• The Journal of Korea Robotics Society
• /
• v.14 no.3
• /
• pp.157-162
• /
• 2019

The video game Tetris is one of most popular game and it is well known that its game rule can be modelled as MDP (Markov Decision Process). This paper presents a DQN (Deep Q-Network) based game agent for Tetris game. To this end, the state is defined as the captured image of the Tetris game board and the reward is designed as a function of cleared lines by the game agent. The action is defined as left, right, rotate, drop, and their finite number of combinations. In addition to this, PER (Prioritized Experience Replay) is employed in order to enhance learning performance. To train the network more than 500000 episodes are used. The game agent employs the trained network to make a decision. The performance of the developed algorithm is validated via not only simulation but also real Tetris robot agent which is made of a camera, two Arduinos, 4 servo motors, and artificial fingers by 3D printing.

• Journal of Korea Game Society
• /
• v.9 no.2
• /
• pp.125-133
• /
• 2009

Game artificial intelligence is usually used to provide intelligent and adjusted game environment for user. Previously, it was used for Non-player character(NPC) playing a role of a company or an enemy through collecting and analyzing a user's behaviour. However, it was just mimicking the user's behavior. This paper introduces a method to change game environment by analyzing a user's game behavior. Game behavior data has been used to understand user's game preference. Also, the user's preference was used to provide more active game environment by reflecting decision of geographical features, items and distribution of NPC. For experiment of the suggested method, we utilized a real 2D action game and confirmed the game environment which changing properly according to the user's game play.

• Journal of Korea Multimedia Society
• /
• v.12 no.12
• /
• pp.1819-1826
• /
• 2009

To enhance the automatic performance of existing predicting and planning algorithms that require a predefined probability of the states' transition, this paper proposes a multiple sequence generation system. When interacting with unknown environments, a virtual agent needs to decide which action or action order can result in a good state and determine the transition probability based on the current state and the action taken. We describe a sequential behavior generation method motivated from the change in the agent's state in order to help the virtual agent learn how to adapt to unknown environments. In a sequence learning process, the sensed states are grouped by a set of proposed motivation filters in order to reduce the learning computation of the large state space. In order to accomplish a goal with a high payoff, the learning agent makes a decision based on the observation of states' transitions. The proposed multiple sequence behaviors generation system increases the complexity and heightens the automatic planning of the virtual agent for interacting with the dynamic unknown environment. This model was tested in a virtual library to elucidate the process of the system.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.05a
• /
• pp.433-436
• /
• 2012

Today due to the development of technology, 3D graphics have become an essential element of the game graphic. When game companies create a game using 3D graphics, game users can enjoy a better game graphics like photo-realistic live action than 2D game graphics. And because the game companies have many advantages in creating games which are easy to deal with many basic effects and special effects, in video game business field, 3D game have become the mainstream. This paper will inquire the characteristics of 2D spline which is basic to various kinds of 3D modeling necessary to making 3D game graphics, compare and analyze the merits and demerits of each kind of spline and find out its development history.

• Journal of Korea Multimedia Society
• /
• v.13 no.12
• /
• pp.1820-1831
• /
• 2010

When interacting with unknown environments, an autonomous agent needs to decide which action or action order can result in a good state and determine the transition probability based on the current state and the action taken. The traditional multiple sequential learning model requires predefined probability of the states' transition. This paper proposes a multiple sequential learning and prediction system with definition of autonomous states to enhance the automatic performance of existing AI algorithms. In sequence learning process, the sensed states are classified into several group by a set of proposed motivation filters to reduce the learning computation. In prediction process, the learning agent makes a decision based on the estimation of each state's cost to get a high payoff from the given environment. The proposed learning and prediction algorithms heightens the automatic planning of the autonomous agent for interacting with the dynamic unknown environment. This model was tested in a virtual library.

• Journal of the Korea Convergence Society
• /
• v.4 no.4
• /
• pp.7-12
• /
• 2013

Presence of music in the modern game is getting bigger and bigger, and storytelling in the area of game play a leading role in many cases. Platform game is one type of action game genre. In its nature, the character and the object in a game are closely coupled, thus they have intermate relation with reactive sound system. In this study, we tried to build a effective and reactive sound system which is suitable for the storytelling of platform game. In addition, we speculated various aspects of game including psychological, musical and social aspects, finally investigating the future aspects of the game music.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2013.07a
• /
• pp.45-46
• /
• 2013

대중에게 하나의 취미 생활로 자리매김한 게임은 특징이나 작동 방법에 따라 다양한 장르로 발전되었다. 그 중 액션게임 장르는 사용자가 조작하는 캐릭터의 역동적인 움직임과 움직임이 큰 동작으로 인해 사용자로 하여금 게임 플레이에 몰입할 수 있는 특징을 가지고 있다. 과거 2D 환경의 게임에서 연속되는 그림으로 표현되던 캐릭터의 애니메이션 장면은 3D 환경으로 발전하면서 새로운 애니메이션 기법을 필요로 하였으며, 현재 다양한 애니메이션 기법이 연구되고 있다. 본 논문에서는 3D 뼈대 애니메이션 통하여 DirectX에서의 캐릭터 애니메이션 적용 대해 설명한다.

• Journal of Korea Game Society
• /
• v.10 no.6
• /
• pp.147-155
• /
• 2010

On this paper, suggests a communication structure making possible to fast data send-receive for the gaming process synchronization. For these things, first of all, analyze the data send-receive speed effecting on the online game by the game genre. Moreover, we suggested a proper data communication structure like real-time online action game genre which gaming synchronization effects on the gaming process. Communication structure suggested on this paper is being used with TCP/UDP protocol, and it is applied to the network system and verify improved data send-receive speed. These data send-receive structure can be applied to the various online games.

• International Journal of Advanced Culture Technology
• /
• v.9 no.4
• /
• pp.417-423
• /
• 2021

Recently, in the Game industries, they are increasing to use of game engines to reduce the development cost of 3D content and software. In particular, Unreal Engine provides a blueprint visual scripting function that enables software production without programming (coding). Although High-end video content can be produced, the problem is that content development is complicated and requires advanced manpower. To solve this problem, we propose an optimized VR game context process. This is because 1) a Blueprint visual script is used, 2) VR games with various interactions can be produced, 3) Non-majors in the software field (or groups) can develop advanced content. In various related industries such as defense, medical care, manufacturing, and construction, we may easily develop any game content without programming with our refined VR rhythm action game development process. We expect to reduce the development cost with the process advantages in the game industries.

• Proceedings of the KIEE Conference
• /
• 1998.11b
• /
• pp.543-545
• /
• 1998

Robotic soccer is multi-agent system playing soccer game under given rule. This system consists of three mobile robots, vision sensor, action decision module, action execution module and communication module. This paper presents new action decision method using multi-layer neural networks.