신경회로망을 이용한 도립진자의 학습제어

• 영문명: Learning Control of Inverted Pendulum Using Neural Networks
• 발행기관: 강원대학교 산업기술연구소
• 저자명: 이재강(Lee Jae Kang) 김일환(Kim Il Hwan)
• 간행물 정보: 『산업기술연구』vol.20, 1~6쪽, 전체 6쪽
• 주제분류: 공학 > 공학일반
• 파일형태: PDF
• 발행일자: 2000.09.30

영문 초록

A priori information of object is needed to control in some well known control methods. But we can’t always know a priori information of object in real world. In this paper, the inverted pendulum is simulated as a control task with the goal of learning to balance the pendulum with no a priori information using neural network controller. In contrast to other applications of neural networks to the inverted pendulum task, the performance feedback is unavailable on each training step. appearing only as a failure signal when the pendulum falls or reaches the bound of track. To solve this task, the delayed performance evaluation and the learning of nonlinear of nonlinear functions must be dealt. Reinforcement learning method is used for those issues.

목차

Abstract

1. 서론

2. 강화학습의 기본개념

3. 정책의 학습(Learning of Optimal policy)

4. 모의실험

5. 결론

참고문헌

키워드

강화학습 신경회로망 도립진자 Reinforcement Learning Neural Network Inverted Pendulum