Imagen de Portada

Direct Post-Training Preference Alignment for Multi-Agent Motion Generation Models Using Implicit Feedback from Pre-training Demonstrations

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Tian, Ran, Goel, Kratarth
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence Robotics
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Integrating Controllable Motion Skills from Demonstrations
por: Liao, Honghao, et al.
Publicado: (2024)

Representation Alignment from Human Feedback for Cross-Embodiment Reward Learning from Mixed-Quality Demonstrations
por: Mattson, Connor, et al.
Publicado: (2024)

Leveraging Pre-trained Large Language Models with Refined Prompting for Online Task and Motion Planning
por: Guo, Huihui, et al.
Publicado: (2025)

Learning Reward and Policy Jointly from Demonstration and Preference Improves Alignment
por: Li, Chenliang, et al.
Publicado: (2024)

Generating Physically Realistic and Directable Human Motions from Multi-Modal Inputs
por: Shrestha, Aayam, et al.
Publicado: (2025)

Scaling Motion Forecasting Models with Ensemble Distillation
por: Ettinger, Scott, et al.
Publicado: (2024)

Scaling Laws of Motion Forecasting and Planning -- Technical Report
por: Baniodeh, Mustafa, et al.
Publicado: (2025)

Steerable Adversarial Scenario Generation through Test-Time Preference Alignment
por: Nie, Tong, et al.
Publicado: (2025)

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

Learning to Discern: Imitating Heterogeneous Human Demonstrations with Preference and Representation Learning
por: Kuhar, Sachit, et al.
Publicado: (2023)

AeroVerse: UAV-Agent Benchmark Suite for Simulating, Pre-training, Finetuning, and Evaluating Aerospace Embodied World Models
por: Yao, Fanglong, et al.
Publicado: (2024)

Aligning Humans and Robots via Reinforcement Learning from Implicit Human Feedback
por: Kim, Suzie, et al.
Publicado: (2025)

Reinforcement Learning from Implicit Neural Feedback for Human-Aligned Robot Control
por: Kim, Suzie
Publicado: (2025)

FoldPath: End-to-End Object-Centric Motion Generation via Modulated Implicit Paths
por: Rabino, Paolo, et al.
Publicado: (2025)

R2BC: Multi-Agent Imitation Learning from Single-Agent Demonstrations
por: Mattson, Connor, et al.
Publicado: (2025)

Implicit Kinodynamic Motion Retargeting for Human-to-humanoid Imitation Learning
por: Chen, Xingyu, et al.
Publicado: (2025)

Pre-training Auto-regressive Robotic Models with 4D Representations
por: Niu, Dantong, et al.
Publicado: (2025)

Maximizing Alignment with Minimal Feedback: Efficiently Learning Rewards for Visuomotor Robot Policy Alignment
por: Tian, Ran, et al.
Publicado: (2024)

Learning Sequential Kinematic Models from Demonstrations for Multi-Jointed Articulated Objects
por: Gupta, Anmol, et al.
Publicado: (2025)

Multi-Agent Planning Using Visual Language Models
por: Brienza, Michele, et al.
Publicado: (2024)

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

ARCap: Collecting High-quality Human Demonstrations for Robot Learning with Augmented Reality Feedback
por: Chen, Sirui, et al.
Publicado: (2024)

Forecast-PEFT: Parameter-Efficient Fine-Tuning for Pre-trained Motion Forecasting Models
por: Wang, Jifeng, et al.
Publicado: (2024)

Hierarchical Vision Language Action Model Using Success and Failure Demonstrations
por: Park, Jeongeun, et al.
Publicado: (2025)

Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trends
por: Xiang, Tian-Yu, et al.
Publicado: (2025)

Learning from Demonstration with Implicit Nonlinear Dynamics Models
por: Fagan, Peter David, et al.
Publicado: (2024)

Neural-Assisted in-Motion Self-Heading Alignment
por: Yampolsky, Zeev, et al.
Publicado: (2026)

Multi-Agent Inverse Q-Learning from Demonstrations
por: Haynam, Nathaniel, et al.
Publicado: (2025)

VARP: Reinforcement Learning from Vision-Language Model Feedback with Agent Regularized Preferences
por: Singh, Anukriti, et al.
Publicado: (2025)

MimicDreamer: Aligning Human and Robot Demonstrations for Scalable VLA Training
por: Li, Haoyun, et al.
Publicado: (2025)

Autonomous Implicit Indoor Scene Reconstruction with Frontier Exploration
por: Zeng, Jing, et al.
Publicado: (2024)

Evaluating VLMs' Spatial Reasoning Over Robot Motion: A Step Towards Robot Planning with Motion Preferences
por: Wu, Wenxi, et al.
Publicado: (2026)

DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning
por: Zhou, Gaoyue, et al.
Publicado: (2024)

Learning Pivoting Manipulation with Force and Vision Feedback Using Optimization-based Demonstrations
por: Shirai, Yuki, et al.
Publicado: (2025)

Zero-Shot Metric Depth Estimation via Monocular Visual-Inertial Rescaling for Autonomous Aerial Navigation
por: Yang, Steven, et al.
Publicado: (2025)

Improving Pre-Trained Vision-Language-Action Policies with Model-Based Search
por: Neary, Cyrus, et al.
Publicado: (2025)

RICL: Adding In-Context Adaptability to Pre-Trained Vision-Language-Action Models
por: Sridhar, Kaustubh, et al.
Publicado: (2025)

Learning Novel Skills from Language-Generated Demonstrations
por: Jin, Ao-Qun, et al.
Publicado: (2024)

Efficient Construction of Implicit Surface Models From a Single Image for Motion Generation
por: Chu, Wei-Teng, et al.
Publicado: (2025)

Motion Control in Multi-Rotor Aerial Robots Using Deep Reinforcement Learning
por: Shetty, Gaurav, et al.
Publicado: (2025)