• 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.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.993-996
• /
• 1993

This paper addresses the structure and its associated learning algorithms of a feedforward multi-layered connectionist network, which has distributed learning abilities, for realizing the basic elements and functions of a traditional fuzzy logic controller. The proposed neural-network-based fuzzy logic control system (NN-FLCS) can be contrasted with the traditional fuzzy logic control system in their network structure and learning ability. An on-line supervised structure/parameter learning algorithm dynamic learning algorithm can find proper fuzzy logic rules, membership functions, and the size of output fuzzy partitions simultaneously. Next, a Reinforcement Neural-Network-Based Fuzzy Logic Control System (RNN-FLCS) is proposed which consists of two closely integrated Neural-Network-Based Fuzzy Logic Controllers (NN-FLCS) for solving various reinforcement learning problems in fuzzy logic systems. One NN-FLC functions as a fuzzy predictor and the other as a fuzzy controller. As ociated with the proposed RNN-FLCS is the reinforcement structure/parameter learning algorithm which dynamically determines the proper network size, connections, and parameters of the RNN-FLCS through an external reinforcement signal. Furthermore, learning can proceed even in the period without any external reinforcement feedback.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2000.03b
• /
• pp.101-108
• /
• 2000

In this study, an expert system was developed to predict the safety of tunnel and choose proper tunnel reinforcement system using fuzzy quantification theory and fuzzy inference rule based on tunnel information database. The expert system developed in this study have two main parts named pre-module and post-module. Pre-module decides tunnel information imput items based on the tunnel face mapping information which can be easily obtained in-situ site. Then, using fuzzy quantification theory II, fuzzy membership function is composed and tunnel safety level is inferred through this membership function. The comparison result between the predicted reinforcement system level and measured ones was very similar. In-situ data were obtained in three tunnel sites including subway tunnel under Han river, This system will be very helpful to make the most of in-situ data and suggest proper applicability of tunnel reinforcement system developing more resonable tunnel support method from dependance of some experienced experts for the absent of guide.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.11a
• /
• pp.120-123
• /
• 1997

In this paper, we propose the Fuzzy Inference-based Reinforcement Learning Algorithm. We offer more similar learning scheme to the psychological learning of the higher animal's including human, by using Fuzzy Inference in Reinforcement Learning. The proposed method follows the way linguistic and conceptional expression have an effect on human's behavior by reasoning reinforcement based on fuzzy rule. The intervals of fuzzy membership functions are found optimally by genetic algorithms. And using Recurrent state is considered to make an action in dynamical environment. We show the validity of the proposed learning algorithm by applying to the inverted pendulum control problem.

• Journal of the Korean Geotechnical Society
• /
• v.16 no.6
• /
• pp.127-139
• /
• 2000

In the study, an expert system was developed to predict the safety of tunnel and select proper tunnel reinforcement system using fuzzy quantification theory and fuzzy inference rule based on tunnel information database, For this development, many tunnelling sites were investigated and the applied countermeasures were studied after building tunnel database. There will be benefit for the deciding tunnel reinforcement method in the case of poor ground condition. The expert system developed in the study has two main parts, pre-module and post-module. Pre-module is used to decide input items of tunnel information based on the tunnel face mapping information which can be easily obtained in in-situ site. Then, using fuzzy quantification theory II, fuzzy membership function is composed and tunnel safety level is inferred through this membership function. Post-module is used to infer the applicability of each reinforcement methods according to the face level. The result of the predicted reinforcement system level was similar to measured ones. In-situ data were obtained in three tunnel sites including subway tunnel under Han River. Therefore, this system will be helpful to make the mose of in-situ data available and suggest proper applicability of tunnel reinforcement system to development more resonable tunnel support method without dependance of some experienced experts opinions.

• Proceedings of the IEEK Conference
• /
• 2000.07b
• /
• pp.677-680
• /
• 2000

The technique of reinforcement learning algorithm is extended to solve the multiobjective control problem for uncertain dynamic systems. A multiobjective adaptive critic structure is proposed in order to realize a max-min method in the reinforcement learning process. Also, the proposed reinforcement learning technique is applied to a multiobjective satisfactory fuzzy logic controller design in which fuzzy logic subcontrollers are assumed to be derived from human experts. Some simulation results are given in order to show effectiveness of the proposed method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.5
• /
• pp.395-400
• /
• 2000

In this paper, we propose a new neuro-fuzzy controller based on reinforcement learning. The proposed system is composed of neuro-fuzzy controller which decides the behaviors of an agent, and dynamic recurrent neural networks(DRNNs) which criticise the result of the behaviors. Neuro-fuzzy controller is learned by reinforcement learning. Also, DRNNs are evolved by genetic algorithms and make internal reinforcement signal based on external reinforcement signal from environments and internal states. This output(internal reinforcement signal) is used as a teaching signal of neuro-fuzzy controller and keeps the controller on learning. The proposed system will be applied to controller optimization and adaptation with unknown environment. In order to verifY the effectiveness of the proposed system, it is applied to collision avoidance of an autonomous mobile robot on computer simulation.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.96.3-96
• /
• 2001

In this paper the self-organized and fuzzy inference used stochastic gradient ascent method is proposed. Fuzzy rule and fuzzy set increase as occasion demands autonomously according to the observation information. And two rules(or two fuzzy sets)becoming to be similar each other as progress of learning are unified. This unification causes the reduction of a number of parameters and learning time. Using fuzzy inference and making a rule with an appropriate state division, our proposed method makes it possible to construct a robust reinforcement learning system.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.245-248
• /
• 2000

In this paper we improve the performance of autonomous mobile robot by induction of reinforcement learning concept. Generally, the system used in this paper is divided into two part. Namely, one is neural-fuzzy and the other is dynamic recurrent neural networks. Neural-fuzzy determines the next action of robot. Also, the neural-fuzzy is determined to optimal action internal reinforcement from dynamic recurrent neural network. Dynamic recurrent neural network evaluated to determine action of neural-fuzzy by external reinforcement signal from environment, Besides, dynamic recurrent neural network weight determined to internal reinforcement signal value is evolved by genetic algorithms. The architecture of propose system is applied to the computer simulations on controlling autonomous mobile robot.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2006.05a
• /
• pp.1235-1239
• /
• 2006

Fractal manufacturing system (FrMS) distinguishes itself from other manufacturing systems by the fact that there is a fractal repeated at every scale. A fractal is a volatile organization which consists of goal-oriented agents referred to as AIR-units (autonomous and intelligent resource units). AIR-units unrestrictedly reconfigure fractals in accordance with their own goals. Their goals can be dynamically changed along with the environmental status. Since goals of AIR-units are represented as fuzzy models, an AIR-unit itself is a fuzzy logic controller. This paper presents a goal regulation mechanism in the FrMS. In particular, a reinforcement learning method is adopted as a regulating mechanism of the fuzzy goal model, which uses only weak reinforcement signal. Goal regulation is achieved by building a feedforward neural network to estimate compatibility level of current goals, which can then adaptively improve compatibility by using the gradient descent method. Goal-oriented features of AIR-units are also presented.