Buchumschlag

RFTF: Reinforcement Fine-tuning for Embodied Agents with Temporal Feedback

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Shu, Junyang, Lin, Zhiwei, Wang, Yongtao
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Robotics
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

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

Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving
von: Lian, Zhexi, et al.
Veröffentlicht: (2026)

Beyond Description: Cognitively Benchmarking Fine-Grained Action for Embodied Agents
von: Liu, Dayong, et al.
Veröffentlicht: (2025)

PFEA: An LLM-based High-Level Natural Language Planning and Feedback Embodied Agent for Human-Centered AI
von: Ding, Wenbin, et al.
Veröffentlicht: (2025)

ETP-R1: Evolving Topological Planning with Reinforcement Fine-tuning for Vision-Language Navigation in Continuous Environments
von: Ye, Shuhao, et al.
Veröffentlicht: (2025)

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

Retrieval-Augmented Embodied Agents
von: Zhu, Yichen, et al.
Veröffentlicht: (2024)

Gen-Drive: Enhancing Diffusion Generative Driving Policies with Reward Modeling and Reinforcement Learning Fine-tuning
von: Huang, Zhiyu, et al.
Veröffentlicht: (2024)

Human Implicit Preference-Based Policy Fine-tuning for Multi-Agent Reinforcement Learning in USV Swarm
von: Kim, Hyeonjun, et al.
Veröffentlicht: (2025)

$\mathcal{P}^3$: Toward Versatile Embodied Agents
von: Zhou, Shengli, et al.
Veröffentlicht: (2025)

RoboOS: A Hierarchical Embodied Framework for Cross-Embodiment and Multi-Agent Collaboration
von: Tan, Huajie, et al.
Veröffentlicht: (2025)

Reinforcement Learning with Foundation Priors: Let the Embodied Agent Efficiently Learn on Its Own
von: Ye, Weirui, et al.
Veröffentlicht: (2023)

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

VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators
von: Li, Hengtao, et al.
Veröffentlicht: (2025)

An Android Robot Head as Embodied Conversational Agent
von: Heisler, Marcel, et al.
Veröffentlicht: (2023)

Memo: Training Memory-Efficient Embodied Agents with Reinforcement Learning
von: Gupta, Gunshi, et al.
Veröffentlicht: (2025)

SWITCH: Benchmarking Modeling and Handling of Tangible Interfaces in Long-horizon Embodied Scenarios
von: Lin, Jieru, et al.
Veröffentlicht: (2025)

MARFT: Multi-Agent Reinforcement Fine-Tuning
von: Liao, Junwei, et al.
Veröffentlicht: (2025)

LAGEA: Language Guided Embodied Agents for Robotic Manipulation
von: Chowdhury, Abdul Monaf, et al.
Veröffentlicht: (2025)

Towards Adaptive Environment Generation for Training Embodied Agents
von: Yeo, Teresa, et al.
Veröffentlicht: (2026)

BBSEA: An Exploration of Brain-Body Synchronization for Embodied Agents
von: Yang, Sizhe, et al.
Veröffentlicht: (2024)

AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions
von: Ying, Zonghao, et al.
Veröffentlicht: (2025)

EmbodiedCoder: Parameterized Embodied Mobile Manipulation via Modern Coding Model
von: Lin, Zefu, et al.
Veröffentlicht: (2025)

REFINE-DP: Diffusion Policy Fine-tuning for Humanoid Loco-manipulation via Reinforcement Learning
von: Gu, Zhaoyuan, et al.
Veröffentlicht: (2026)

All Robots in One: A New Standard and Unified Dataset for Versatile, General-Purpose Embodied Agents
von: Wang, Zhiqiang, et al.
Veröffentlicht: (2024)

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

Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation
von: Yuan, Yifu, et al.
Veröffentlicht: (2025)

Imaginative World Modeling with Scene Graphs for Embodied Agent Navigation
von: Hu, Yue, et al.
Veröffentlicht: (2025)

LEGS: Fine-Tuning Teleop-Free VLAs for Humanoid Loco-manipulation in an Embodied Gaussian Splatting World
von: Kim, Hojune, et al.
Veröffentlicht: (2026)

EmbodiedCity: A Benchmark Platform for Embodied Agent in Real-world City Environment
von: Gao, Chen, et al.
Veröffentlicht: (2024)

Reinforced Embodied Planning with Verifiable Reward for Real-World Robotic Manipulation
von: Bo, Zitong, et al.
Veröffentlicht: (2025)

Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making
von: Li, Manling, et al.
Veröffentlicht: (2024)

MIPD: A Multi-sensory Interactive Perception Dataset for Embodied Intelligent Driving
von: Li, Zhiwei, et al.
Veröffentlicht: (2024)

FDPP: Fine-tune Diffusion Policy with Human Preference
von: Chen, Yuxin, et al.
Veröffentlicht: (2025)

MemCompiler: Compile, Don't Inject -- State-Conditioned Memory for Embodied Agents
von: Ding, Xin, et al.
Veröffentlicht: (2026)

FOSP: Fine-tuning Offline Safe Policy through World Models
von: Cao, Chenyang, et al.
Veröffentlicht: (2024)

Transforming Monolithic Foundation Models into Embodied Multi-Agent Architectures for Human-Robot Collaboration
von: Sun, Nan, et al.
Veröffentlicht: (2025)

FiLM-Nav: Efficient and Generalizable Navigation via VLM Fine-tuning
von: Yokoyama, Naoki, et al.
Veröffentlicht: (2025)

Refinery: Active Fine-tuning and Deployment-time Optimization for Contact-Rich Policies
von: Tang, Bingjie, et al.
Veröffentlicht: (2025)

VIKI-R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning
von: Kang, Li, et al.
Veröffentlicht: (2025)