Risk-Sensitivity Vanishing Limit for Controlled Markov Processes

In this paper, we prove that the optimal risk-sensitive reward for Markov decision processes with compact state space and action space converges to the optimal average reward as the risk-sensitive factor tends to 0. In doing so, a variational formula for the optimal risk-sensitive reward is derived....

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Journal of dynamical and control systems 2023-10, Vol.29 (4), p.1471-1508
Hauptverfasser:	Dai, Yanan, Chen, Jinwen
Format:	Artikel
Sprache:	eng
Schlagworte:	Calculus of Variations and Optimal Control Optimization Control Dynamical Systems Dynamical Systems and Ergodic Theory Markov processes Mathematics Mathematics and Statistics Maximization Optimization Systems Theory Vibration
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!