METHOD FOR PERFORMING REINFORCEMENT LEARNING USING MULTI-MODAL ARTIFICIAL INTELLIGENCE AGENT AND COMPUTING APPARATUS FOR PERFORMING THE SAME

• Main Authors: PARK JUNSEOK, LEE MINSU, LEE MIN WHOO, PARK KWANYOUNG, OH HYUN SEOK, LEE GANGHUN, LEE YOUNGKI, ZHANG BYOUNG TAK
• Format: Patent
• Language: English; Korean
• Published: 12.06.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC COMMUNICATION TECHNIQUE; ELECTRICITY; PHYSICS; PICTORIAL COMMUNICATION, e.g. TELEVISION

A method for performing reinforcement learning using a multimodal artificial intelligence agent comprises: a step of dividing the frames included in the video of the virtual environment into a plurality of sections; and a step of performing reinforcement learning by applying one of a plurality of gu...