With　the　popularity　of　blockchains,　low　transaction　throughput　has　become　a　significant　bottleneck　in　applications　such　as　cryptocurrencies.　Payment　channel　networks　(PCNs)　have　received　attention　as　a　way　to　improve　throughput.　However,　due　to　the　difficulty　of　predicting　future　transactions　for　nodes,　the　transactions　are　prone　to　failure　when　the　channel　balances　do　not　meet　required　conditions.　It　has　been　shown　that　increasing　buffers　(queues)　in　PCNs　can　increase　the　success　rate　of　transactions　and　throughput.　Nevertheless,　there　is　no　effective　transaction　scheduling　strategy　in　buffers　when　transaction　values　are　flexible　and　variable.　To　solve　this　problem,　we　first　formulate　the　Scheduling　Problem　in　PCNs　(named　PSP),　and　then　prove　it　is　NP-hard.　We　design　a　neural　network　solver　based　on　the　Sequence　to　Sequence　(Seq2Seq)　architecture　and　train　the　solver　using　the　reinforcement　learning　method.　With　the　solver,　we　first　give　two　scheduling　strategies　to　maximize　transaction　throughput,　and　then　design　a　PCN　simulator　for　performance　evaluation.　Extensive　experiments　are　conducted　to　show　the　superiority　and　various　performances　of　our　proposal　and　illustrate　that　our　proposal　can　get　a　significant　advantage　in　terms　of　the　transaction　throughput　compared　to　the　existing　works.