• 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 Korea Game Society
• /
• v.14 no.2
• /
• pp.7-18
• /
• 2014

Emotion is one of the elements of the game that will help the user interaction. The way to express the emotions and personality of the character was taken into account severity of reaction to action or a specific graphics in the game so far. However recently structured for the interest in the study of emotion increases and to utilize a variety of feelings in the game is needed. In the field of autonomous agents, studies of the possibility of the use of emotion, defined 12 different emotion rules. In this paper, we dilate by defining the terms used in the game rules of emotion made the rules of the emotion of the game. And, we analyzed emotions in actual game character used Game Emotions Rule. As a result, it was possible to see the rules of the game feeling separate from that being used for game genre similar.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.5
• /
• pp.134-139
• /
• 2008

In this paper, we propose a story generation system using multi emotional agents. The proposed multi emotional agents are equipped with multiple emotional model so that it can be used as individually personalized agents that can generates unique storylines. Basically these kinds of multi emotional agents are easily employed as Avatar or NPC in computer games. In the proposed system, emotional agents are used as actor or actress whose characters and preferences are different each other. The storylines generated using the proposed system are realistic since the characters are emotional as humans.

• Journal of Korea Game Society
• /
• v.16 no.2
• /
• pp.27-40
• /
• 2016

Predicting stealthy behaviors plays an important role in designing stealth games. It is, however, difficult to automate this task because human players interact with dynamic environments in real time. In this paper, we present a reinforcement learning (RL) method for simulating stealthy movements in dynamic environments, in which an integrated model of Q-learning with Artificial Neural Networks (ANN) is exploited as an action classifier. Experiment results show that our simulation agent responds sensitively to dynamic situations and thus is useful for game level designer to determine various parameters for game.

• The KIPS Transactions:PartB
• /
• v.10B no.1
• /
• pp.1-12
• /
• 2003

In this paper, we Introduce the Unreal Tournament (UT) game and the Gamebots system. The former it a well-known 3D first-person action game and the latter is an intelligent agent research testbed based on UT And then we explain the design and implementation of KGBot, which is an intelligent non-player character deploying effectively within the 3D virtual environment provided by UT and the Gamebots system. KGBot is a bot client within the Gamebots System. KGBot accomplishes its own task to find out and dominate several domination points pro-located on the complex surface map of 3D virtual environment KGBot adopts UM-PRS as its control engine, which is a general BDI agent architecture. KGBot contains a hierarchical knowledge base representing its complex behaviors in multiple layers. In this paper, we explain details of KGBot's Intelligent behaviors, tuck af locating the hidden domination points by exploring the unknown world effectively. constructing a path map by collecting the waypoints and paths distributed over the world, and finding an optimal path to certain destination based on this path graph. Finally we analyze the performance of KGBot exploring strategy and control engine through some experiments on different 3D maps.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.11
• /
• pp.4282-4290
• /
• 2010

Recently, business environment is spreading from singular business to supply-chain problem. SCM(Supply Chain Management) is changing from closed and static to opened and dynamic environment, so these environment changes of SCM require to enterprise different approach than past. As supply chain is becoming opened and dynamic, a claim is being naming that converse of real-time the get reaction from to recognizing the level of supply chain problem, grope of alternative plan to solving this problem and choosing optimum alternative plan raise the enterprise competitive. But until present, the research to deal with these changes of SCM is on insufficient situation. Thus in this paper proposes the agent system by a way of realizing dynamic supply chain. The agent is going to accomplish the management activities in real-time depends on environment and given condition and designed for solving problems development and maintenance. Also, algorithms performance of the agent is tested on TAC SCM environment. Agents in TAC SCM are simulations of small manufacturers, who must compete with each other for both supplies and customers, and manage inventories and production facilities.

• Journal of Internet Computing and Services
• /
• v.8 no.4
• /
• pp.137-147
• /
• 2007

As Web-based online communities are rapidly growing, the agents in social groups need to know their measurable belief of trust for safe andsuccessful interactions. In this paper, we propose a computational model of trust resulting from available feedbacks in online communities. The notion of trust can be defined as an aggregation of consensus given a set of past interactions. The averagetrust of an agent further represents the center of gravity of the distribution of its trustworthiness and untrustworthiness. And then, we precisely describe the relationship between reputation, trust, and averagetrust through a concrete example of their computations. We apply our trust model to online internet settings in order to show how trust mechanisms are involved in a rational decision-making of the agents.

• Journal of Korea Game Society
• /
• v.15 no.2
• /
• pp.115-122
• /
• 2015

In this paper we propose a serious game for experience of music performance, which allows users to readily enjoy musical playing, even if the player has little or no experience in playing musical instruments. This game makes it easier for users to correctly perform given melodies along with standard performance, using a score-adjusting algorithm that can cope with the particular errors commonly made by beginners. This music performance is achieved by the agent to interpret the gestural sign of the user. We understands the interaction of the user and the agent as a communication model from the Peircean Semiotic perspectives.

• Journal of Korea Game Society
• /
• v.10 no.5
• /
• pp.95-102
• /
• 2010

This paper proposes a parallel algorithm of the flocking behaviors using GPU. To do this, we used CUDA as the parallel processing architecture of GPU and then analyzed its characteristics and constraints. Based on them, the paper improved the performance by parallelizing to find the neighbors for an agent which requires the largest cost in the flocking behaviors. We implemented the proposed algorithm on GTX 285 GPU and compared experimentally its performance with the original spatial partitioning method. The results of the comparison showed that the proposed algorithm outperformed the original method up to 9 times with respect to the execution time.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.04a
• /
• pp.639-642
• /
• 2002

오늘날 영화, 게임, 애니메이션 등 다양한 분야에서 사용되고 있는 군중 장면은 모델러의 많은 수작업을 필요로 한다. 모델러에게 있어 배경과 배경 물체들 그리고 수많은 에이전트들을 적절히 배치해야 하며, 매 프레임마다 이들 간에 충돌이 얼도록 적절히 움직여 주어야 하는 수작업은 비능률 적이다. 따라서 본 논문에서는 군중 장면 연출 도구를 제작하여 군중들을 배치할 수 있는 방법과, 배경 물체들과 군중 사이 그리고 군중을 이루는 에이전트들 사이의 충돌 회피 방법을 제시한다. 이를 통해 모델러는 군중을 일일이 배치하고, 매 프레임마다 군중을 적절히 움직여 주어야 하는 수작업에 드는 시간을 모델링에 투자함으로 작업 효율을 높일 수 있다. 또한 본 논문의 군중 장면 연출도구는 마야 플러그인으로 개발되어 대표적인 모델링 도구인 마야와 연동하여 군중 장면을 연출할 수 있는 장점을 가진다.