• Journal of Practical Engineering Education
• /
• v.14 no.1
• /
• pp.219-224
• /
• 2022

Q-Learning is a technique widely used as a basic algorithm for reinforcement learning. Q-Learning trains the agent in the direction of maximizing the reward through the greedy action that selects the largest value among the rewards of the actions that can be taken in the current state. In this paper, we studied a policy that can speed up agent training using Q-Learning in Frozen Lake 8×8 grid environment. In addition, the training results of the existing algorithm of Q-learning and the algorithm that gave the attribute 'direction' to agent movement were compared. As a result, it was analyzed that the Q-Learning policy proposed in this paper can significantly increase both the accuracy and training speed compared to the general algorithm.

• Journal of KIISE:Software and Applications
• /
• v.31 no.11
• /
• pp.1431-1438
• /
• 2004

Reinforcement learning learns policies for accomplishing a task's goal by experience through interaction between agent and environment. Q-learning, basis algorithm of reinforcement learning, has the problem of curse of dimensionality and slow learning speed in the incipient stage of learning. In order to solve the problems of Q-learning, new function approximation methods suitable for reinforcement learning should be studied. In this paper, to improve these problems, we suggest Fuzzy Q-Map algorithm that is based on online fuzzy clustering. Fuzzy Q-Map is a function approximation method suitable to reinforcement learning that can do on-line teaming and express uncertainty of environment. We made an experiment on the mountain car problem with fuzzy Q-Map, and its results show that learning speed is accelerated in the incipient stage of learning.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.43 no.6
• /
• pp.991-1000
• /
• 1994

To control nonlinear systems adaptively, we improve learning speed of neural networks and present a novel control algorithm characterized by compensation of control inputs. In an error-backpropagation algorithm for tranining multilayer neural networks(MLNN's) the effect of the slope of activation functions on learning performance is investigated and the learning speed of neural networks is improved by auto-adjusting the slope of activation functions. The control system is composed of two MLNN's, one for control and the other for identification, with the weights initialized by off-line training. The control algoritm is modified by a control strategy which compensates the control error induced by the indentification error. Computer simulations show that the proposed control algorithm is efficient in controlling a nonlinear system with abruptly changing parameters.

• Journal of information and communication convergence engineering
• /
• v.2 no.1
• /
• pp.36-39
• /
• 2004

In this paper, a method of improving the learning speed and convergence rate is proposed to exploit the advantages of artificial neural networks and neuro-fuzzy systems. This method is applied to the XOR problem, n bit parity problem, which is used as the benchmark in the field of pattern recognition. The method is also applied to the recognition of digital image for practical image application. As a result of experiment, it does not always guarantee convergence. However, the network showed considerable improvement in learning time and has a high convergence rate. The proposed network can be extended to any number of layers. When we consider only the case of the single layer, the networks had the capability of high speed during the learning process and rapid processing on huge images.

• Journal of Institute of Control, Robotics and Systems
• /
• v.10 no.1
• /
• pp.42-46
• /
• 2004

A 2-mass resonant system is one that has a flexible coupling between a load and a driving motor. Due to this flexibility, the system often suffers vibration especially when the motor is controlled for higher speed command. In order to suppress such a vibration, an iterative learning control is applied to the 2-mass resonant system in this paper. The motor speed is controlled according to the relation with the load speed. The desired speed trajectories are derived under the condition for no vibration. The simulation result suggests that the proposed method effectively suppresses the vibration even when there exist model uncertainties.

• ETRI Journal
• /
• v.17 no.1
• /
• pp.11-22
• /
• 1995

This paper proposes a modified error function to improve the error back-propagation (EBP) algorithm for multi-Layer perceptrons (MLPs) which suffers from slow learning speed. It can also suppress over-specialization for training patterns that occurs in an algorithm based on a cross-entropy cost function which markedly reduces learning time. In the similar way as the cross-entropy function, our new function accelerates the learning speed of the EBP algorithm by allowing the output node of the MLP to generate a strong error signal when the output node is far from the desired value. Moreover, it prevents the overspecialization of learning for training patterns by letting the output node, whose value is close to the desired value, generate a weak error signal. In a simulation study to classify handwritten digits in the CEDAR [1] database, the proposed method attained 100% correct classification for the training patterns after only 50 sweeps of learning, while the original EBP attained only 98.8% after 500 sweeps. Also, our method shows mean-squared error of 0.627 for the test patterns, which is superior to the error 0.667 in the cross-entropy method. These results demonstrate that our new method excels others in learning speed as well as in generalization.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.6
• /
• pp.693-698
• /
• 2004

In this paper, an iterative learning control method is applied to suppress a vibration of a 2-mass system which has a flexible coupling between a load and a motor. More specifically, conditions for the load speed without vibration are derived based on the steady-state condition. And the desired motor position trajectory is synthesized based on the relation between the load and motor speed. Finally, a PD-type iterative learning control law is applied for the desired motor position trajectory. Since the learning law applied for the desired trajectory guarantees the perfect tracking performance, the resulting load speed shows no vibration even when there exist model uncertainties. A modification to the learning law is also Presented to suppress undesired effects of an initial position error, The simulation results show the effectiveness of the proposed learning method.

• Journal of Korea Game Society
• /
• v.10 no.1
• /
• pp.105-113
• /
• 2010

It takes quite amount of time to study a board game because there are many game characters and different stages are exist for board games. Also, the opponent is not just a single character that means it is not one on one game, but group vs. group. That is why strategy is needed, and therefore applying optimum learning is a must. If there were equal result that both are considered to be best ones during the course of learning stage, Heuristic which utilizes learning of problem area of Jul-Gonu was used to improve the speed of learning. To compare a normal character to an improved one, a jul-gonu game was created, and then they fought against each other. Improved character considered distance and attacked other one. As a result, improved character's ability was improved on learning speed.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.1
• /
• pp.41-49
• /
• 2022

This paper proposes a novel lane detection algorithm based on inverse perspective transformation and machine learning in lightweight embedded system. The inverse perspective transformation method is presented for obtaining a bird's-eye view of the scene from a perspective image to remove perspective effects. This method requires only the internal and external parameters of the camera without a homography matrix with 8 degrees of freedom (DoF) that maps the points in one image to the corresponding points in the other image. To improve the accuracy and speed of lane detection in complex road environments, machine learning algorithm that has passed the first classifier is used. Before using machine learning, we apply a meaningful first classifier to the lane detection to improve the detection speed. The first classifier is applied in the bird's-eye view image to determine lane regions. A lane region passed the first classifier is detected more accurately through machine learning. The system has been tested through the driving video of the vehicle in embedded system. The experimental results show that the proposed method works well in various road environments and meet the real-time requirements. As a result, its lane detection speed is about 3.85 times faster than edge-based lane detection, and its detection accuracy is better than edge-based lane detection.

• Journal of The Korean Association For Science Education
• /
• v.15 no.2
• /
• pp.164-172
• /
• 1995

In this study, the researcher tried to find out the effect of using a computer interface in teaching speed concept in the elementary school. The 4th and 5th pupils were sampled for this study. The school is located in a sub-urban agricultural area in Korea. In the study, the subjects were divided into two groups: experimental and comparison group. From the pretest, two groups did not show any difference in the understanding of speed concept. The computer interface and the programs to operate the interface and data analysis were developed by researcher. The interface is a modular type and designed ready to connect to microcomputer. The test items were consisted of (1) comparison of speed, (2) change of motion, (3) acceleration, and (4) deceleration. As the result, the researcher found the following results: 1. In case of speed comparison, no significant difference was found between experimental and comparison group. 2. In case of change of motion, acceleration, and deceleration, the experimental groups showed higher achievement both in 4th grade and 5th grade. However, the 4th graders showed more learning than the 5th graders. In conclusion, this study showed that the use of computer interface seemed to be very effective in teaching and learning speed concept in elementary school.