Mapping out the Space of Human Feedback for Reinforcement Learning: A Conceptual Framework

Reinforcement Learning from Human feedback (RLHF) has become a powerful tool to fine-tune or train agentic machine learning models. Similar to how humans interact in social contexts, we can use many types of feedback to communicate our preferences, intentions, and knowledge to an RL agent. However,...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Metz, Yannick, Lindner, David, Baur, Raphaël, El-Assady, Mennatallah
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Human-Computer Interaction Computer Science - Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!