With the recent developments in sensor technology and pose estimation algorithms, skeleton based action recognition has become popular. This paper proposes a deep learning framework for action recognition task using ensemble learning. We design two subnets to capture spatial and temporal dynamics of the entire video sequence, referred to as Spatial -distance Net (SdNet) and Temporal – distance Net (TdNet) respectively. More specifically, SdNet is a Convolutional Neural Network based subnet to capture spatial dynamics of joints within a frame and TdNet is a long short term memory based subnet to exploit temporal dynamics of joints between frames along the sequence. Finally, two subnets are fused as one ensemble network, referred to as Spatio-Temporal distance Net (STdNet) to explore both spatial and temporal information. The efficacy of the proposed method is evaluated on two widely used datasets, UTD MHAD and NTU RGB+D, and the proposed STdNet achieved 91.16% and 82.55% accuracies respectively.