Cover Image

Beyond Imitation: Reinforcement Learning-Based Sim-Real Co-Training for VLA Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shi, Liangzhi, Chen, Shuaihang, Gao, Feng, Chen, Yinuo, Chen, Kang, Zhang, Tonghe, Zang, Hongzhi, Zhang, Weinan, Yu, Chao, Wang, Yu
Format:	Preprint
Published:	2026
Subjects:	Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

RLinf-VLA: A Unified and Efficient Framework for Reinforcement Learning of Vision-Language-Action Models
by: Zang, Hongzhi, et al.
Published: (2025)

Beyond Human Demonstrations: Diffusion-Based Reinforcement Learning to Generate Data for VLA Training
by: Yang, Rushuai, et al.
Published: (2025)

RoboScape-R: Unified Reward-Observation World Models for Generalizable Robotics Training via RL
by: Tang, Yinzhou, et al.
Published: (2025)

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

What Matters in Learning A Zero-Shot Sim-to-Real RL Policy for Quadrotor Control? A Comprehensive Study
by: Chen, Jiayu, et al.
Published: (2024)

Re$^3$Sim: Generating High-Fidelity Simulation Data via 3D-Photorealistic Real-to-Sim for Robotic Manipulation
by: Han, Xiaoshen, et al.
Published: (2025)

Multi-UAV Formation Control with Static and Dynamic Obstacle Avoidance via Reinforcement Learning
by: Xie, Yuqing, et al.
Published: (2024)

Generalizable Domain Adaptation for Sim-and-Real Policy Co-Training
by: Cheng, Shuo, et al.
Published: (2025)

JuggleRL: Mastering Ball Juggling with a Quadrotor via Deep Reinforcement Learning
by: Ji, Shilong, et al.
Published: (2025)

SimVLA: A Simple VLA Baseline for Robotic Manipulation
by: Luo, Yuankai, et al.
Published: (2026)

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
by: Li, Haozhan, et al.
Published: (2025)

StreamingVLA: Streaming Vision-Language-Action Model with Action Flow Matching and Adaptive Early Observation
by: Shi, Yiran, et al.
Published: (2026)

ScissorBot: Learning Generalizable Scissor Skill for Paper Cutting via Simulation, Imitation, and Sim2Real
by: Lyu, Jiangran, et al.
Published: (2024)

Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation
by: Maddukuri, Abhiram, et al.
Published: (2025)

SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential Modeling
by: Zhang, Yixian, et al.
Published: (2025)

ST4VLA: Spatially Guided Training for Vision-Language-Action Models
by: Ye, Jinhui, et al.
Published: (2026)

REAP: Reinforcement-Learning End-to-End Autonomous Parking with Gaussian Splatting Simulator for Real2Sim2Real Transfer
by: Li, Changze, et al.
Published: (2026)

Robotic Sim-to-Real Transfer for Long-Horizon Pick-and-Place Tasks in the Robotic Sim2Real Competition
by: Yang, Ming, et al.
Published: (2025)

Robotic Strawberry Harvesting with Robust Vision and Deep Reinforcement Learning based Sim-to-Real Control
by: Bashir, Al, et al.
Published: (2026)

A Mechanistic Analysis of Sim-and-Real Co-Training in Generative Robot Policies
by: Lei, Yu, et al.
Published: (2026)

GeCo-SRT: Geometry-aware Continual Adaptation for Robotic Cross-Task Sim-to-Real Transfer
by: Yu, Wenbo, et al.
Published: (2026)

World-Env: Leveraging World Model as a Virtual Environment for VLA Post-Training
by: Xiao, Junjin, et al.
Published: (2025)

RLinf-USER: A Unified and Extensible System for Real-World Online Policy Learning in Embodied AI
by: Zang, Hongzhi, et al.
Published: (2026)

LoopSR: Looping Sim-and-Real for Lifelong Policy Adaptation of Legged Robots
by: Wu, Peilin, et al.
Published: (2024)

A Recipe for Efficient Sim-to-Real Transfer in Manipulation with Online Imitation-Pretrained World Models
by: Wang, Yilin, et al.
Published: (2025)

Dual Action Policy for Robust Sim-to-Real Reinforcement Learning
by: Terence, Ng Wen Zheng, et al.
Published: (2024)

Betting for Sim-to-Real Performance Evaluation
by: Mahboob, Zaid, et al.
Published: (2026)

Real-to-Sim Grasp: Rethinking the Gap between Simulation and Real World in Grasp Detection
by: Cai, Jia-Feng, et al.
Published: (2024)

Beyond Imitation: Reinforcement Learning Fine-Tuning for Adaptive Diffusion Navigation Policies
by: Sheng, Junhe, et al.
Published: (2026)

HyperSim: A Holistic Sim-To-Real Framework For Robust Robotic Manipulation
by: Dong, Junyi, et al.
Published: (2026)

Bridging the Sim-to-Real Gap from the Information Bottleneck Perspective
by: He, Haoran, et al.
Published: (2023)

WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL
by: Jiang, Zhennan, et al.
Published: (2026)

AtomVLA: Scalable Post-Training for Robotic Manipulation via Predictive Latent World Models
by: Sun, Xiaoquan, et al.
Published: (2026)

MetaVLA: Unified Meta Co-training For Efficient Embodied Adaption
by: Li, Chen, et al.
Published: (2025)

Learning from Mistakes: Post-Training for Driving VLA with Takeover Data
by: Gao, Yinfeng, et al.
Published: (2026)

Sim-to-Real Gentle Manipulation of Deformable and Fragile Objects with Stress-Guided Reinforcement Learning
by: Ikemura, Kei, et al.
Published: (2025)

Impact of Static Friction on Sim2Real in Robotic Reinforcement Learning
by: Hu, Xiaoyi, et al.
Published: (2025)

BORA: Bridging Offline Reinforcement Learning and Online Residual Adaptation for Real-World Dexterous VLA Models
by: Chen, Zhongxi, et al.
Published: (2026)

BlockVLA: Accelerating Autoregressive VLA via Block Diffusion Finetuning
by: Wang, Ruiheng, et al.
Published: (2026)

Reinforcement Learning-Based Model Matching to Reduce the Sim-Real Gap in COBRA
by: Salagame, Adarsh, et al.
Published: (2024)