Cover Image

H2O+: An Improved Framework for Hybrid Offline-and-Online RL with Dynamics Gaps

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Niu, Haoyi, Ji, Tianying, Liu, Bingqi, Zhao, Haocheng, Zhu, Xiangyu, Zheng, Jianying, Huang, Pengfei, Zhou, Guyue, Hu, Jianming, Zhan, Xianyuan
Format:	Preprint
Published:	2023
Subjects:	Machine Learning Artificial Intelligence Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Comprehensive Survey of Cross-Domain Policy Transfer for Embodied Agents
by: Niu, Haoyi, et al.
Published: (2024)

When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning
by: Niu, Haoyi, et al.
Published: (2022)

xTED: Cross-Domain Adaptation via Diffusion-Based Trajectory Editing
by: Niu, Haoyi, et al.
Published: (2024)

Are Expressive Models Truly Necessary for Offline RL?
by: Wang, Guan, et al.
Published: (2024)

Efficient Robotic Policy Learning via Latent Space Backward Planning
by: Liu, Dongxiu, et al.
Published: (2025)

PhysiAgent: An Embodied Agent Framework in Physical World
by: Wang, Zhihao, et al.
Published: (2025)

Skill Expansion and Composition in Parameter Space
by: Liu, Tenglong, et al.
Published: (2025)

UniLegs: Universal Multi-Legged Robot Control through Morphology-Agnostic Policy Distillation
by: Xi, Weijie, et al.
Published: (2025)

Continual Driving Policy Optimization with Closed-Loop Individualized Curricula
by: Niu, Haoyi, et al.
Published: (2023)

Deadlock-Free Hybrid RL-MAPF Framework for Zero-Shot Multi-Robot Navigation
by: Wang, Haoyi, et al.
Published: (2025)

OMPO: A Unified Framework for RL under Policy and Dynamics Shifts
by: Luo, Yu, et al.
Published: (2024)

Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL
by: Luo, Yu, et al.
Published: (2024)

Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model
by: Zheng, Yinan, et al.
Published: (2024)

OmniVLA-RL: A Vision-Language-Action Model with Spatial Understanding and Online RL
by: Jie, Haoxiang, et al.
Published: (2026)

ENOTO: Improving Offline-to-Online Reinforcement Learning with Q-Ensembles
by: Zhao, Kai, et al.
Published: (2023)

Dynamically Expanding Capacity of Autonomous Driving with Near-Miss Focused Training Framework
by: Yang, Ziyuan, et al.
Published: (2024)

VLA-OPD: Bridging Offline SFT and Online RL for Vision-Language-Action Models via On-Policy Distillation
by: Zhong, Zhide, et al.
Published: (2026)

Efficient Online RL Fine Tuning with Offline Pre-trained Policy Only
by: Xiao, Wei, et al.
Published: (2025)

Failure-Aware RL: Reliable Offline-to-Online Reinforcement Learning with Self-Recovery for Real-World Manipulation
by: Li, Huanyu, et al.
Published: (2026)

Towards Robust Zero-Shot Reinforcement Learning
by: Zheng, Kexin, et al.
Published: (2025)

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

Crowdsense Roadside Parking Spaces with Dynamic Gap Reduction Algorithm
by: Zheng, Wenjun, et al.
Published: (2024)

Hybrid Offline-Online Reinforcement Learning for Sensorless, High-Precision Force Regulation in Surgical Robotic Grasping
by: Fazzari, Edoardo, et al.
Published: (2026)

DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning
by: Li, Jianxiong, et al.
Published: (2024)

GAP-RL: Grasps As Points for RL Towards Dynamic Object Grasping
by: Xie, Pengwei, et al.
Published: (2024)

SafeMove-RL: A Certifiable Reinforcement Learning Framework for Dynamic Motion Constraints in Trajectory Planning
by: Liu, Tengfei, et al.
Published: (2025)

Bidirectional-Reachable Hierarchical Reinforcement Learning with Mutually Responsive Policies
by: Luo, Yu, et al.
Published: (2024)

OffRIPP: Offline RL-based Informative Path Planning
by: Gadipudi, Srikar Babu, et al.
Published: (2024)

GripMap: An Efficient, Spatially Resolved Constraint Framework for Offline and Online Trajectory Planning in Autonomous Racing
by: Werner, Frederik, et al.
Published: (2025)

Language-Conditioned Offline RL for Multi-Robot Navigation
by: Morad, Steven, et al.
Published: (2024)

Block-Map-Based Localization in Large-Scale Environment
by: Feng, Yixiao, et al.
Published: (2024)

HIQL: Offline Goal-Conditioned RL with Latent States as Actions
by: Park, Seohong, et al.
Published: (2023)

RL Token: Bootstrapping Online RL with Vision-Language-Action Models
by: Xu, Charles, et al.
Published: (2026)

RM-RL: Role-Model Reinforcement Learning for Precise Robot Manipulation
by: Chen, Xiangyu, et al.
Published: (2025)

HybridMimic: Hybrid RL-Centroidal Control for Humanoid Motion Mimicking
by: Tay, Ludwig Chee-Ying, et al.
Published: (2026)

Flow Matching-Based Autonomous Driving Planning with Advanced Interactive Behavior Modeling
by: Tan, Tianyi, et al.
Published: (2025)

120 Minutes and a Laptop: Minimalist Image-goal Navigation via Unsupervised Exploration and Offline RL
by: Liu, Xiaoming, et al.
Published: (2026)

Dynamic Gap: Safe Gap-based Navigation in Dynamic Environments
by: Asselmeier, Max, et al.
Published: (2022)

Balancing Signal and Variance: Adaptive Offline RL Post-Training for VLA Flow Models
by: Zhang, Hongyin, et al.
Published: (2025)

Subspace-wise Hybrid RL for Articulated Object Manipulation
by: Kim, Yujin, et al.
Published: (2024)