• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• pp.59-64
• /
• 2001

The robot soccer simulation game is a dynamic multi-agent environment. In this paper we suggest a new reinforcement learning approach to each agent's dynamic positioning in such dynamic environment. Reinforcement learning is the machine learning in which an agent learns from indirect, delayed reward an optimal policy to chose sequences of actions that produce the greatest cumulative reward. Therefore the reinforcement learning is different from supervised learning in the sense that there is no presentation of input pairs as training examples. Furthermore, model-free reinforcement learning algorithms like Q-learning do not require defining or learning any models of the surrounding environment. Nevertheless it can learn the optimal policy if the agent can visit every state- action pair infinitely. However, the biggest problem of monolithic reinforcement learning is that its straightforward applications do not successfully scale up to more complex environments due to the intractable large space of states. In order to address this problem. we suggest Adaptive Mediation-based Modular Q-Learning (AMMQL)as an improvement of the existing Modular Q-Learning (MQL). While simple modular Q-learning combines the results from each learning module in a fixed way, AMMQL combines them in a more flexible way by assigning different weight to each module according to its contribution to rewards. Therefore in addition to resolving the problem of large state effectively, AMMQL can show higher adaptability to environmental changes than pure MQL. This paper introduces the concept of AMMQL and presents details of its application into dynamic positioning of robot soccer agents.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1997.10a
• /
• pp.68-70
• /
• 1997

본 연구의 목적은 정보산업의 발달로 급변하고 있는 교육환경하에서 인트라넷(intranet)을 활용한 경영모의게임(Business Simulation Game)의 활용방안을 제시하고, 이러한 수업이 갖는 장점 및 수업효과에 미치는 영향을 조사하였다. 즉, 학생들이 팀을 이루어 게임을 하는데 있어 남녀별, 직장경험별, MBTI의 특성 별, 팀 구성원의 수의 차이에 따른 게임 성과 및 수업효과와의 상호관계를 실증적으로 비교, 연구하여, 궁극적으로는 한국교육실정에 맞는 인트라넷을 이용한 경영 모의 게임의 개발을 그 목적으로 하고 있다. 근래에 정보 및 통신기술의 발전과 인터넷 사용의 보편화로 여러 가지 학문 분야에서 정보화 및 국제화가 많이 이루어져왔다. 특히 인터넷과 관련된 여러 가지 기술(technology)들을 적극적으로 통합, 활용하고자 하는 인트라넷(intranet)의 발전은 정보기술의 여러 학문 분야에서의 활용가능성을 더욱 높이고 있는 실정이다. 그러나 이러한 인터넷, 정보 및 통신기술의 교육현장에서의 활용 방안에 대한 많은 연구들은 실질적으로 그 이론적 배경 및 효과에 대한 깊은 연구없이 종래의 교육방법에 대한 대안 또는 보조 역할로서의 가능성만 제시하고 있는 형편이다. 따라서 본 연구는 첫째, 경영모의게임과 정보통신기술의 활용을 위한 학술진흥방안의 하나로서 인트라넷을 이용한 경영모의게임 과목의 구축및 수행에 관한 구체적인 절차를 제시한다. 즉 경영모의게임 구성은 어떤 모듈들이 어떻게 인터넷상에서 사용되었으며, 도한 게임의 운영은 어떻게 하는것이 바람직한가 등에 관한 연구이다. 둘째, 성별, 직장경험별, MBTI 특성별, 팀의 크기별로 게임성과 및 수업효과에 관한 실증적 연구를 함으로써, 게임 이론의 경영마인드 형성 및 정보화에서 예견 될수 있는 여러 가지 문제점 및 가능성을 지적하여, 한국문화 및 현실에 맞는 정보화를 이용한 경영모의게임 교육방안을 제시한다. 셋째, 본 연구는 의사결정지원 시스템(DSS), 전문가 시스템(ES), 전자우편(E-mail)등과 같은 정보기술의 교육현장에서의 활용방안 및 그 교육적 효과도 점검하였으며, 마지막으로 본 연구는 당면현실로 다가온 정보화 및 세계화의 기업환경에서 예견되는 몰입(committment)의 약화에 대한 치유방안으로서, 정보화된 경영모의게임의 기업 교육훈련 시스템(Business Training System)으로의 발전 가능성을 제시한다 하겠다.

• Journal of Korea Game Society
• /
• v.15 no.5
• /
• pp.131-142
• /
• 2015

A self-driving car is an autonomous vehicle capable of fulfilling the main transportation capabilities of a traditional car. It must be capable of sensing its environment and navigating without human input. In this paper, we design the agent that can simulate these self-driving cars and develop a prototype for it. To do this, we analyze the requirements for the self-driving car, and then the agent is designed to be suitable for traditional multi-agent system. The key point of the design is that agents move along the steering forces only. The prototype of the designed agent was implemented by using Unity 3D. From simulation results using the prototype, movements of the agents were very realistic. However, in the case of increasing the number of the agent the performance was seriously degraded, and so the alternatives of the problem were suggested.

• Journal of the Korea Society for Simulation
• /
• v.17 no.4
• /
• pp.159-165
• /
• 2008

The ROK army has equipped ATCIS (Army Tactical Control Information System) for the Corps echelon to visualize the battlefield and reduce the reaction time. Due to the information&surveillance equipment, uncertainty and variance of the battlefield have been decreased. However decision making for the ground operations has not changed as it depends on knowledge of the commander and staffs. The War game process to select and assess the best CoA (Course of Action) also depends on the pros and cons due to the limitation of time and capability. For the balanced development between intangible and tangible military strength, a new decision making process which is quantitative and useful for the military is needed. In this study, we suggest a Fuzzy-AHP based decision making model to improve troop leading procedure which is useful to evaluate and reflect intangible characteristics of the battlefield.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.4
• /
• pp.91-99
• /
• 2014

The main game architectures for multiplayer online games are the traditional client-server architectures, multi-server architectures and P2P(peer-to-peer) architectures. P2P architectures, due to their distributed and collaborative nature, have low infrastructure costs and can achieve high scalability as well as fast response time by creating direct connections between players. However, P2P architectures face many challenges. Distributing a game among peers makes maintaining control over the game more complex. These architectures also tend to be vulnerable to churn and cheating. Providing consistency control in P2P systems is also more difficult since conflicting updates might be executed at different sites resulting in inconsistency. In order to avoid or correct inconsistencies, most multiplayer games use a primary-copy replication approach where any update to the object has to be first performed on the primary copy. This paper presents the primary-copy model with the update dissemination mechanism that provides consistency control over an object in P2P architectures for multiplayer online games. The performance for this model is evaluated through simulation experiments and analysis.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.626-632
• /
• 2009

An Edutainment Contents help the learners to recognize the problems effectively, grasp and classify important information needed to solve the problems and convey the contents of what they have learned. Owing not only to this game-like fun but also to the educational effect, The Edutainment contents can be usefully applied to education and training in the areas of scientific technology and industrial technology. This study proposes the Edutainment that users can apply to biotechnology by using intuitive multi-modal interfaces. In this study, a stereoscopic monitor is used to make three dimensional molecular structures, and multi-modal interface is used to efficiently control. Based on the system, this study easily solved the docking simulation function, which is one of the important experiments, by applying these game factors. For this, we suggested the level-up concept as a game factor that depends on numbers of objects and users.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.59-65
• /
• 2009

An Edutainment Contents help the learners to recognize the problems effectively, grasp and classify important information needed to solve the problems and convey the contents of what they have learned. Owing not only to this game-like fun but also to the educational effect, The Edutainment contents can be usefully applied to education and training in the areas of scientific technology and industrial technology. This study proposes the Edutainment that users can apply to biotechnology by using intuitive multi-modal interfaces. In this study, a stereoscopic monitor is used to make three dimensional molecular structures, and multi-modal interface is used to efficiently control. Based on the system, this study easily solved the docking simulation function, which is one of the important experiments, by applying these game factors. For this, we suggested the level-up concept as a game factor that depends on numbers of objects and users.

• Journal of Satellite, Information and Communications
• /
• v.10 no.1
• /
• pp.49-55
• /
• 2015

In cognitive radio network (CRN), spectrum sensing is an elementary level of technology for non-interfering to licensed user. Required sample number for spectrum sensing is directly related to the throughput of secondary user and makes the tradeoff between the throughput of secondary user and interference to primary user. Required spectrum sensing sample is derived from required false alarm, detection probability and minimum required SNR of primary user (PU). If we make clustering and minimize the required transmission boundary of secondary user (SU), we can relax the required PU SNR for spectrum sensing because the required SNR for PU signal sensing is related to transmission range of SU. Therefore we can achieve efficient throughput of CRN by minimizing spectrum sensing sample. For this, we design the tradeoff between gain and loss could be obtained from clustering, according to the size of cluster members through game theory and simulation results confirm the effectiveness of the proposed method.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.1
• /
• pp.3-8
• /
• 2013

In this paper, we present an energy-efficient base station operation with base station sharing in wireless cellular networks. Firstly, cost functions are modeled related with the amount of energy usage and traffic load. We use game theory and formulate an energy bill game, where the players are the service operators which are operating base stations and their strategies are the bill of their base station energy consumption and hand-over traffic load to the others service operators. We show that the global optimal performance in terms of minimizing the energy costs is achieved at the Nash equilibrium of the formulated energy bill game. Simulation results confirm that the proposed approach can reduce the energy bill of the service operator, and show the relationship between the energy cost saving and various parameters.

• Journal of Internet Computing and Services
• /
• v.18 no.2
• /
• pp.43-51
• /
• 2017

As the game industry is blooming, the generation of contents is far behind the consumption of contents. With this reason, it is necessary to afford the game contents considering level of game player's skill. In order to effectively solve this problem, Procedural Content Generation(PCG) using Artificial Intelligence(AI) is one of the plausible options. This paper proposes the procedural method to generate various monsters considering level of player's skill using genetic algorithm. One gene consists of the properties of a monster and one genome consists of genes for various monsters. A generated monster is evaluated by battle simulation with a player and then goes through selection and crossover steps. Using our proposed scheme, players adaptive monsters are generated procedurally based on genetic algorithm and the variety of monsters which are generated with different number of genome is compared.