Cover Image

Focus On What Matters: Separated Models For Visual-Based RL Generalization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Di, Lv, Bowen, Zhang, Hai, Yang, Feifan, Zhao, Junqiao, Yu, Hang, Huang, Chang, Zhou, Hongtu, Ye, Chen, Jiang, Changjun
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ACSAC: Adaptive Chunk Size Actor-Critic with Causal Transformer Q-Network
by: Chen, Qian, et al.
Published: (2026)

Learning Geometrically-Grounded 3D Visual Representations for View-Generalizable Robotic Manipulation
by: Zhang, Di, et al.
Published: (2026)

What to Ignore, What to React: Visually Robust RL Fine-Tuning of VLA Models
by: Peng, Yuanfang, et al.
Published: (2026)

KineDex: Learning Tactile-Informed Visuomotor Policies via Kinesthetic Teaching for Dexterous Manipulation
by: Zhang, Di, et al.
Published: (2025)

Point What You Mean: Visually Grounded Instruction Policy
by: Yu, Hang, et al.
Published: (2025)

POWQMIX: Weighted Value Factorization with Potentially Optimal Joint Actions Recognition for Cooperative Multi-Agent Reinforcement Learning
by: Huang, Chang, et al.
Published: (2024)

FocusVLA: Focused Visual Utilization for Vision-Language-Action Models
by: Zhang, Yichi, et al.
Published: (2026)

What Matters in RL-Based Methods for Object-Goal Navigation? An Empirical Study and A Unified Framework
by: Wang, Hongze, et al.
Published: (2025)

N$^{3}$-Mapping: Normal Guided Neural Non-Projective Signed Distance Fields for Large-scale 3D Mapping
by: Song, Shuangfu, et al.
Published: (2024)

LIMOT: A Tightly-Coupled System for LiDAR-Inertial Odometry and Multi-Object Tracking
by: Zhu, Zhongyang, et al.
Published: (2023)

OVPD: A Virtual-Physical Fusion Testing Dataset of OnSite Auton-omous Driving Challenge
by: Zhang, Yuhang, et al.
Published: (2026)

DL-SLOT: Dynamic LiDAR SLAM and object tracking based on collaborative graph optimization
by: Tian, Xuebo, et al.
Published: (2022)

Convex Hull-based Algebraic Constraint for Visual Quadric SLAM
by: Yu, Xiaolong, et al.
Published: (2025)

LOG-LIO2: A LiDAR-Inertial Odometry with Efficient Uncertainty Analysis
by: Huang, Kai, et al.
Published: (2024)

GenFlowRL: Shaping Rewards with Generative Object-Centric Flow in Visual Reinforcement Learning
by: Yu, Kelin, et al.
Published: (2025)

A Visual Reinforcement Learning-Based Separate Primitive Policy for Peg-in-Hole Tasks
by: Xu, Zichun, et al.
Published: (2025)

PO-GVINS: Tightly Coupled GNSS-Visual-Inertial Integration with Pose-Only Representation
by: Xu, Zhuo, et al.
Published: (2025)

Empowering Embodied Visual Tracking with Visual Foundation Models and Offline RL
by: Zhong, Fangwei, et al.
Published: (2024)

VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning
by: Lu, Guanxing, et al.
Published: (2025)

Discover, Learn, and Reinforce: Scaling Vision-Language-Action Pretraining with Diverse RL-Generated Trajectories
by: Yang, Rushuai, et al.
Published: (2025)

ResWM: Residual-Action World Model for Visual RL
by: Zhang, Jseen, et al.
Published: (2026)

Language-Conditioned Open-Vocabulary Mobile Manipulation with Pretrained Models
by: Tan, Shen, et al.
Published: (2025)

General Methods for Evaluating Collision Probability of Different Types of Theta-phi Positioners
by: Chen, Baolong, et al.
Published: (2024)

Environment-Adaptive Solid-State LiDAR-Inertial Odometry
by: Zhang, Zhi, et al.
Published: (2026)

EasyCalib: Simple and Low-Cost In-Situ Calibration for Force Reconstruction with Vision-Based Tactile Sensors
by: Li, Mingxuan, et al.
Published: (2024)

Mask World Model: Predicting What Matters for Robust Robot Policy Learning
by: Lou, Yunfan, et al.
Published: (2026)

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)

VolumeDP: Modeling Volumetric Representation for Manipulation Policy Learning
by: Zhou, Tianxing, et al.
Published: (2026)

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

GenAI-based Multi-Agent Reinforcement Learning towards Distributed Agent Intelligence: A Generative-RL Agent Perspective
by: Wang, Hang, et al.
Published: (2025)

Physics-informed Neural Network Predictive Control for Quadruped Locomotion
by: Li, Haolin, et al.
Published: (2025)

RL-Based Coverage Path Planning for Deformable Objects on 3D Surfaces
by: Zhang, Yuhang, et al.
Published: (2026)

Object-Focus Actor for Data-efficient Robot Generalization Dexterous Manipulation
by: Li, Yihang, et al.
Published: (2025)

RL-Driven Data Generation for Robust Vision-Based Dexterous Grasping
by: Kanehira, Atsushi, et al.
Published: (2025)

Vision-Based Deep Reinforcement Learning of UAV Autonomous Navigation Using Privileged Information
by: Wang, Junqiao, et al.
Published: (2024)

VR-Robo: A Real-to-Sim-to-Real Framework for Visual Robot Navigation and Locomotion
by: Zhu, Shaoting, et al.
Published: (2025)

RL-augmented Adaptive Model Predictive Control for Bipedal Locomotion over Challenging Terrain
by: Kamohara, Junnosuke, et al.
Published: (2025)

Incipient Slip-Based Rotation Measurement via Visuotactile Sensing During In-Hand Object Pivoting
by: Li, Mingxuan, et al.
Published: (2023)

ActionCodec: What Makes for Good Action Tokenizers
by: Dong, Zibin, et al.
Published: (2026)

What Matters for Active Texture Recognition With Vision-Based Tactile Sensors
by: Böhm, Alina, et al.
Published: (2024)