• Journal of the Korean earth science society
• /
• v.30 no.2
• /
• pp.257-264
• /
• 2009

The purpose of this study was to examine the effects of the game application learning 8th graders' scientific attitude, which was utilized as a strategy to improve the teaching skills and methods in the lesson of 'the history of the earth and diastrophism'. The subjects of this study were 120 students of 8th grade at a middle school located in a metropolitan city in Korea. To start off with homogeneity of a group, this study recruited participants by the results of a diagnostic test taken early in the year and a mid-term examination taken at the end of April. As a result, a total of 4 male classes that showed similar results on the two tests were selected and divided into two groups: one in experimental and the other in control. In addition, the top 20% students and the low 20% students were chosen for comparison of their scientific attitudes based on the results of the mid-term examination. The traditional teachings were offered to the control groups while the experimental lessons with the game activities performed at the stages of application and summary in teaching were offered to the experimental groups over 10 periods. Results of the pre- and post-test on the students' scientific attitude demonstrated that there was a statistical significance between the two groups, which suggested that the experimental group showed a meaningful improvement in the scientific attitude after experimental intervention lesson activities with game applications. Also, the more meaningful improvement in the scientific attitude was found in the lower group than in the higher group. It implies that lessons with the game activities motivated the students to voluntarily participate in school science learning by enhancing their interests. Therefore, it is suggested that game application learning be a new teaching-learning material that helps to encourage learners to actively participate in middle school science learning.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.4
• /
• pp.289-293
• /
• 2002

Learning Classifier System (LCS) finds a new rule set using genetic algorithm (GA). In this paper, The Zeroth Level Classifier System (ZCS) is applied to evolving the strategy of a robot soccer simulation game (SimuroSot), which is a state varying dynamical system changed over time, as GBML (Genetic Based Machine Learning) and we show the effectiveness of the proposed scheme through the simulation of robot soccer.

• Journal of the Institute of Electronics Engineers of Korea TE
• /
• v.39 no.1
• /
• pp.83-90
• /
• 2002

This paper proposed the strategy learning method by means of the fusion of Back-Propagation neural network and Q learning algorithm for two-person, deterministic janggi board game. The learning process is accomplished simply through the playing each other. The system consists of two parts of move generator and search kernel. The one consists of move generator generating the moves on the board, the other consists of back-propagation and Q learning plus $\alpha$$\beta$ search algorithm in an attempt to learn the evaluation function. while temporal difference learns the discrepancy between the adjacent rewards, Q learning acquires the optimal policies even when there is no prior knowledge of effects of its moves on the environment through the learning of the evaluation function for the augmented rewards. Depended on the evaluation function through lots of games through the learning procedure it proved that the percentage won is linearly proportional to the portion of learning in general.

• Journal of Convergence for Information Technology
• /
• v.11 no.3
• /
• pp.1-6
• /
• 2021

Most of the match-3 puzzle games supports automatic play using the MCTS algorithm. However, implementing reinforcement learning agents is not an easy job because it requires both the knowledge of machine learning and the way of complex interactions within the development environment. This study proposes a method in which we can easily design reinforcement learning agents and implement game play agents by applying PPO(Proximal Policy Optimization) algorithms. And we could identify the performance was increased about 44% than the conventional method. The tools we used are the Unity 3D game engine and Unity ML SDK. The experimental result shows that agents became to learn game rules and make better strategic decisions as experiments go on. On average, the puzzle gameplay agents implemented in this study played puzzle games better than normal people. It is expected that the designed agent could be used to speed up the game level design process.

• Digital Contents
• /
• no.12 s.127
• /
• pp.146-148
• /
• 2003

인터넷 입시 과외를 비롯 외국어학습, 대학 정규과정 등 각종 e-러닝(e-Learning) 학습 프로그램이 빠른 속도로 번지고 있다. 또한 기업 연수현장에도‘사이버 바람’이 거세게 불고 있다. 이런 배경에서 지난 10월 23일 정보통신부는 한국e-러닝학회, KDI국제정책대학원, 한국정보통신기자협회의 후원 아래‘한국 e-러닝 산업 활성화 전략 세미나’를 개최했다. 국내 e-러닝 비즈니스 관계자 182명이 참석한 이날 행사에는 e-러닝 산업현황 및 성공사례, 비즈니스 모델 등이 발표되고, 게임 및 모바일 관점에서의 서비스 동향도 소개돼 뜻깊은 자리가 됐다.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.1 s.45
• /
• pp.83-88
• /
• 2007

The goal of this research was to investigate the effect the computer game-based learning has on learning achievement in computer education for middle school students. To achieve this goal 74 middle schoolers were allocated into the experiment group(34 students) with the educational computer games class and the control group(34 students) with the traditional face-to-face class. After identifying the homogeneity of two groups through the pre-test, the experiment was carried out. As a result, the mean difference between the experiment group and the control group was statistically significant. That is, learning achievement of middle schoolers utilizing the computer games was higher than that of the face-to-face class. It is suggested that the game factors should be considered in designing the computer education.

• Annual Conference of KIPS
• /
• 2020.11a
• /
• pp.988-991
• /
• 2020

다양한 실세계 응용 분야들에서 공동의 목표를 위해 여러 에이전트들이 상호 유기적으로 협력할 수 있는 행동 정책을 배우는 것은 매우 중요하다. 이러한 다중 에이전트 강화 학습(MARL) 환경에서 기존의 연구들은 대부분 중앙-집중형 훈련과 분산형 실행(CTDE) 방식을 사실상 표준 프레임워크로 채택해왔다. 하지만 이러한 다중 에이전트 강화 학습 방식은 훈련 시간 동안에는 경험하지 못한 새로운 환경 변화가 실전 상황에서 끊임없이 발생할 수 있는 동적 환경에서는 효과적으로 대처하기 어렵다. 이러한 동적 환경에 효과적으로 대응하기 위해, 본 논문에서는 새로운 다중 에이전트 강화 학습 체계인 C-COMA를 제안한다. C-COMA는 에이전트들의 훈련 시간과 실행 시간을 따로 나누지 않고, 처음부터 실전 상황을 가정하고 지속적으로 에이전트들의 협력적 행동 정책을 학습해나가는 지속 학습 모델이다. 본 논문에서는 대표적인 실시간 전략게임인 StarcraftII를 토대로 동적 미니게임을 구현하고 이 환경을 이용한 다양한 실험들을 수행함으로써, 제안 모델인 C-COMA의 효과와 우수성을 입증한다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09b
• /
• pp.35-38
• /
• 2003

최근 컴퓨터 게임의 확산과 함께 보다 나은 가상환경 생성을 위한 기술에 대한 필요성이 증가하고 있다 다양한 환경에서 지능적으로 행동하는 인공 캐릭터의 설계를 위해 다양한 인공지능 기술이 적용되고 있다. 하지만 게임의 캐릭터 설계에 적용된 휴리스틱이나 규칙기반 시스템 등의 기존 인공지능 기술은 게임 개발자에 의존적이기 때문에 플레이어가 쉽게 캐릭터의 행동패턴을 파악하여 게임의 흥미를 저하시키는 단점이 있다 따라서 진화연산이나 신경망 등의 학습기반 인공지능 기술의 게임에의 적용이 모색되고 있다 특히 진화를 이용한 지능기술은 자연계의 복잡성과 의외성을 모방하여 최적화된 지능보다는 속임수/의외성 등의 창의적인 지능행동의 생성을 가능하게 하며 새로운 게임전략의 생성, 게임 캐릭터의 성격형성 및 다양한 행동 생성 등에 매우 유용하다. 본 논문에서는 진화기술의 게임에의 효과적인 적용을 위해 진화엔진을 설계 및 제작하고 인공지능 시뮬레이터에 적용하여 그 유용성을 확인하였다.

• Journal of Korea Game Society
• /
• v.21 no.4
• /
• pp.3-12
• /
• 2021

In this study, models for predicting the final result of League of Legends game were constructed for each rank using data from the first 10 minutes of the game. Variable importance was extracted from the prediction models to derive strategic direction in early phase of the game. As a result, it was possible to predict final results with over 70% accuracy in all ranks. It was found that early game advantage tends to lead to the final win and this tendency appeared stronger as it goes to challenger ranks. Kill(death) was found to be the most influential factor for win, however, there were also variables whose importance rank changed according to rank. This indicates there is a difference in the strategic direction in the early stage of the game depending on the rank.

• The Journal of the Korea Contents Association
• /
• v.7 no.9
• /
• pp.248-256
• /
• 2007

The purpose of this study is to design, develope, and deploy of online game content in middle school mathematics. This study analyzed related literature review, case studies, and educational game web sites for seeking better applicable design strategies. After serious discussion with experts based the design ideas, this study established its own educational game design model and it was applied to develop algebraic function lesson for middle school students. The developed content also was deployed in real classroom setting to see how students received the game contents and how. well they processed the design procedures and activities. We found that educational online game content, especially when applied to mathematics subject, can be effective in students interests and their motivations. We also observed that there were a few managerial errors such as need for detailed guidance for game, cumulative game results for later feedback, and so on. This study concluded that educational game contents should be able to widely spread out to get students' learning interests and strong motivation as well. We suggest that related research should be done toward to other subject than mathmatics and various students age groups.