MetaCURL: Non-stationary Concave Utility Reinforcement Learning

We explore online learning in episodic loop-free Markov decision processes on non-stationary environments (changing losses and probability transitions). Our focus is on the Concave Utility Reinforcement Learning problem (CURL), an extension of classical RL for handling convex performance criteria in...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Moreno, Bianca Marin, Brégère, Margaux, Gaillard, Pierre, Oudjane, Nadia
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Learning Mathematics - Probability Mathematics - Statistics Theory Statistics - Machine Learning Statistics - Theory
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!