TARGET-ORIENTED REINFORCEMENT LEARNING METHOD AND APPARATUS FOR PERFORMING THE SAME

• Main Authors: LEE MINSU, LEE MIN WHOO, KIM KIBEOM, KIM YOONSUNG, ZHANG BYOUNG TAK
• Format: Patent
• Language: English; Korean
• Published: 31.12.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

A method for a target-oriented reinforcement learning according to one embodiment comprises: a step of collecting the data related to the target of reinforcement learning as the target data in a process of performing reinforcement learning; a step of learning the collected target data as auxiliary learning for the reinforcement learning; and a step of applying the result of learning the target data when performing the reinforcement learning. Therefore, the present invention is capable of expecting an effect of increasing an effectiveness and efficiency of reinforcement learning. 일 실시예에 따른 목표 지향적 강화학습 방법은, 강화학습을 수행하는 과정에서 상기 강화학습의 목표와 관련된 데이터를 목표 데이터로서 수집하는 단계, 상기 강화학습에 대한 보조학습으로서 상기 수집된 목표 데이터를 학습하는 단계 및 상기 목표 데이터를 학습한 결과를 상기 강화학습 수행 시 반영하는 단계를 포함한다.