Copertina

Masked IRL: LLM-Guided Reward Disambiguation from Demonstrations and Language

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Hwang, Minyoung, Forsey-Smerek, Alexandra, Dennler, Nathaniel, Bobu, Andreea
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

Learning Contextually-Adaptive Rewards via Calibrated Features
di: Forsey-Smerek, Alexandra, et al.
Pubblicazione: (2025)

QuickLAP: Quick Language-Action Preference Learning for Semi-Autonomous Agents
di: Nader, Jordan Abi, et al.
Pubblicazione: (2025)

GIFT: Generalizing Intent for Flexible Test-Time Rewards
di: Amin, Fin, et al.
Pubblicazione: (2026)

Improving through Interaction: Searching Behavioral Representation Spaces with CMA-ES-IG
di: Dennler, Nathaniel, et al.
Pubblicazione: (2026)

Robots That Know What to Ask: Recovering Misaligned Rewards through Targeted Explanations
di: Merker, Helena, et al.
Pubblicazione: (2026)

Improving User Experience in Preference-Based Optimization of Reward Functions for Assistive Robots
di: Dennler, Nathaniel, et al.
Pubblicazione: (2024)

Goal Inference from Open-Ended Dialog
di: Ma, Rachel, et al.
Pubblicazione: (2024)

Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons
di: Liang, Anthony, et al.
Pubblicazione: (2026)

Preference-Conditioned Language-Guided Abstraction
di: Peng, Andi, et al.
Pubblicazione: (2024)

Singing the Body Electric: The Impact of Robot Embodiment on User Expectations
di: Dennler, Nathaniel, et al.
Pubblicazione: (2024)

Flexible Agent Alignment with Goal Inference from Open-Ended Dialog
di: Ma, Rachel, et al.
Pubblicazione: (2025)

IRL-VLA: Training an Vision-Language-Action Policy via Reward World Model
di: Jiang, Anqing, et al.
Pubblicazione: (2025)

Contrastive Learning from Exploratory Actions: Leveraging Natural Interactions for Preference Elicitation
di: Dennler, Nathaniel, et al.
Pubblicazione: (2025)

Aligning Robot and Human Representations
di: Bobu, Andreea, et al.
Pubblicazione: (2023)

IRL-DAL: Safe and Adaptive Trajectory Planning for Autonomous Driving via Energy-Guided Diffusion Models
di: Miangoleh, Seyed Ahmad Hosseini, et al.
Pubblicazione: (2026)

Automation from the Worker's Perspective
di: Armstrong, Ben, et al.
Pubblicazione: (2024)

Visual IRL for Human-Like Robotic Manipulation
di: Asali, Ehsan, et al.
Pubblicazione: (2024)

VernaCopter: Disambiguated Natural-Language-Driven Robot via Formal Specifications
di: van de Laar, Teun, et al.
Pubblicazione: (2024)

Position: Olfaction Standardization is Essential for the Advancement of Embodied Artificial Intelligence
di: France, Kordel K., et al.
Pubblicazione: (2025)

TreeIRL: Safe Urban Driving with Tree Search and Inverse Reinforcement Learning
di: Tomov, Momchil S., et al.
Pubblicazione: (2025)

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

From Demonstrations to Rewards: Test-Time Prompt Optimization for VLM Reward Models
di: Gumbsch, Christian, et al.
Pubblicazione: (2026)

Reward Learning from Suboptimal Demonstrations with Applications in Surgical Electrocautery
di: Karimi, Zohre, et al.
Pubblicazione: (2024)

PRISM: Projection-based Reward Integration for Scene-Aware Real-to-Sim-to-Real Transfer with Few Demonstrations
di: Sun, Haowen, et al.
Pubblicazione: (2025)

MotIF: Motion Instruction Fine-tuning
di: Hwang, Minyoung, et al.
Pubblicazione: (2024)

Sample-Efficient Reinforcement Learning with Symmetry-Guided Demonstrations for Robotic Manipulation
di: Enayati, Amir M. Soufi, et al.
Pubblicazione: (2023)

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

CLARA: Classifying and Disambiguating User Commands for Reliable Interactive Robotic Agents
di: Park, Jeongeun, et al.
Pubblicazione: (2023)

Reduced-Order Model-Guided Reinforcement Learning for Demonstration-Free Humanoid Locomotion
di: Liu, Shuai, et al.
Pubblicazione: (2025)

Evaluating and Personalizing User-Perceived Quality of Text-to-Speech Voices for Delivering Mindfulness Meditation with Different Physical Embodiments
di: Shi, Zhonghao, et al.
Pubblicazione: (2024)

Integrating Disambiguation and User Preferences into Large Language Models for Robot Motion Planning
di: Abugurain, Mohammed, et al.
Pubblicazione: (2024)

Large Reward Models: Generalizable Online Robot Reward Generation with Vision-Language Models
di: Wu, Yanru, et al.
Pubblicazione: (2026)

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

Causally Robust Reward Learning from Reason-Augmented Preference Feedback
di: Hwang, Minjune, et al.
Pubblicazione: (2026)

Demonstrating the Octopi-1.5 Visual-Tactile-Language Model
di: Yu, Samson, et al.
Pubblicazione: (2025)

PROGRESSOR: A Perceptually Guided Reward Estimator with Self-Supervised Online Refinement
di: Ayalew, Tewodros, et al.
Pubblicazione: (2024)

Human-Guided Harm Recovery for Computer Use Agents
di: Li, Christy, et al.
Pubblicazione: (2026)

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

Text2Touch: Tactile In-Hand Manipulation with LLM-Designed Reward Functions
di: Field, Harrison, et al.
Pubblicazione: (2025)

LEMMo-Plan: LLM-Enhanced Learning from Multi-Modal Demonstration for Planning Sequential Contact-Rich Manipulation Tasks
di: Chen, Kejia, et al.
Pubblicazione: (2024)