This is the code for the simulation part of the paper

Pang, Bo, and Zhong-Ping Jiang. "Reinforcement Learning for Adaptive Optimal Stationary Control of Linear Stochastic Systems." arXiv preprint arXiv:2107.07788 (2021).

This scripts generates input/state data from the continuous-time linear stochastic system to be controlled.

This scripts learn the near-optimal stationary control policy using the collected input/state data.

This scripts generates the Figure 1 in the paper.

This scripts generates the Figure 2 and Figure 3 in the paper.

I successfully ran the code in MATLAB R2017b.