An Actor–Critic Algorithm With Function Approximation for Risk Sensitive Cost Markov Decision Processes

Soumyajit Guin

doi:10.1109/TAC.2025.3593328

An Actor–Critic Algorithm With Function Approximation for Risk Sensitive Cost Markov Decision Processes

2025-07-28

0

PRE

AI

DOI：10.1109/TAC.2025.3593328

Original

Original request for help

Save

Abstract

En 中文

In this article, we consider the risk-sensitive cost criterion with exponentiated costs for Markov decision processes and develop a model-free policy gradient algorithm in this setting. Unlike additive cost criteria, such as average or discounted cost, the risk-sensitive cost criterion is less studied due to the complexity resulting from the multiplicative structure of the resulting Bellman equation. We develop an actor–critic algorithm with function approximation in this setting and provide its asymptotic convergence analysis. We also show the results of numerical experiments that demonstrate the superiority in performance of our algorithm over other recent algorithms in the literature.

Keywords:

Reinforcement learning

risk-sensitive cost

stochastic approximation

An Actor–Critic Algorithm With Function Approximation for Risk Sensitive Cost Markov Decision Processes

Abstract

Journal

Organization