• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.5
• /
• pp.353-360
• /
• 2004

This paper considers reinforcement learning control with the self-organizing map. Reinforcement learning uses the observable states of objective system and signals from interaction of the system and environment as input data. For fast learning in neural network training, it is necessary to reduce learning data. In this paper, we use the self-organizing map to partition the observable states. Partitioning states reduces the number of learning data which is used for training neural networks. And neural dynamic programming design method is used for the controller. For evaluating the designed reinforcement learning controller, an inverted pendulum on the cart system is simulated. The designed controller is composed of serial connection of self-organizing map and two Multi-layer Feed-Forward Neural Networks.

• Journal of Korean Biological Nursing Science
• /
• v.20 no.2
• /
• pp.132-140
• /
• 2018

Purpose: This study has been carried out in order to develop and verify the effects of self-leadership reinforcement program for hospital nurses. Methods: The research design was a non-equivalent control group pre-posttest design. Participants were 64 individuals (32 in each group), all of whom were nurses working at a university hospital, with less than five years of job experience. Experimental group was provided with two hours of self-leadership reinforcement program, once per week, for four weeks. The questionnaire for pre and post test included general characteristics, transfer motivation for learning, self-leadership, communication ability, clinical nursing competency, organizational commitment, and turnover intentions. Results: There was a significant difference in self-leadership scores between experimental group and control group (F= 15.10, p<.001). There was also a significant difference between the experimental group and the control group in terms of transfer motivation for learning (t = -5.44 p<.001), communication ability (F = 15.29, p<.001), clinical nursing competency (F = 15.23, p<.001), and organizational commitment scores (F = 7.21, p=.009). Conclusion: The self-leadership reinforcement program developed in this study was effective in improving self-leadership, communication ability, clinical nursing competency, and organizational commitment. Thus, by implementing the program at clinical levels, it will be a basis for nursing personnel resource administration.

• Journal of IKEEE
• /
• v.25 no.4
• /
• pp.644-649
• /
• 2021

Self-Imitation Learning is a simple off-policy actor-critic algorithm that makes an agent find an optimal policy by using past good experiences. In case that Self-Imitation Learning is combined with reinforcement learning algorithms that have actor-critic architecture, it shows performance improvement in various game environments. However, its applications are limited to reinforcement learning algorithms that have actor-critic architecture. In this paper, we propose a method of applying Self-Imitation Learning to Deep Q-Network which is a value-based deep reinforcement learning algorithm and train it in various game environments. We also show that Self-Imitation Learning can be applied to Deep Q-Network to improve the performance of Deep Q-Network by comparing the proposed algorithm and ordinary Deep Q-Network training results.

• Earthquakes and Structures
• /
• v.22 no.1
• /
• pp.39-51
• /
• 2022

The axial compression behavior of nine self-compacting concrete columns confined with CFRP-PVC spirals was studied. Three parameters of spiral reinforcement spacing, spiral reinforcement diameter and height diameter ratio were studied. The test results show that the CFRP strip and PVC tube are destroyed first, and the spiral reinforcement and longitudinal reinforcement yield. The results show that with the increase of spiral reinforcement spacing, the peak bearing capacity decreases, but the ductility increases; with the increase of spiral reinforcement diameter, the peak bearing capacity increases, but has little effect on ductility, and the specimen with the ratio of height to diameter of 7.5 has the best mechanical properties. According to the reasonable constitutive relation of material, the finite element model of axial compression is established. Based on the verified finite element model, the stress mechanism is revealed. Finally, the composite constraint model and bearing capacity calculation method are proposed.

• Journal of Industrial Technology
• /
• v.24 no.A
• /
• pp.99-107
• /
• 2004

This paper considers reinforcement learning control with the self-organizing map. Reinforcement learning uses the observable states of objective system and signals from interaction of the system and the environments as input data. For fast learning in neural network training, it is necessary to reduce learning data. In this paper, we use the self-organizing map to parition the observable states. Partitioning states reduces the number of learning data which is used for training neural networks. And neural dynamic programming design method is used for the controller. For evaluating the designed reinforcement learning controller, an inverted pendulum of the cart system is simulated. The designed controller is composed of serial connection of self-organizing map and two Multi-layer Feed-Forward Neural Networks.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.142-145
• /
• 2003

Many control applications using Neural Network need a priori information about the objective system. But it is impossible to get exact information about the objective system in real world. To solve this problem, several control methods were proposed. Reinforcement learning control using neural network is one of them. Basically reinforcement learning control doesn't need a priori information of objective system. This method uses reinforcement signal from interaction of objective system and environment and observable states of objective system as input data. But many methods take too much time to apply to real-world. So we focus on faster learning to apply reinforcement learning control to real-world. Two data types are used for reinforcement learning. One is reinforcement signal data. It has only two fixed scalar values that are assigned for each success and fail state. The other is observable state data. There are infinitive states in real-world system. So the number of observable state data is also infinitive. This requires too much learning time for applying to real-world. So we try to reduce the number of observable states by classification of states with Self-Organizing Map. We also use neural dynamic programming for controller design. An inverted pendulum on the cart system is simulated. Failure signal is used for reinforcement signal. The failure signal occurs when the pendulum angle or cart position deviate from the defined control range. The control objective is to maintain the balanced pole and centered cart. And four states that is, position and velocity of cart, angle and angular velocity of pole are used for state signal. Learning controller is composed of serial connection of Self-Organizing Map and two Multi-layer Feed-Forward Neural Networks.

• Journal of Institute of Control, Robotics and Systems
• /
• v.2 no.2
• /
• pp.108-114
• /
• 1996

We present proofs of the stability and convergence of Self-organizing feature map (SOFM) neural network with time-invarient learning rate and binary reinforcement function. One of the major problems in Self-organizing feature map neural network concerns with learning rate-"Kalman Filter" gain in stochsatic control field which is monotone decreasing function and converges to 0 for satisfying minimum variance property. In this paper, we show that the stability and convergence of Self-organizing feature map neural network with time-invariant learning rate. The analysis of the proposed algorithm shows that the stability and convergence is guranteed with exponentially stable and weak convergence properties as well.s as well.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.1
• /
• pp.180-188
• /
• 1995

A modified Kohonen's self-organizing feature map (SOFM) algorithm which has binary reinforcement function and a constant learning rate is proposed. In contrast to the time-varing adaptaion gain of the original Kohonen's SOFM algorithm, the proposed algorithm uses a constant adaptation gain, and adds a binary reinforcement function in order to compensate for the lowered learning ability of SOFM due to the constant learning rate. Since the proposed algorithm does not have the complicated multiplication, it's digital hardware implementation is much easier than that of the original SOFM.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.10
• /
• pp.23-31
• /
• 2018

Recently, there have been many studies on machine learning. Among them, studies on reinforcement learning are actively worked. In this study, we propose a controller to control bicycle using DDPG (Deep Deterministic Policy Gradient) algorithm which is the latest deep reinforcement learning method. In this paper, we redefine the compensation function of bicycle dynamics and neural network to learn agents. When using the proposed method for data learning and control, it is possible to perform the function of not allowing the bicycle to fall over and reach the further given destination unlike the existing method. For the performance evaluation, we have experimented that the proposed algorithm works in various environments such as fixed speed, random, target point, and not determined. Finally, as a result, it is confirmed that the proposed algorithm shows better performance than the conventional neural network algorithms NAF and PPO.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.5A
• /
• pp.511-518
• /
• 2009

This study was intended to compare and evaluate the adhesion of High flowing Self-compacting Concrete (HSCC), Conventional Concrete (CC) and deformed bar based on concrete strength 3 (30, 50 and 70 MPa), among the factors affecting the bond strength between concrete and rebar, after fabricating the specimen by modifying the rebar position at Horizontal reinforcement at bottom position (HB), horizontal reinforcement at top position (HT) and vertical reinforcement type (V). As a result of measuring bond strength of HB/HT rebar to evaluate the factor of the rebar at top position, the bond strength of HB/HT rebar at 50 and 70 MPa was 1.3 or less and at 30 MPa, HSCC and CC appeared to be 1.2 and 2,1, respectively. Thus, when designing the anchorage length according to the concrete structure design standard (2007) at HSCC 30, 50 and 70 MPa, it would be desirable to reduce the correction factor of anchorage length of the horizontal reinforcement at top position, which is suggested for the reinforcement at top position, to less than 1.3 of CC.