Image de couverture de livre

MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Baur, Raphaël, Metz, Yannick, Gkoulta, Maria, El-Assady, Mennatallah, Ramponi, Giorgia, Buening, Thomas Kleine
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Reward Learning from Multiple Feedback Types
par: Metz, Yannick, et autres
Publié: (2025)

Mapping out the Space of Human Feedback for Reinforcement Learning: A Conceptual Framework
par: Metz, Yannick, et autres
Publié: (2024)

Aligning Language Models from User Interactions
par: Buening, Thomas Kleine, et autres
Publié: (2026)

Stackelberg Learning from Human Feedback: Preference Optimization as a Sequential Game
par: Pásztor, Barna, et autres
Publié: (2025)

Deconstructing Human-AI Collaboration: Agency, Interaction, and Adaptation
par: Holter, Steffen, et autres
Publié: (2024)

Environment Design for Inverse Reinforcement Learning
par: Buening, Thomas Kleine, et autres
Publié: (2022)

Causal Imitation Learning under Expert-Observable and Expert-Unobservable Confounding
par: Shao, Daqian, et autres
Publié: (2025)

A Minimax Approach to Ad Hoc Teamwork
par: Villin, Victor, et autres
Publié: (2025)

SyntaxShap: Syntax-aware Explainability Method for Text Generation
par: Amara, Kenza, et autres
Publié: (2024)

Challenges and Opportunities in Text Generation Explainability
par: Amara, Kenza, et autres
Publié: (2024)

Concept-Level Explainability for Auditing & Steering LLM Responses
par: Amara, Kenza, et autres
Publié: (2025)

DxHF: Providing High-Quality Human Feedback for LLM Alignment via Interactive Decomposition
par: Shi, Danqing, et autres
Publié: (2025)

Strategyproof Reinforcement Learning from Human Feedback
par: Buening, Thomas Kleine, et autres
Publié: (2025)

Cross-Cultural Simulation of Citizen Emotional Responses to Bureaucratic Red Tape Using LLM Agents
par: Ni, Wanchun, et autres
Publié: (2026)

PleaSQLarify: Visual Pragmatic Repair for Natural Language Database Querying
par: Chan, Robin Shing Moon, et autres
Publié: (2026)

On Feasible Rewards in Multi-Agent Inverse Reinforcement Learning
par: Freihaut, Till, et autres
Publié: (2024)

Deconstructing Human‐AI Collaboration: Agency, Interaction, and Adaptation
par: Steffen Holter, et autres
Publié: (2024)

TopoAlign: Topology-Aware Visual Representation Alignment
par: Yan, Xinyuan, et autres
Publié: (2026)

Fine-tuning Behavioral Cloning Policies with Preference-Based Reinforcement Learning
par: Macuglia, Maël, et autres
Publié: (2025)

Why context matters in VQA and Reasoning: Semantic interventions for VLM input modalities
par: Amara, Kenza, et autres
Publié: (2024)

Instance-Adaptive Parametrization for Amortized Variational Inference
par: Pollastro, Andrea, et autres
Publié: (2026)

Preference Elicitation for Offline Reinforcement Learning
par: Pace, Alizée, et autres
Publié: (2024)

iNNspector: Visual, Interactive Deep Model Debugging
par: Spinner, Thilo, et autres
Publié: (2024)

Fast and Robust Likelihood-Guided Diffusion Posterior Sampling with Amortized Variational Inference
par: Zheng, Léon, et autres
Publié: (2026)

Contextual Bilevel Reinforcement Learning for Incentive Alignment
par: Thoma, Vinzenz, et autres
Publié: (2024)

Aligning Few-Step Generative Models by Amortizing Sample-based Variational Inference
par: Lee, Jaewoo, et autres
Publié: (2026)

Strategic Linear Contextual Bandits
par: Buening, Thomas Kleine, et autres
Publié: (2024)

LayerFlow: Layer-wise Exploration of LLM Embeddings using Uncertainty-aware Interlinked Projections
par: Sevastjanova, Rita, et autres
Publié: (2025)

CafGa: Customizing Feature Attributions to Explain Language Models
par: Boyle, Alan, et autres
Publié: (2025)

LayerFlow: Layer‐wise Exploration of LLM Embeddings using Uncertainty‐aware Interlinked Projections
par: Rita Sevastjanova, et autres
Publié: (2025)

ProvenanceWidgets: A Library of UI Control Elements to Track and Dynamically Overlay Analytic Provenance
par: Narechania, Arpit, et autres
Publié: (2024)

Iterative Amortized Inference: Unifying In-Context Learning and Learned Optimizers
par: Mittal, Sarthak, et autres
Publié: (2025)

BRAIn: Bayesian Reward-conditioned Amortized Inference for natural language generation from feedback
par: Pandey, Gaurav, et autres
Publié: (2024)

Understanding Large Language Model Behaviors through Interactive Counterfactual Generation and Analysis
par: Cheng, Furui, et autres
Publié: (2024)

Reinforcement Learning via Self-Distillation
par: Hübotter, Jonas, et autres
Publié: (2026)

Repairing Reward Functions with Feedback to Mitigate Reward Hacking
par: Hatgis-Kessell, Stephane, et autres
Publié: (2025)

Challenges and Opportunities for Visual Analytics in Jurisprudence
par: Fürst, Daniel, et autres
Publié: (2024)

BONSAI: A Mixed-Initiative Workspace for Human-AI Co-Development of Visual Analytics Applications
par: Spinner, Thilo, et autres
Publié: (2026)

MAVRL: Learn to Fly in Cluttered Environments with Varying Speed
par: Yu, Hang, et autres
Publié: (2024)

Amortized Variational Inference for Logistic Regression with Missing Covariates
par: Cherifi, M., et autres
Publié: (2026)