Cascaded Gaps: Towards Gap-Dependent Regret for Risk-Sensitive Reinforcement Learning

In this paper, we study gap-dependent regret guarantees for risk-sensitive reinforcement learning based on the entropic risk measure. We propose a novel definition of sub-optimality gaps, which we call cascaded gaps, and we discuss their key components that adapt to the underlying structures of the...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2022-03
Hauptverfasser:	Fei, Yingjie, Xu, Ruitu
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Decision theory Learning Lower bounds Markov processes Risk Upper bounds
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!