Long , JihaoHan , Jiequn and E , Weinan. (2022). An $L^2$ Analysis of Reinforcement Learning in High Dimensions with Kernel and Neural Network Approximation.
            <i>CSIAM Transactions on Applied Mathematics</i>. <i>3</i> (2).
            191-220.
         doi:10.4208/csiam-am.SO-2021-0026