• 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.

• Electronics and Telecommunications Trends
• /
• v.35 no.4
• /
• pp.115-134
• /
• 2020

Several studies on machine learning (ML) based self-organizing networks (SONs) have been conducted, specifically for LTE, since studies to apply ML to optimize mobile communication systems started with 2G. However, they are still in the infancy stage. Owing to the complicated KPIs and stringent user requirements of 5G, it is necessary to design the 5G SON engine with intelligence to enable users to seamlessly and unlimitedly achieve connectivity regardless of the state of the mobile communication network. Therefore, in this study, we analyze and summarize the current state of machine learning studies applied to SONs as solutions to the complicated optimization problems that are caused by the unpredictable context of mobile communication scenarios.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1468-1473
• /
• 2005

In this paper, I proposed the INTelligent Agent System by Kohonen's Self Organizing Neural Network (INTAS). INTAS creates each user's profile from the information. Based on it, learning community grouping suitable to each individual is automatically executed by using unsupervised learning algorithm. In INTAS, grouping and learning are automatically performed on real time by multiagents, regardless of the number of learners. A new framework has been proposed to generate multiagents, and it is a feature that efficient multiagents can be executed by proposing a new negotiation mode between multiagents..

• Perspectives in Nursing Science
• /
• v.13 no.1
• /
• pp.29-35
• /
• 2016

Purpose: This study aimed to explore the underlying structures of students' interaction networks to monitor network changes during the year, to verify the relationship with self-directed learning, and to identify the effect of problem-based learning on interaction and self-directed learning. Methods: A longitudinal study was designed which included 3 parts (A=25, B=27, C=26) with a total of 78 second-year nursing students from 2013 to 2014. Interaction indicators used group network centralization and density, and individual in-degree centrality. Results: Group network centralization showed mean reversion patterns, however, centralization and density showed a slight increase from 2013 to 2014 (Centralization of A part from 52.78 to 36.96, B part from 20.56 to 32.20, C part from 34.40 to 37.24; Density of A part from 0.122 to 0.123, B part from 0.111 to 0.121, C part from 0.109 to 0.121). The individual in-degree centrality is significantly correlated with self-directed learning and the correlation coefficient increased during the year (r=.274 in 2013, r=.356 in 2014, p<.001). Conclusion: Students share information more interactively during the year and the more they share the higher the scores of self-directed learning.

• 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.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.625-628
• /
• 1997

In this paper the new neural network and sliding mode suspension controller is proposed. That neural network is error self-recurrent neural network. For fast on-line learning, this paper use recursive least squares method. A new neural networks converges considerably faster than the backpropagation algorithm and has advantages of being less affected by the poor initial weights and learning rate. The controller for suspension systems is designed according to sliding mode technique based on new proposed neural network.

• 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
• /
• 1991.10a
• /
• pp.768-772
• /
• 1991

The Self Creating and organizing (SCO) is a new architecture and one of the unsupervized learning algorithm for the artificial neural network. SCO begins with only one output node which has a sufficiently wide response range, and the response ranges of all the nodes decrease with time. Self Creating and Organizing Neural Network (SCONN) decides automatically whether adapting the weights of existing node or creating a new node. It is compared to the Kohonen's Self Organizing Feature Map (SOFM). The results show that SCONN has lots of advantages over other competitive learning architecture.

• International Journal of Control, Automation, and Systems
• /
• v.3 no.1
• /
• pp.43-55
• /
• 2005

In this paper, a predictive control method using self-recurrent wavelet neural network (SRWNN) is proposed for chaotic systems. Since the SRWNN has a self-recurrent mother wavelet layer, it can well attract the complex nonlinear system though the SRWNN has less mother wavelet nodes than the wavelet neural network (WNN). Thus, the SRWNN is used as a model predictor for predicting the dynamic property of chaotic systems. The gradient descent method with the adaptive learning rates is applied to train the parameters of the SRWNN based predictor and controller. The adaptive learning rates are derived from the discrete Lyapunov stability theorem, which are used to guarantee the convergence of the predictive controller. Finally, the chaotic systems are provided to demonstrate the effectiveness of the proposed control strategy.

• The Journal of Information Technology
• /
• v.8 no.1
• /
• pp.119-124
• /
• 2005

Learning procedure in the neural network is updating of weights between neurons. Unadequate initial learning coefficient causes excessive iterations of learning process or incorrect learning results and degrades learning efficiency. In this paper, adaptive learning algorithm is proposed to increase the efficient in the learning algorithms of Kohonens Self-Organization Neural networks. The algorithm updates the weights adaptively when learning procedure runs. To prove the efficiency the algorithm is experimented to clustering of the random weight. The result shows improved learning rate about 42~55% ; less iteration counts with correct answer.