The　uncertainty　of　renewable　energy　and　demand　response　brings　many　challenges　to　the　microgrid　energy　management.　Driven　by　the　recent　advances　and　applications　of　deep　reinforcement　learning　a　microgrid　energy　management　strategy,　i.e.,　upper　confidence　bound　based　advantage　actor-critic　(A3C),　is　proposed　to　utilize　a　novel　action　exploration　mechanism　to　learn　the　power　output　of　wind　power　generation,　the　price　of　electricity　trading　and　power　load.　The　simulation　results　indicate　that　the　UCB-A3C　learning　based　energy　management　strategy　is　better　than　conventional　PPO,　actor　critical　and　A3C　algorithm.　Copyright　©　2022　Yang,　Li,　Shen,　Pei　and　Peng.