The agent plays much better than the one with supervised learning. It even learns to hit the ball with the edge of racket to create harder situation for the opponent.
//create the model. the styleTransferModelData.bytes is the binary files provided that contains all needed pretrained data of the network.
var styleTransferModel = new UniversalStyleTransferModel(CNTK.DeviceDescriptor.GPUDevice(0), styleTransferModelData.bytes);
//build it with specified dimentions
styleTransferModel.CreateModelWithDimensions(contentSize, styleSize);
// Get the raw data of content and style imagefrom the Unity Texture2D object using helper functions.
var tempContentTexture = Images.GetReadableTextureFromUnreadable(contentTexture);
byte[] contentBytes = tempContentTexture.GetRGB24FromTexture2D(contentResize);
LECTURE
Lecture