• 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 Internet Computing and Services
• /
• v.6 no.2
• /
• pp.85-97
• /
• 2005

At th first time in 1985, Tetris appeared, it became game that are loved to many users until now. Existent Tetris employed way to give score according to number of that is destroyed whenever line are destroyed, and give advantage about serial attack and so on, But, these score calculation method gave so fixed and simple pattern. In this paper, We design and implement the new tetris game System by score calculation method per level that Is different with existent method. That Is, this method is to compare present and before with number of destroyed line and give advantage in basis score, Also, It is going to permit strategic utilization of still more developed tetris than existent tetris using score calculation method per level.

• Journal of Korea Game Society
• /
• v.12 no.4
• /
• pp.77-85
• /
• 2012

The purpose of this study was to investigate the effects of Tetris game on the cognitive abilities of students with mental retardation. Especially, this study focused on the arrangement of figures and the task attention. To do this, 33 students with mental retardation in a middle school participated and were assigned to the two treatment group. The experimental group did the Tetris game three times a week for 4 weeks, but the control group didn't the Tetris game. The experimental group revealed more higher improvement than the control group in the arrangement of figures and the task attention. The Tetris game can be used as an educational program to improve the cognitive abilities of students with mental retardation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.364-365
• /
• 2021

In this paper, we study and develop content for a puzzle game that can be enjoyed lightly with appropriate rules us ing Chilgyo-Nori blocks and Tetris blocks. We plan and develop puzzle games with low entry barriers and high revisit rates from the perspective of client indie game developers who are away from mass-produced games that additionally r equire specific items in a specific game section by focusing on the commercialization of game contents. The implement ed game promotes the creativity of users based on the possibility of creating more 2D designs than the existing Chilgy o-nori by using the Tetris block and the Chilgyo-nori block at the same time.

• Korean Architects
• /
• s.643
• /
• pp.60-65
• /
• 2022

• Journal of Convergence for Information Technology
• /
• v.10 no.8
• /
• pp.144-151
• /
• 2020

User-authentication process is necessary in Fintech Service. Especially, authentication on smartphones are carried out through PIN which is inputted through virtual keypads on touch screen. Attacker can analogize password by watching touched letter and position over the shoulder or using high definition cameras. To prevent password spill, various research of virtual keypad techniques are ongoing. It is hard to design secure keypad which assures safety by fluctuative keypad and enhance convenience at once. Also, to reconfirm user whether password is wrongly pressed, the inputted information is shown on screen. This makes the password easily exposed through high definition cameras or Google Class during recording. This research analyzed QWERTY based secure keypad's merits and demerits. And through these features, creating Tetris shaped keypad and piece them together on Android environment, and showing inputted words as Tetris shape to users through smart-screen is suggested for the ways to prevent password spill by recording.

• Journal of Korea Game Society
• /
• v.11 no.3
• /
• pp.9-20
• /
• 2011

This article attempts to analyze story of computer game by structuralistic storytelling model. The storytelling model is mainly used in traditional media. But the model is made not only by analyzing the text of story but also chasing the human psychological instinct, so I thought that it is applicable to computer games. Tetris, one of classical game was the object of analysis in this article. As a result, the 7 archetype and 12 journey of hero storytelling model were also available in tetris. The characteristic that the game user becomes protagonist itself must have been taken into account while analyzing game.

• Korean Architects
• /
• s.637
• /
• pp.88-93
• /
• 2022

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.12
• /
• pp.978-982
• /
• 2009

This paper proposes a potential-based reinforcement learning, called "RLs-CBDT", which combines multiple RL agents and case-base decision theory designed for decision making in uncertain environment as an expert knowledge in RL. We empirically show that RLs-CBDT converges to an optimal policy faster than pre-existing RL algorithms through a Tetris experiment.

• Journal of the Korea Convergence Society
• /
• v.8 no.6
• /
• pp.37-44
• /
• 2017

Mobile devices provide various services through payment and authentication by inputting important information such as passwords on the screen with the virtual keypads. In order to infer the password inputted by the user, the attacker captures the user's touch location information. The attacker is able to infer the password by using the location information or to obtain password information by peeping with Google Glass or Shoulder Surfing Attack. As existing secure keypads place the same letters in a set order except for few keys, considering handy input, they are vulnerable to attacks from Google Glass and Shoulder Surfing Attack. Secure keypads are able to improve security by rearranging various shapes and locations. In this paper, we propose secure keypads that generates 13 different shapes and sizes of Tetris and arranges keypads to be attached one another. Since the keypad arranges different shapes and sizes like the game, Tetris, for the virtual keypad to be different, it is difficult to infer the inputted password because of changes in size even though the attacker knows the touch location information.