AUTHOR=Tian Hui , Su Xin , Hou Yanfang 

TITLE=Feedback stabilization of probabilistic finite state machines based on deep Q-network

JOURNAL=Frontiers in Computational Neuroscience

VOLUME=Volume 18 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/computational-neuroscience/articles/10.3389/fncom.2024.1385047

DOI=10.3389/fncom.2024.1385047

ISSN=1662-5188

ABSTRACT=This paper investigates the stabilization of probabilistic finite state machines (PFSMs) through the deep Q-network (DQN) technique, which is a model-free optimization method. First, the feedback stabilization problem of PFSMs is transformed into an optimization problem. Next, a necessary and sufficient stabilizability condition is derived for PFSMs. Then, under the stabilizability condition, the optimization problem can be solved by DQN. This method is particularly suitable for non-small-scale PFSMs. Finally, the effectiveness of our results is demonstrated through an example.