• Journal of Korea Society of Digital Industry and Information Management
• /
• v.13 no.1
• /
• pp.1-12
• /
• 2017

Recently, the Go game has been performed between the 'AlphaGo' of the DeepMind and Lee Sedol, a famous professional Go-player of Korea, which leads to arise a lot of interests in the AI (Artificial Intelligence) research area. Based on the Fuzzy logic of the AI, we have also developed another game's AI, .i.e., the Yutnori game, one of Korean traditional board games. However, it is not easy and simple to consider all the cases of the Yutnori game since it is a non-perfect information game in terms of the AI. Thus, we have developed the Fuzzy-logic-based AI which tries to simulate humans' selections, meaning that the suggested AI has focused on the humans' choices depending on diverse situations in the Yutnori. With our extensive simulations using the suggested Yutnori AI, we have analyzed its performances with respect to 10 Yutnori situations among various scenarios. In conclusion, our suggested AI have demonstrated that 6 out of 10 situations are exactly same with the humans' choices and the rest 4 cases are also similar to that of human's, which reveals that our Fuzz-logic-based Yutnori AI can effectively simulate human's choices.

• Journal of Korea Game Society
• /
• v.8 no.3
• /
• pp.77-85
• /
• 2008

In the current online game field, many studies on the realization of AI have been carried out. It is, however, very hard to apply smart AI to the online games due to the limited use of resources. The Fuzzy extension method this thesis presents is suitable to online games because it causes less loads in the system and makes it possible to realize more human-like AI. To realize this kind of AI, this paper suggests AI system design methods suitable to fuzzy-based online game and presents practical plans to apply them through the produced demos.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2014.07a
• /
• pp.289-292
• /
• 2014

게임에서 AI(Artificial Intelligence)는 게임의 재미요소와 가장 밀접한 부분이며, 대부분의 게임에 포함되어 있다. 그러나 단순한 AI패턴은 게임플레이에 지속성을 저하시키며 게임의 재미요소 하락시키는 원인이 되기도 한다. 본 논문에서는 이러한 문제점을 극복하기 위해, 2D 횡 스크롤 액션 게임으로 "아트록스"를 개발하여 게임의 흥미를 높일 수 있는 AI패턴을 연구하였다.

• Journal of Korea Game Society
• /
• v.5 no.4
• /
• pp.23-32
• /
• 2005

This paper introduces environment analysis way to improve the game AI. The way of environment analysis can provide game user the more reality than generally used AI patterns. This paper suggests the way to make die NPC patterns variously. To realize this theory we designed the organization of NPC server newly, and also accomplished the experiment of NPC server simulation test to get the performance applied in real situation.

• Proceedings of the Korea Contents Association Conference
• /
• 2006.05a
• /
• pp.388-391
• /
• 2006

In the lately fews years, it take a growing interested in game AI and study zealously on game AI. In this paper, we research an usual individuality of NPC(Non-Player Character) on MMORPG(Massively Multiplayor Online Role Playing Game) and An AI technique on computer game. we study on a role and an individuality of NPC for take-up the game, moreover, we research on technique of game AI for take-up the game.

• Journal of Korea Game Society
• /
• v.17 no.4
• /
• pp.101-108
• /
• 2017

This study explores how Artificial Intelligence (AI), which is tremendously developed these days, applies to the game and advances. It analyzes the reality of AI and provides reasonable suggestion in Poker, one of the most popular games. Specifically, this study focuses on Texas Hold'em, the most favored kind in the world among various kinds of Poker games and deals with two AIs, Libratus and DeepStack that have applied to the game. Several news media report the growth of AI, but this study will multi-dimensionally discusses how and why AI works in Poker, the real problems of AI, and suggestions for advancement.

• KIISE Transactions on Computing Practices
• /
• v.21 no.8
• /
• pp.572-577
• /
• 2015

Generally, the existing Artificial Intelligence (AI) systems were designed for specific purposes and their capabilities handle only specific problems. Alternatively, Artificial General Intelligence can solve new problems as well as those that are already known. Recently, General Video Game Playing the game AI version of General Artificial Intelligence, has garnered a large amount of interest among Game Artificial Intelligence communities. Although video games are the sole concern, the design of a single AI that is capable of playing various video games is not an easy process. In this paper, we propose a GreedyUCB1 algorithm and rollout method that were formulated using the knowledge from a game analysis for the Monte-Carlo Tree Search game AI. An AI that used our method was ranked fourth at the GVG-AI (General Video Game-Artificial Intelligence) competition of the IEEE international conference of CIG (Computational Intelligence in Games) 2014.

• Journal of Korea Multimedia Society
• /
• v.11 no.1
• /
• pp.76-87
• /
• 2008

As hardware performance rises, game users demand higher computer graphic, more convenient UI(User Interface), faster network, and smarter AI(Artificial Intelligence). At this time, however, AI development is accomplished by a co-development team or only one developer. For that reason, it's hard to verify that AI performance and basic game AI technology is lacking for developing high-level AI. Searching the merits and demerits of existing game AI platforms, we investigate main points to consider when designing game AI platforms in this paper. From this we suggest Darwin, a game platform, based on agent that developers embody AI easily and capable of proposing AI test with module that makes them find strategic position. And then evaluate achievement results through making agent used strategic module that Darwin offers.

• Journal of Korea Game Society
• /
• v.20 no.3
• /
• pp.3-14
• /
• 2020

The purpose of this paper is to analyze the factors effecting users' satisfaction on game AI for early AI diffusion. For this purpose, we interviewed 20 users who had experiences playing Blade&Soul, made by NCsoft. Interview data had been analyzed through the Semantic Network Analysis program to identify key subject words and their relations. As a result, the paper has found keywords such as patterns, contents, variety, system, and getting new users as factors effecting users satisfaction on game AI.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.165-166
• /
• 2023

게임 그래픽 제작 분야는 기술적 진보가 가속화 되어 가고 있는데 리소스 제작 도구의 다양한 출현과 개발자의 학습과 적절한 사용도 큰 몫을 담당하고 있다. 최근에 빠르게 발전하고 있는 분야인 AI기반의 콘텐츠 제작 도구가 게임 개발의 여러 영역에 다양한 영향을 줄 것으로 보인다. 그 중 비교적 개발 파이프라인에 빠르고 안정적인 도입이 가능한 AI 기반의 텍스쳐 자동 생성 도구를 기존에 사용하고 있는 텍스쳐 제작 도구와 비교 분석 해 보았다. 이를 통해 효과적인 텍스쳐 생성 프로세스 파이프라인 구축을 위해 AI 기반의 텍스쳐 자동 생성 도구의 적극적인 도입의 필요성과 함께 이후 연구의 방향을 제시한다.