Nowadays,　the　trend　of　powertrain　electrification　in　the　public　transportation　sector　is　clear.　To　fit　the　periodical　high-load　variation　and　relatively　high　handling　stability　requirements　for　battery　electric　buses,　the　dual-motor　four-wheel　powertrain　attracts　great　attention　in　recent　years.　Although　the　bus　routes　are　fixed,　the　passenger　capacity　and　driving　speed　vary　significantly　with　time,　season,　and　traffic　conditions,　which　presents　a　serious　challenge　for　efficient　power　coupling　in　the　dual-motor　system　to　reduce　energy　consumption.　To　mitigate　the　negative　effect　of　periodical　power　demand　variation　on　energy　coupling　efficiency　for　dual-motor　powertrain,　specific　driving　cycle　fitting　is　provided　based　on　massive　amounts　of　collected　bus　driving　data.　Then,　Deep　Deterministic　Policy　Gradient　(DDPG)　algorithm　is　introduced　in　Energy　Management　Strategy　(EMS)　design　to　improve　the　vehicle　energy　performance　in　fixed　driving　routes　with　uncertain　demand.　The　results　show　that　DDPG-EMS　achieve　93.79%-97.67%　of　the　benchmark　Dynamic　Programming　(DP)　-　based　EMS　under　different　validation　cycles.　The　comparison　of　DDPG-EMS　agent　trained　by　fitting　cycle　and　typical　cycle　reached　97.1%-97.67%　and　93.79%-96.99%　of　DP,　respectively,　which　proved　the　effectiveness　of　the　specifically　designed　cycle　in　reinforcement　learning-based　EMS　for　dual-motor　electrified　bus.　　©　2022　IEEE.