Imagen de Portada

EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Dong, Perry, Hung, Kuo-Han, Gao, Tian, Sadigh, Dorsa, Finn, Chelsea
Formato:	Preprint
Publicado:	2026
Materias:	Robotics Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

EXPO: Stable Reinforcement Learning with Expressive Policies
por: Dong, Perry, et al.
Publicado: (2025)

What Matters for Batch Online Reinforcement Learning in Robotics?
por: Dong, Perry, et al.
Publicado: (2025)

Latent Diffusion Planning for Imitation Learning
por: Xie, Amber, et al.
Publicado: (2025)

Efficient Data Collection for Robotic Manipulation via Compositional Generalization
por: Gao, Jensen, et al.
Publicado: (2024)

Invariance Co-training for Robot Visual Generalization
por: Yang, Jonathan, et al.
Publicado: (2025)

TQL: Scaling Q-Functions with Transformers by Preventing Attention Collapse
por: Dong, Perry, et al.
Publicado: (2026)

FASTER: Value-Guided Sampling for Fast RL
por: Dong, Perry, et al.
Publicado: (2026)

Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning
por: Wagenmaker, Andrew, et al.
Publicado: (2025)

Efficiently Generating Expressive Quadruped Behaviors via Language-Guided Preference Learning
por: Clark, Jaden, et al.
Publicado: (2025)

Action-Free Reasoning for Policy Generalization
por: Clark, Jaden, et al.
Publicado: (2025)

Data Analogies Enable Efficient Cross-Embodiment Transfer
por: Yang, Jonathan, et al.
Publicado: (2026)

Value Flows
por: Dong, Perry, et al.
Publicado: (2025)

Emergence of Human to Robot Transfer in Vision-Language-Action Models
por: Kareer, Simar, et al.
Publicado: (2025)

Batch Active Learning of Reward Functions from Human Preferences
por: Bıyık, Erdem, et al.
Publicado: (2024)

Data Retrieval with Importance Weights for Few-Shot Imitation Learning
por: Xie, Amber, et al.
Publicado: (2025)

Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
por: Kim, Moo Jin, et al.
Publicado: (2025)

Self-Guided Action Diffusion
por: Malhotra, Rhea, et al.
Publicado: (2025)

RT-H: Action Hierarchies Using Language
por: Belkhale, Suneel, et al.
Publicado: (2024)

SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning
por: Luo, Jianlan, et al.
Publicado: (2024)

Sample-Efficient Robot Skill Learning for Construction Tasks: Benchmarking Hierarchical Reinforcement Learning and Vision-Language-Action VLA Model
por: Hu, Zhaofeng, et al.
Publicado: (2025)

Physically Grounded Vision-Language Models for Robotic Manipulation
por: Gao, Jensen, et al.
Publicado: (2023)

SteerVLA: Steering Vision-Language-Action Models in Long-Tail Driving Scenarios
por: Gao, Tian, et al.
Publicado: (2026)

Scaling Verification Can Be More Effective than Scaling Policy Learning for Vision-Language-Action Alignment
por: Kwok, Jacky, et al.
Publicado: (2026)

Polychromic Objectives for Reinforcement Learning
por: Hamid, Jubayer Ibn, et al.
Publicado: (2025)

Robust Finetuning of Vision-Language-Action Robot Policies via Parameter Merging
por: Yadav, Yajat, et al.
Publicado: (2025)

MoRE: Unlocking Scalability in Reinforcement Learning for Quadruped Vision-Language-Action Models
por: Zhao, Han, et al.
Publicado: (2025)

Commonsense Reasoning for Legged Robot Adaptation with Vision-Language Models
por: Chen, Annie S., et al.
Publicado: (2024)

RLRC: Reinforcement Learning-based Recovery for Compressed Vision-Language-Action Models
por: Chen, Yuxuan, et al.
Publicado: (2025)

Motion Tracks: A Unified Representation for Human-Robot Transfer in Few-Shot Imitation Learning
por: Ren, Juntao, et al.
Publicado: (2025)

Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling
por: Liu, Yuejiang, et al.
Publicado: (2024)

A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning
por: Zhai, Shaopeng, et al.
Publicado: (2025)

Altruistic Maneuver Planning for Cooperative Autonomous Vehicles Using Multi-agent Advantage Actor-Critic
por: Toghi, Behrad, et al.
Publicado: (2021)

FLAIR: Feeding via Long-horizon AcquIsition of Realistic dishes
por: Jenamani, Rajat Kumar, et al.
Publicado: (2024)

Robot-Powered Data Flywheels: Deploying Robots in the Wild for Continual Data Collection and Foundation Model Adaptation
por: Grannen, Jennifer, et al.
Publicado: (2025)

VLA-AN: An Efficient and Onboard Vision-Language-Action Framework for Aerial Navigation in Complex Environments
por: Wu, Yuze, et al.
Publicado: (2025)

Toward Grounded Commonsense Reasoning
por: Kwon, Minae, et al.
Publicado: (2023)

KineVLA: Towards Kinematics-Aware Vision-Language-Action Models with Bi-Level Action Decomposition
por: Han, Gaoge, et al.
Publicado: (2026)

A Taxonomy for Evaluating Generalist Robot Manipulation Policies
por: Gao, Jensen, et al.
Publicado: (2025)

Affordance-Guided Reinforcement Learning via Visual Prompting
por: Lee, Olivia Y., et al.
Publicado: (2024)

Learning Skills from Action-Free Videos
por: Fang, Hung-Chieh, et al.
Publicado: (2025)