METHOD FOR REINFORCEMENT LEARNING USING VIRTUAL ENVIRONMENT GENERATED BY DEEP LEARNING

摘要

A method for reinforcement learning using a virtual environment generated by deep learning comprises the following steps. A first artificial intelligence module performs reinforcement learning of a first artificial neural network by using a second artificial neural network of a second artificial intelligence module as a virtual environment. After the reinforcement learning of the first artificial neural network is completed, the first artificial intelligence module determines a control command by applying sensing information received from a sensor of a control environment to the first artificial neural network. The first artificial intelligence module provides the control command to an actuator so that the actuator in the control environment may control a control object according to the control command.