Integrating Offline Pre-Training with Online Fine-Tuning: A Reinforcement Learning Approach for Robot Social Navigation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Su, Run, Fu, Hao, Zhou, Shuai, Fu, Yingao
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Robotics Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Intrinsic-Motivation Multi-Robot Social Formation Navigation with Coordinated Exploration
di: Fu, Hao, et al.
Pubblicazione: (2025)

Adversarial Fine-tuning in Offline-to-Online Reinforcement Learning for Robust Robot Control
di: Ayabe, Shingo, et al.
Pubblicazione: (2025)

MOTO: Offline Pre-training to Online Fine-tuning for Model-based Robot Learning
di: Rafailov, Rafael, et al.
Pubblicazione: (2024)

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

Socially Integrated Navigation: A Social Acting Robot with Deep Reinforcement Learning
di: Flögel, Daniel, et al.
Pubblicazione: (2024)

Attention Graph for Multi-Robot Social Navigation with Deep Reinforcement Learning
di: Escudie, Erwan, et al.
Pubblicazione: (2024)

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

Cross-Embodiment Offline Reinforcement Learning for Heterogeneous Robot Datasets
di: Abe, Haruki, et al.
Pubblicazione: (2026)

IN-RIL: Interleaved Reinforcement and Imitation Learning for Policy Fine-Tuning
di: Gao, Dechen, et al.
Pubblicazione: (2025)

Online Context Learning for Socially Compliant Navigation
di: Okunevich, Iaroslav, et al.
Pubblicazione: (2024)

Research on Autonomous Robots Navigation based on Reinforcement Learning
di: Wang, Zixiang, et al.
Pubblicazione: (2024)

Robotic Manipulation Datasets for Offline Compositional Reinforcement Learning
di: Hussing, Marcel, et al.
Pubblicazione: (2023)

RankQ: Offline-to-Online Reinforcement Learning via Self-Supervised Action Ranking
di: Choi, Andrew, et al.
Pubblicazione: (2026)

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

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

Compositional Conservatism: A Transductive Approach in Offline Reinforcement Learning
di: Song, Yeda, et al.
Pubblicazione: (2024)

Robot Policy Transfer with Online Demonstrations: An Active Reinforcement Learning Approach
di: Hou, Muhan, et al.
Pubblicazione: (2025)

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

Target Search and Navigation in Heterogeneous Robot Systems with Deep Reinforcement Learning
di: Chen, Yun, et al.
Pubblicazione: (2023)

SINRL: Socially Integrated Navigation with Reinforcement Learning using Spiking Neural Networks
di: Tretter, Florian, et al.
Pubblicazione: (2025)

What Matters for Simulation to Online Reinforcement Learning on Real Robots
di: As, Yarden, et al.
Pubblicazione: (2026)

DiSA-IQL: Offline Reinforcement Learning for Robust Soft Robot Control under Distribution Shifts
di: He, Linjin, et al.
Pubblicazione: (2025)

Video-Enhanced Offline Reinforcement Learning: A Model-Based Approach
di: Pan, Minting, et al.
Pubblicazione: (2025)

RoboRAN: A Unified Robotics Framework for Reinforcement Learning-Based Autonomous Navigation
di: El-Hariry, Matteo, et al.
Pubblicazione: (2025)

Hierarchical Reinforcement Learning in Multi-Goal Spatial Navigation with Autonomous Mobile Robots
di: Johnson, Brendon, et al.
Pubblicazione: (2025)

A Central Motor System Inspired Pre-training Reinforcement Learning for Robotic Control
di: Zhang, Pei, et al.
Pubblicazione: (2023)

Incremental Residual Reinforcement Learning Toward Real-World Learning for Social Navigation
di: Nagahisa, Haruto, et al.
Pubblicazione: (2026)

Boundary-to-Region Supervision for Offline Safe Reinforcement Learning
di: Su, Huikang, et al.
Pubblicazione: (2025)

NeuPAN: Direct Point Robot Navigation with End-to-End Model-based Learning
di: Han, Ruihua, et al.
Pubblicazione: (2024)

Few-Shot Inference of Human Perceptions of Robot Performance in Social Navigation Scenarios
di: Zhang, Qiping, et al.
Pubblicazione: (2025)

Lifelike Agility and Play in Quadrupedal Robots using Reinforcement Learning and Generative Pre-trained Models
di: Han, Lei, et al.
Pubblicazione: (2023)

Safe Navigation for Robotic Digestive Endoscopy via Human Intervention-based Reinforcement Learning
di: Tan, Min, et al.
Pubblicazione: (2024)

COLSON: Controllable Learning-Based Social Navigation via Diffusion-Based Reinforcement Learning
di: Matsumoto, Kohei, et al.
Pubblicazione: (2025)

Transformable Gaussian Reward Function for Socially-Aware Navigation with Deep Reinforcement Learning
di: Kim, Jinyeob, et al.
Pubblicazione: (2024)

Reward Training Wheels: Adaptive Auxiliary Rewards for Robotics Reinforcement Learning
di: Wang, Linji, et al.
Pubblicazione: (2025)

World-Gymnast: Training Robots with Reinforcement Learning in a World Model
di: Sharma, Ansh Kumar, et al.
Pubblicazione: (2026)

ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy
di: Chen, Yuhui, et al.
Pubblicazione: (2025)

Integrating End-to-End and Modular Driving Approaches for Online Corner Case Detection in Autonomous Driving
di: Kaljavesi, Gemb, et al.
Pubblicazione: (2024)

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

A Clean Slate for Offline Reinforcement Learning
di: Jackson, Matthew Thomas, et al.
Pubblicazione: (2025)