US Patent 11446575 Machine learned ground coverage for virtual gaming environment

Virtual game worlds for computer games can be provided using machine learning. The use of machine learning enables the virtual game worlds to be generated at run time by standard consumer hardware devices. Machine learning agents are trained in advance to the characteristics of the particular game world. In doing so, ground coverage of the virtual game world can be determined. In one implementation, the ground coverage is determined using at least one ground coverage agent, which is a trained machine learning agent to provide appropriate ground coverage for the terrain of the virtual game world. Advantageously, the virtual game world can be provided in high resolution and is able to cover a substantially larger region than conventional practical.