• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1187-1194
• /
• 2019

This paper proposes a CNN architecture as value function network of an artificial intelligence Othello game agent and its learning scheme using reinforcement learning algorithm. We propose an approach to construct the value function network by using CNN to learn the records of professional players' real game and an approach to enhance the network parameter by learning from self-play using reinforcement learning algorithm. The performance of value function network CNN was compared with existing ANN by letting two agents using each network to play games each other. As a result, the winning rate of the CNN agent was 69.7% and 72.1% as black and white, respectively. In addition, as a result of applying the reinforcement learning, the performance of the agent was improved by showing 100% and 78% winning rate, respectively, compared with the network-based agent without the reinforcement learning.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.2
• /
• pp.61-66
• /
• 2024

This paper aims to design a simulation for path-finding of objects in a simulation or game environment using reinforcement learning techniques. The main feature of this study is that the objects in the simulation are trained to avoid obstacles at random locations generated on a given track and to automatically explore path to get items. To implement the simulation, ML Agents provided by Unity Game Engine were used, and a learning policy based on PPO (Proximal Policy Optimization) was established to form a reinforcement learning environment. Through the reinforcement learning-based simulation designed in this study, we were able to confirm that the object moves on the track by avoiding obstacles and exploring path to acquire items as it learns, by analyzing the simulation results and learning result graph.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.170-171
• /
• 2013

In aspect of HCI(Human Computer Interaction) gameplay is the procedure to solve the problem that gamers encounter in order to generate or discover a new rule to achieve gamers' goal. The goal of this research is to investigate the structure and understand the gameplay in aspect of affordance from ecological psychology rather than the traditional problem solving theory. This research selects 'World of Warcraft' as MMORPG(Massively Multiplayer Online Role Playing Game). Five expert gamers participated in this experiment. We record all gameplay using audio and video device. We conducted protocol analysis as qualitative method based on the verbal report and action protocol during game playing. As result, gameplay based on affordance includes selection and relation. We found that subjects selected one thing at once with attention. Moreover, we found that there were two behaviors : exploratory action and performatory action. We believe that learning, utilization, and transformation for affordance appear. The result of this research imply to suggest design guideline for game design methodology when designers develop game.

• Journal of The Korean Association of Information Education
• /
• v.18 no.3
• /
• pp.453-460
• /
• 2014

In this study, we develop a teaching and learning model for elementary students on game programming using KODU. The developed model consists of four steps: introducing the game programming, making the game, playing the game, and modifying the game. After teaching the students, we conduct a survey to gather their opinions on the game making tool and activities. The results show that the students are satisfied with KODU and prefer make a game to play a game. Game programming educating with KODU can keep elementary students from game addiction while increasing confidence in their studies.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2015.07a
• /
• pp.37-38
• /
• 2015

본 논문에서는 XNA Framework 기반의 모바일 게임 History Adventure를 설계하고 구현한다. 이 모바일 게임은 영웅별 3개의 스테이지 구성되어 있으며 각 단계별로 각 나라를 대표를 하는 영웅들과 전쟁의 발발 원인에 대한 퀴즈 풀이를 진행한다. 이때 정답을 선택하면 HP를 공급하고 실패하면 정답을 알려줌으로써 게임과 학습을 함께 할 수 있다. 영웅들이 적을 격파하지 못하고 적선이 통과를 하게 된다면 HP(Hit Point)는 감소하고, 적선을 격퇴하면 난이도가 높은 스테이지로 이동한다. 게임중에 일정 점수를 획득하면 보너스 코인과 HP를 지급한다. 지급받은 코인 및 HP는 현재 스테이지를 수행하고 다음 스테이지로 이동해도 유효하다. 적의 보스를 처리할시 실제 전쟁의 결과를 알려주면서 다음 단계로 이동한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2012.07a
• /
• pp.361-362
• /
• 2012

대학의 게임 개발 프로젝트 교육을 수행함에 있어 개발 방법론을 적용하여 체계적인 단계를 거치도록 하는 것이 필요하나 기본의 소프트웨어 개발 방법론들은 복잡성과 기간 등의 제약으로 적용하기 어렵다. 애자일 방법론 중 하나인 스크럼은 주기적인 개발을 지원하고 있어 프로젝트 교육에 적합한 특성을 가지고 있다. 본 논문에서는 기존의 스크럼 방법론을 한 학기의 게임 개발프로젝트 교육에 적합하도록 최적화한 CK-Scrum 방법론을 제시한다. CK-Scrum 방법론을 적용할 경우 주기적으로 산출물을 생산하여 검토하고 반복적으로 개발함으로써 학생들이 프로젝트를 수행하며 품질이 높은 게임을 개발하고 방법론에 대한 학습도 병행할 수 있다.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.12a
• /
• pp.177-180
• /
• 2000

최근에 음성인식의 상용화가 급격히 추진되고 있다. 그러나 음성인식 응용제품의 부족과 음성인식 시스템의 성능문제로 인하여 일반인의 이용은 그다지 많지 않다. 본 논문에서는 연구실에서 만든 가변 어휘 음성인식기를 이용하여 음성인식 끝말 이어가기 게임을 구현하였다. 가변어휘 음성 인식기는 VCCV(Vowel＋consonant＋Consonant＋vowel) 기반의 화자독립으로 구현하였다. 끝말 이어가기 게임을 위해서 약 500만 어절이 포함된 문장에서 추출한 단어의 일부를 이용하여 사전을 구축하였고, 같은 음절로 시작하는 단어가 많은 경우에는 그 수를 제안하였다. 본 연구에서 구현한 음성인식 끝말 이어가기 게임은 제한된 단어사전을 이용하도록 하였으나 음성인식기의 성능향상과 완전한 사전구축이 이루어지면 음성인식을 이용한 언어 학습기나 게임 등의 개발과 이용의 활성화에 크게 기여할 것이라 생각된다.

• Journal of Korea Game Society
• /
• v.17 no.5
• /
• pp.133-142
• /
• 2017

Recently, screen climbing contents such as sports climbing learning program and screen climbing games. Especially, there are many researches on screen climbing games. In this paper, we propose the skeleton correction method based on the body area of a climber to improve the posture recognition accuracy. The correction method consists of the modified skeletal frame normalization with abnormal skeleton joint filtering, the classification of body area into joint parts, and the final skeleton joint correction. The skeletal information obtained by the proposed method can be used to compare the climber's posture and the ideal climbing posture.

• Journal of Digital Convergence
• /
• v.17 no.2
• /
• pp.381-387
• /
• 2019

Since the development of NCS-based curriculum in field of game education is not well studied, so we carried out research on the curriculum development of game contents department of Kimpo University as the first study to link game education and NCS. In order to develop the NCS-based game education course, we analyzed the game industry environment and conducted a demand survey on the game industry officials to derive the vocational basic subjects required for game contents creation. In addition, we analyzed the types of manpower training by using on-site experts (SME). SME also designed the NCS curriculum by matching the manpower type comparing with NCS classification and capacity unit, analyzing the usefulness of each Capacity unit, and finally, by arranging each NCS and non-NCS subjects by semester. This research is meaningful as the first study linking NCS and game content creation, and it will be a reference for other education institutions planning game education course based on NCS. It also can be used as a basic material for researching game education quality management (CQI) as well as improvement methods for future game education courses.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.3
• /
• pp.139-144
• /
• 2010

In this study, we have propose an english, math education program to the children of elementary school and Single Display Groupware (SDG) technique was applied to implement the program. By SDG-based program, learners will be performed at the same time learning cooperatively. Finally, we have implement a prototype of SDG system and take a usability test with elementary school children.