
Pubblicazione: (2024)

LearningFlow: Automated Policy Learning Workflow for Urban Driving with Large Language Models
di: Peng, Zengqi, et al.
Pubblicazione: (2025)

Subtask-Aware Visual Reward Learning from Segmented Demonstrations
di: Kim, Changyeon, et al.
Pubblicazione: (2025)

TopoSD: Topology-Enhanced Lane Segment Perception with SDMap Prior
di: Yang, Sen, et al.
Pubblicazione: (2024)

Absolute Policy Optimization
di: Zhao, Weiye, et al.
Pubblicazione: (2023)

Q-learning with Adjoint Matching
di: Li, Qiyang, et al.
Pubblicazione: (2026)

Conditional Flow Matching for Continuous Anomaly Detection in Autonomous Driving on a Manifold-Aware Spectral Space
di: Guillen-Perez, Antonio
Pubblicazione: (2026)

Deep Learning Warm Starts for Trajectory Optimization on the International Space Station
di: Banerjee, Somrita, et al.
Pubblicazione: (2025)

Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting
di: Kollovieh, Marcel, et al.
Pubblicazione: (2024)

Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss
di: Zheng, Ruijie, et al.
Pubblicazione: (2024)

IMLE Policy: Fast and Sample Efficient Visuomotor Policy Learning via Implicit Maximum Likelihood Estimation
di: Rana, Krishan, et al.
Pubblicazione: (2025)

Temporal Distance-aware Transition Augmentation for Offline Model-based Reinforcement Learning
di: Lee, Dongsu, et al.
Pubblicazione: (2025)

Robust Policy Learning via Offline Skill Diffusion
di: Kim, Woo Kyung, et al.
Pubblicazione: (2024)