Abstract: Machine learning is used to generate and update predictive models configured to predict the positions, orientations, or actions of various gameplay elements capable of being controlled by players of a network-based multiplayer game. A gaming server can send a trained predictive model to each player device actively involved in a gaming session. Those devices can use the predictive model to predict the positions and orientations of various gameplay elements, where the actual data will not be received for a period of time due to latency of transmission over at least one network connection. When the actual data is received, the game state and gameplay action can be corrected or initiated as appropriate, enabling the overall gameplay experience to be smoother and more enjoyable. The gameplay and prediction data can be analyzed to further train or improve the models.

Abstract: Multi-dimensional models are supported for game creation via two-dimensional (2D) visual scripting systems. Visual scripting can utilize 2D nodes on a grid, where the nodes can interact through the use of input and output ports, and can be wired together to create gameplay behavior. A 2D rendering of a three-dimensional (3D) object (e.g., a mesh) can be added to the node grid for a gaming application. A scripting interface allows rules and ports to be created for specific aspects of the mesh, such as may relate to features, skeletons, or bounding boxes. Multiple scripting nodes can be associated with the same mesh such that the mesh is not duplicated in the visual scripting view port. The functionality for the 3D object can then be incorporated into the game based at least in part upon the associated nodes without manual coding or compilation.

Abstract: A digital asset, such as may be created as part of a game development process, can go through various stages of development where various types of processing are performed. Some of this processing requires the asset to be in specific formats. In order to ensure that a computing device has the appropriate packages installed for processing the asset, an asset processor tool can monitor the assets and send information to a package management service regarding an asset that is unable to be processed on the computing device. The package management service can attempt to determine an appropriate package for the processing, and provide that package to the computing device. In some cases the identification and installation of packages can be performed automatically, while in other cases a user may need to select a recommended package, approve installation, or provide payment, among other such options.