Earticle

Cart-pole 균형 문제는 유전자 알고리즘, 인공신경망, 강화학습 등을 이용한 제어 전략 분야의 표준 문제이다. 본 논문에서는 cart-pole 균형문제를 해결하기 위해 실시간 강화 학습을 이용한 접근 방법을 제안하였다. 본 논문의 목적은 cart-pole 균형 문제에서 OREL 학습 시스템의 학습 방법을 분석하는데 있다. 실험을 통해, 본 논문에서 제안한 OREL 학습 방법은 Q-학습보다 최적 값 함수에 더 빠르게 접근함을 알 수 있었다.

The cart-pole balancing problem is a pseudo-standard benchmark problem from the field of control methods including genetic algorithms, artificial neural networks, and reinforcement learning. In this paper, we propose a novel approach by using online reinforcement learning(OREL) to solve this cart-pole balancing problem. The objective is to analyze the learning method of the OREL learning system in the cart-pole balancing problem. Through experiment, we can see that approximate faster the optimal value-function than Q-learning.

Individual items are produced continuously from an industrial process. Each item is checked to determine whether it satisfies a lower screening limit for the quality characteristic which is the weight of an expensive ingredient. If it does, it is sold at a regular price; if it does not, it is reprocessed or sold at a reduced price. The process mean may be adjusted to a higher value in order to reduce the proportion of the nonconforming items. Using a higher process mean, however, may result in a higher production cost. In this paper, the optimal process mean and lower screening limit are determined in situations where the probability that an item functions well is given by a logistic function of the quality characteristic. Profit models are constructed which involve four price/cost components; selling prices, cost from an accepted nonconforming item, and reprocessing and inspection costs. Methods of finding the optimal process mean and lower screening limit are presented and numerical examples are given.