Learn Quasi-Stationary Distributions of Finite State Markov Chain

Learn Quasi-Stationary Distributions of Finite State Markov Chain

We propose a reinforcement learning (RL) approach to compute the expression of quasi-stationary distribution. Based on the fixed-point formulation of quasi-stationary distribution, we minimize the KL-divergence of two Markovian path distributions induced by candidate distribution and true target dis...

Full description

Bibliographic Details
Main Authors: Zhiqiang Cai, Ling Lin, Xiang Zhou
Format: Article
Language:English
Published: MDPI AG 2022-01-01
Series:Entropy
Subjects:
quasi-stationary distribution
reinforcement learning
KL-divergence
actor-critic algorithm
Online Access:https://www.mdpi.com/1099-4300/24/1/133

Internet

https://www.mdpi.com/1099-4300/24/1/133

Similar Items