Tight Performance Guarantees of Imitator Policies with Continuous Actions

Behavioral Cloning (BC) aims at learning a policy that mimics the behavior demonstrated by an expert. The current theoretical understanding of BC is limited to the case of finite actions. In this paper, we study BC with the goal of providing theoretical guarantees on the performance of the imitator...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Maran, Davide, Metelli, Alberto Maria, Restelli, Marcello
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!