Image de couverture de livre

ReFORM: Reflected Flows for On-support Offline RL via Noise Manipulation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Songyuan, So, Oswin, Ahmad, H. M. Sabbir, Yu, Eric Yang, Cleaveland, Matthew, Black, Mitchell, Fan, Chuchu
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence Robotics
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Solving Parameter-Robust Avoid Problems with Unknown Feasibility using Reinforcement Learning
par: So, Oswin, et autres
Publié: (2026)

Discrete GCBF Proximal Policy Optimization for Multi-agent Safe Optimal Control
par: Zhang, Songyuan, et autres
Publié: (2025)

Solving Multi-Agent Safe Optimal Control with Distributed Epigraph Form MARL
par: Zhang, Songyuan, et autres
Publié: (2025)

GCBF+: A Neural Graph Control Barrier Function Framework for Distributed Safe Multi-Agent Control
par: Zhang, Songyuan, et autres
Publié: (2024)

Solving Minimum-Cost Reach Avoid using Reinforcement Learning
par: So, Oswin, et autres
Publié: (2024)

Safety on the Fly: Constructing Robust Safety Filters via Policy Control Barrier Functions at Runtime
par: Knoedler, Luzia, et autres
Publié: (2024)

Safe Beyond the Horizon: Efficient Sampling-based MPC with Neural Control Barrier Functions
par: Yin, Ji, et autres
Publié: (2025)

Bellman Value Decomposition for Task Logic in Safe Optimal Control
par: Sharpless, William, et autres
Publié: (2026)

Value Functions for Temporal Logic: Optimal Policies and Safety Filters
par: So, Oswin, et autres
Publié: (2026)

Towards Efficient and Expressive Offline RL via Flow-Anchored Noise-conditioned Q-Learning
par: Lee, Sungyoung, et autres
Publié: (2026)

Hierarchical Multi-Agent Reinforcement Learning with Control Barrier Functions for Safety-Critical Autonomous Systems
par: Ahmad, H. M. Sabbir, et autres
Publié: (2025)

Foundation Models to the Rescue: Deadlock Resolution in Connected Multi-Robot Systems
par: Garg, Kunal, et autres
Publié: (2024)

AuDeRe: Automated Strategy Decision and Realization in Robot Planning and Control via LLMs
par: Meng, Yue, et autres
Publié: (2025)

ReFORM: Review-aggregated Profile Generation via LLM with Multi-Factor Attention for Restaurant Recommendation
par: Park, Moonsoo, et autres
Publié: (2026)

TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matching
par: Meng, Yue, et autres
Publié: (2025)

Maximizing Reach-Avoid Probabilities for Linear Stochastic Systems via Control Architectures
par: Schmid, Niklas, et autres
Publié: (2026)

Rigid Body Path Planning using Mixed-Integer Linear Programming
par: Yu, Mingxin, et autres
Publié: (2024)

Balancing Signal and Variance: Adaptive Offline RL Post-Training for VLA Flow Models
par: Zhang, Hongyin, et autres
Publié: (2025)

CycleRL: Sim-to-Real Deep Reinforcement Learning for Robust Autonomous Bicycle Control
par: Liu, Gelu, et autres
Publié: (2026)

RADIUM: Predicting and Repairing End-to-End Robot Failures using Gradient-Accelerated Sampling
par: Dawson, Charles, et autres
Publié: (2024)

Failure-Aware RL: Reliable Offline-to-Online Reinforcement Learning with Self-Recovery for Real-World Manipulation
par: Li, Huanyu, et autres
Publié: (2026)

CATCH-FORM-3D: Compliance-Aware Tactile Control and Hybrid Deformation Regulation for 3D Viscoelastic Object Manipulation
par: Ma, Hongjun, et autres
Publié: (2025)

CATCH-FORM-ACTer: Compliance-Aware Tactile Control and Hybrid Deformation Regulation-Based Action Transformer for Viscoelastic Object Manipulation
par: Ma, Hongjun, et autres
Publié: (2025)

Optimization of Multi-Agent Flying Sidekick Traveling Salesman Problem over Road Networks
par: Yang, Ruixiao, et autres
Publié: (2024)

Robotic Manipulation Datasets for Offline Compositional Reinforcement Learning
par: Hussing, Marcel, et autres
Publié: (2023)

Real-Time Optical Communication Using Event-Based Vision with Moving Transmitters
par: Dhillon, Harmeet, et autres
Publié: (2026)

120 Minutes and a Laptop: Minimalist Image-goal Navigation via Unsupervised Exploration and Offline RL
par: Liu, Xiaoming, et autres
Publié: (2026)

Efficient Motion Planning for Manipulators with Control Barrier Function-Induced Neural Controller
par: Yu, Mingxin, et autres
Publié: (2024)

FlowPolicy: Enabling Fast and Robust 3D Flow-based Policy via Consistency Flow Matching for Robot Manipulation
par: Zhang, Qinglun, et autres
Publié: (2024)

Learning to Stabilize High-dimensional Unknown Systems Using Lyapunov-guided Exploration
par: Zhang, Songyuan, et autres
Publié: (2023)

Offline Policy Evaluation for Manipulation Policies via Discounted Liveness Formulation
par: Wang, Hao, et autres
Publié: (2026)

Constrained Sampling to Guide Universal Manipulation RL
par: Toussaint, Marc, et autres
Publié: (2026)

VLA-OPD: Bridging Offline SFT and Online RL for Vision-Language-Action Models via On-Policy Distillation
par: Zhong, Zhide, et autres
Publié: (2026)

OffRIPP: Offline RL-based Informative Path Planning
par: Gadipudi, Srikar Babu, et autres
Publié: (2024)

SutureFormer: Learning Surgical Trajectories via Goal-conditioned Offline RL in Pixel Space
par: Liu, Huanrong, et autres
Publié: (2026)

Affordance-based Robot Manipulation with Flow Matching
par: Zhang, Fan, et autres
Publié: (2024)

Failure Prediction from Limited Hardware Demonstrations
par: Parashar, Anjali, et autres
Publié: (2024)

Subspace-wise Hybrid RL for Articulated Object Manipulation
par: Kim, Yujin, et autres
Publié: (2024)

Language-Conditioned Offline RL for Multi-Robot Navigation
par: Morad, Steven, et autres
Publié: (2024)

Code-as-Symbolic-Planner: Foundation Model-Based Robot Planning via Symbolic Code Generation
par: Chen, Yongchao, et autres
Publié: (2025)