Imagen de Portada

Conservative Offline Robot Policy Learning via Posterior-Transition Reweighting

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Wanpeng, Luo, Hao, Zheng, Sipeng, Feng, Yicheng, Xu, Haiweng, Xi, Ziheng, Xu, Chaoyi, Yuan, Haoqi, Lu, Zongqing
Formato:	Preprint
Publicado:	2026
Materias:	Robotics
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Unmasking the Illusion of Embodied Reasoning in Vision-Language-Action Models
por: Xu, Haiweng, et al.
Publicado: (2026)

Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization
por: Luo, Hao, et al.
Publicado: (2026)

Joint-Aligned Latent Action: Towards Scalable VLA Pretraining in the Wild
por: Luo, Hao, et al.
Publicado: (2026)

Being-H0.7: A Latent World-Action Model from Egocentric Videos
por: Luo, Hao, et al.
Publicado: (2026)

Rethinking Visual-Language-Action Model Scaling: Alignment, Mixture, and Regularization
por: Wang, Ye, et al.
Publicado: (2026)

Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videos
por: Feng, Yicheng, et al.
Publicado: (2025)

DiG-Flow: Discrepancy-Guided Flow Matching for Robust VLA Models
por: Zhang, Wanpeng, et al.
Publicado: (2025)

Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos
por: Luo, Hao, et al.
Publicado: (2025)

UniTacHand: Unified Spatio-Tactile Representation for Human to Robotic Hand Skill Transfer
por: Zhang, Chi, et al.
Publicado: (2025)

Universal Dexterous Functional Grasping via Demonstration-Editing Reinforcement Learning
por: Mao, Chuan, et al.
Publicado: (2025)

DemoGrasp: Universal Dexterous Grasping from a Single Demonstration
por: Yuan, Haoqi, et al.
Publicado: (2025)

DemoHLM: From One Demonstration to Generalizable Humanoid Loco-Manipulation
por: Fu, Yuhui, et al.
Publicado: (2025)

X-DiffVLA: X-Embodied Diffusion Action Heads for Vision-Language-Action Models
por: Li, Boyu, et al.
Publicado: (2026)

Being-0: A Humanoid Robotic Agent with Vision-Language Models and Modular Skills
por: Yuan, Haoqi, et al.
Publicado: (2025)

Unified Multimodal Understanding via Byte-Pair Visual Encoding
por: Zhang, Wanpeng, et al.
Publicado: (2025)

Efficient Residual Learning with Mixture-of-Experts for Universal Dexterous Grasping
por: Huang, Ziye, et al.
Publicado: (2024)

Learning Diverse Bimanual Dexterous Manipulation Skills from Human Demonstrations
por: Zhou, Bohan, et al.
Publicado: (2024)

Cross-Embodiment Dexterous Grasping with Reinforcement Learning
por: Yuan, Haoqi, et al.
Publicado: (2024)

VideoOrion: Tokenizing Object Dynamics in Videos
por: Feng, Yicheng, et al.
Publicado: (2024)

From Pixels to Tokens: Byte-Pair Encoding on Quantized Visual Modalities
por: Zhang, Wanpeng, et al.
Publicado: (2024)

Towards Proprioception-Aware Embodied Planning for Dual-Arm Humanoid Robots
por: Li, Boyu, et al.
Publicado: (2025)

RL from Physical Feedback: Aligning Large Motion Models with Humanoid Control
por: Yue, Junpeng, et al.
Publicado: (2025)

Guided Policy Optimization under Partial Observability
por: Li, Yueheng, et al.
Publicado: (2025)

SPAFormer: Sequential 3D Part Assembly with Transformers
por: Xu, Boshen, et al.
Publicado: (2024)

COSBO: Conservative Offline Simulation-Based Policy Optimization
por: Kargar, Eshagh, et al.
Publicado: (2024)

Offline Policy Evaluation for Manipulation Policies via Discounted Liveness Formulation
por: Wang, Hao, et al.
Publicado: (2026)

UniCode: Learning a Unified Codebook for Multimodal Large Language Models
por: Zheng, Sipeng, et al.
Publicado: (2024)

AdaRefiner: Refining Decisions of Language Models with Adaptive Feedback
por: Zhang, Wanpeng, et al.
Publicado: (2023)

DualTHOR: A Dual-Arm Humanoid Simulation Platform for Contingency-Aware Planning
por: Li, Boyu, et al.
Publicado: (2025)

RLDG: Robotic Generalist Policy Distillation via Reinforcement Learning
por: Xu, Charles, et al.
Publicado: (2024)

UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping
por: Wang, Wenbo, et al.
Publicado: (2024)

ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learning
por: Wu, Kun, et al.
Publicado: (2024)

Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning
por: Liu, Tenglong, et al.
Publicado: (2024)

From Experts to a Generalist: Toward General Whole-Body Control for Humanoid Robots
por: Wang, Yuxuan, et al.
Publicado: (2025)

Policy Contrastive Decoding for Robotic Foundation Models
por: Wu, Shihan, et al.
Publicado: (2025)

Beyond Static Datasets: Robust Offline Policy Optimization via Vetted Synthetic Transitions
por: Agand, Pedram, et al.
Publicado: (2026)

Adaptive Visual Perception for Robotic Construction Process: A Multi-Robot Coordination Framework
por: Xu, Jia, et al.
Publicado: (2024)

Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization
por: Lei, Kun, et al.
Publicado: (2023)

AdaWorldPolicy: World-Model-Driven Diffusion Policy with Online Adaptive Learning for Robotic Manipulation
por: Yuan, Ge, et al.
Publicado: (2026)

Reference-Steering via Data-Driven Predictive Control for Hyper-Accurate Robotic Flying-Hopping Locomotion
por: Zeng, Yicheng, et al.
Publicado: (2024)