Keiwan Donyagard published Evolution simulator, in which the user creates a creature from bones, muscles and joints in the form of lines and dots, and the creature develops using a neural network as the brain. This is reported by The Next Web.
The creature evolves, performing the simplest actions: running, jumping and climbing up. The process clearly demonstrates the stage-by-stage learning of the neural network: it learns to analyze the distance to the ground and the number of points of contact, the direction of movement of the individual and speed, location in space and other parameters.
AI takes into account the position of the object in space, the direction of motion and speed, the distance to the ground, as well as the number of points of contact with it. During attempts, copies of the creature appear, from which the neural network chooses the two most successful ones, based on the conditions of the problem. Parameters are used to create new creatures and the loop is repeated until the task is executed correctly.