• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.164.1-164
• /
• 2001

Q-learning is a recent reinforcement learning algorithm that does not need a modeling of environment and it is a suitable approach to learn behaviors for autonomous agents. But when it is applied to multi-agent learning with many I/O states, it is usually too complex and slow. To overcome this problem in the multi-agent learning system, we propose the successive Q-learning algorithm. Successive Q-learning algorithm divides state-action pairs, which agents can have, into several Q-functions, so it can reduce complexity and calculation amounts. This algorithm is suitable for multi-agent learning in a dynamically changing environment. The proposed successive Q-learning algorithm is applied to the prey-predator problem with the one-prey and two-predators, and its effectiveness is verified from the efficient avoidance ability of the prey agent.

• Journal of Korean Institute of Industrial Engineers
• /
• v.41 no.6
• /
• pp.588-598
• /
• 2015

In this paper, a simulation model for assessing the impact of alternative field service engineer replenishment policies is introduced. The end-to-end supply chain simulation model is created using a discrete-event and agent-based simulation model, which enables accurate description of key individual entities in the investigated supply chain, such as field service engineers. Once the model is validated with the historical data, it is used to assess the impacts of field service engineer replenishment policies for a major printing equipment manufacturing firm.In the case study, newly proposed replenishment policies for post-sale distribution supply chain are assessed for the level of service improvement to end customers.

• Trans-
• /
• v.14
• /
• pp.65-92
• /
• 2023

The knowledge of the narrative agent not only constitutes the content and meaning of the narrative itself, but is also closely related to the emotional response of the recipient. Also, the disparity of knowledge between narrative agents is an important factor in making a narrative richer and more interesting. But It tends to be treated as a sub-topic of narration theory or genre/style studies rather than an independent subject of narrative studies or criticism. In this paper, I propose a model that can systematically and quantitatively analyze the knowledge of narrative agents. The proposed model consists of the knowledge structure that represents a narrative, the knowledge state that expresses the knowledge of narrative agent as a degree of belief, and the knowledge flow that means changes in the knowledge state according to the development of events. In addition, the formal notation of the knowledge structure and a probabilistic inference model that could obtain the state of knowledge were proposed, and the knowledge structure and knowledge flow were analyzed by applying the model to the actual narrative. It is expected that the proposed model will be of practical help in the creation and evaluation of narratives.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10a
• /
• pp.343-345
• /
• 2000

기존의 객체지향, 구조적 방법적인 패러다임에서의 접근은 본질적으로 Goal 중심의 에이전트 시스템의 특성과 성질을 적절히 반영하기 어렵다. 그러므로 패러다임의 이동을 기하여 에이전트 시스템의 분석 관점을 Goal에 맞추고, Goal을 달성하려는 에이전트를 모델링해야 한다. 본 논문에서는 에이전트 기반의 소프트웨어를 효율적으로 분석하기 위하여 문제영역을 Goal의 측면에서 분석하고, Agent 선택 규칙으로 에이전트를 추출하여, 사용자의 요구사항을 달성하기 위한 에이전트들을 모델링하는 방법을 제안한다.

• Journal of KIISE:Software and Applications
• /
• v.36 no.3
• /
• pp.200-207
• /
• 2009

U-Healthcare is more efficient as a solving method for health problems rather than visiting the hospital. Recently, systems have been studied to offer appropriate service to user, which gather and analyze biological signals of a user and context information around the user from a variety of sensors. The existing systems for U-Healthcare are based on domain specific service so it is difficult to expand and link to other systems. Also, they lack services focusing on the specific quality of the user, because they offer a general service which targets a lot of users. To address this problem, we expand an extensibility of system using the context-awareness agent based on multi-agents. Also, we provide the suitable services which match with the context information of user to each user using the modeling toolkit JaUCE based on GUI. We design and implement U-Silvercare service to demonstrate the effectiveness of the proposed context-awareness agent and modeling toolkit.

• Journal of KIISE:Computing Practices and Letters
• /
• v.10 no.1
• /
• pp.89-98
• /
• 2004

Conversational agent is a system that provides users with proper information and maintains the context of dialogue on the natural language. Analyzing and modeling process of user's query is essential to make it more realistic, for which Bayesian network is a promising technique. When experts design the network for a domain, the network is usually very complicated and is hard to be understood. The separation of variables in the domain reduces the size of networks and makes it easy to design the conversational agent. Composing Bayesian network as two stages, we aim to design conversational agent easily and analyze user's query in detail. Also, previous information of dialogue makes it possible to maintain the context of conversation. Actually implementing it for a guide of web pages, we can confirm the usefulness of the proposed architecture for conversational agent.

• Journal of the Korea Society for Simulation
• /
• v.27 no.2
• /
• pp.101-114
• /
• 2018

Several different approaches and mechanisms are introduced to solve the UAV path planning problem. In this paper, we designed and implemented an agent-based simulation software using the Repast platform and Java Genetic Algorithm Package to examine an evolutionary path planning method by implementing and testing within the Repast environment. The paper demonstrates the life-cycle of an agent-based simulation software engineering project while providing a documentation strategy that allows specifying autonomous, adaptive, and interactive software entities in a Multi-Agent System. The study demonstrates how evolutionary path planning can be introduced to improve cognitive agent capabilities within an agent-based simulation environment.

• Proceedings of the Korea Society for Simulation Conference
• /
• 2001.10a
• /
• pp.9-10
• /
• 2001

Simulation has been evolved with the advance of computer and technique of modeling application systems. Early simulations were numerical analysis of engineering models known as continuous simulation, analysis of random events using various random number generators thus named as Monte Carlo simulation, iud analysis o(\\\\`queues which are prevalent in many real world systems including manufacturing, transportation, telecommunication. Discrete-event simulation has been used far modeling and analyzing the systems with waiting lines and inefficient delays. These simulations, either discrete-event, continuous, or hybrid, have played a key role in industrial age by helping to design and implement the efficient real world systems. In the information age which has been brought up by the advent of Internet, e-business has emerged. E-business, any business using Internet, can be characterized by the network of extended enterprises---extended supply and demand chains. The extension of value chains spans far reaching scope in business functions and space globally. It also extends to the individual customer, customer preferences and behaviors, to find the best service and product fit for each individual---mass customization. Simulation should also play a key role in analyzing and evaluating the various phenomena of e-business where the phenomena can be characterized by dynamics, uncertainty, and complexity. In this tutorial, applications of simulation to e-business phenomena will be explained and illustrated. Examples are the dynamics of new economy, analysis of e-business processes, virtual manufacturing system, digital divide phenomena, etc. Partly influenced by e-business, a new trend of simulation has emerged called agent-based simulation, Agent-based simulation is a technique of simulation using software agent that have autonomy and proactivity which are useful in analyzing and integrating numerous individual customer's behavior. One particular form of agent-based simulation is swarm. This tutorial concludes with the illustration of swarm or swarm Intelligence applied to various e-business applications, and future directions and implications of this new trend of simulation.

• The Journal of Society for e-Business Studies
• /
• v.14 no.4
• /
• pp.133-148
• /
• 2009

This study has tried to suggest a new model that can effectively redistribute the tickets in the online ticket resale market, while suggesting a new allocation mechanism based on an agent negotiation. To this end, this study has analyzed an auction in the online ticket resale market through Game theory. As a result of new agent mechanism, it has been proved that the price stability of ticket resale market leads to an increase. An agent negotiation helps to stabilize the ticket prices that are usually inclined to rise at auction, benefiting all the participants in the negotiations, consequently showing a Pareto solution. Especially, a framework for a negotiation process is suggested and domain and processes ontology are designed interrelatedly. With this modeling, a possibility of Ontology based agent negotiation is suggested.

• The Journal of Society for e-Business Studies
• /
• v.4 no.1
• /
• pp.145-157
• /
• 1999

The challenge is to maximize the time-to-market benefits of concurrent engineering while maintaining control of data and distributing it automatically to the people who need it when they need it. The way PDM systems cope with this challenge is that master data is held only once in a secure vault where its integrity can be assured and all changes to it monitored, controlled and recorded. The structure of PDM is various from vendor, but they have common module. That is PDM and it is most important. The goal is to design the workflow in PDM using object-oriented modeling method. The past methods have concentrated on the flow between workflow engine and agent, but this paper will focus on task. We will model task as individual object. This paper uses OMT(Object Modeling Technique) by James Rumbaugh for base modeling tool and uses DCOM(Distributed Component Object Model) for base ORB(Object Request Broker). Research object is to design the static object model, to design state change by dynamic model and to design data transition by functional model.