Controlling the self learning behavior of an autonomous agent

The present invention relates to machine learning and more particularly to training and optimization of autonomous agents embodied in a computer system. In a computer system functioning as an autonomous agent with a robotic controller wherein the computer system need not be programmed to perform a specific task, values in an array of error variables are obtained from comparison between an array of resources variables used to indicate resource use and state of an Autonomous Agent and an array of corresponding desired levels for the resource variables. Each individual value in the array of error variables represents an error in the actual value of a particular resource variable as compared to its desired value. Derivative variables for the resource variables and for parameters controlling behavior of the Autonomous Agent are created. The values of the array of error variables and their associated derivative variables are used to adjust values of the behavior-controlling parameters thereby modifying behavior of the Autonomous Agent.