• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.3
• /
• pp.87-94
• /
• 2024

We investigated the feasibility of utilizing Large Language Models (LLMs) to perform text-based games without training on game data in advance. We adopted ChatGPT-3.5 and its state-of-the-art, ChatGPT-4, as the systems that implemented LLM. In addition, we added the persistent memory feature proposed in this paper to ChatGPT-4 to create three game player agents. We used Zork, one of the most famous text-based games, to see if the agents could navigate through complex locations, gather information, and solve puzzles. The results showed that the agent with persistent memory had the widest range of exploration and the best score among the three agents. However, all three agents were limited in solving puzzles, indicating that LLM is vulnerable to problems that require multi-level reasoning. Nevertheless, the proposed agent was still able to visit 37.3% of the total locations and collect all the items in the locations it visited, demonstrating the potential of LLM.

• Journal of Korean Society of Transportation
• /
• v.27 no.6
• /
• pp.147-156
• /
• 2009

We present a methodology for modeling and solving the transit frequency design problem with variable demand. The problem is described as a bi-level model based on a non-cooperative Stackelberg game. The upper-level operator problem is formulated as a non-linear optimization model to minimize net cost, which includes operating cost, travel cost and revenue, with fleet size and frequency constraints. The lower-level user problem is formulated as a capacity-constrained stochastic user equilibrium assignment model with variable demand, considering transfer delay between transit lines. An efficient algorithm is also presented for solving the proposed model. The upper-level model is solved by a gradient projection method, and the lower-level model is solved by an existing iterative balancing method. An application of the proposed model and algorithm is presented using a small test network. The results of this application show that the proposed algorithm converges well to an optimal point. The methodology of this study is expected to contribute to form a theoretical basis for diagnosing the problems of current transit systems and for improving its operational efficiency to increase the demand as well as the level of service.

• The Journal of the Korea Contents Association
• /
• v.21 no.2
• /
• pp.707-717
• /
• 2021

The purpose of this study was to explore whether PPAT drawing using an application can be developed on digital devices for game addicts. The PPAT drawing test is useful and reliable for verifying problem-solving skills in how people pick apples. As a result of this study, the over-immersion group scored lower than the average user group in the "problem Solving" category of the PPAT drawing test using the PPAT drawing applicaion on digital devices, and expressed by not reaching for apples, or by picking apples without reasonable support. The findings in this study suggest that the PPAT drawing test application on digital devices has significantly demonstrated its original purpose of 'problem resolution', as well as future psychotherapeutic interventions for Internet over-immersion subjects as well as users who are familiar with digital devices.

• Journal of Digital Convergence
• /
• v.14 no.6
• /
• pp.415-423
• /
• 2016

Numerous studies have been made on the negative effects of online games, as the negatives effects of the usage of online games have been recognized as social issues. However, this is a study on the positive functions of online gaming; more specifically, on how the guild activities on online games affect the user's leadership. This study has conducted in-depth interviews with online games, and drew the result using Giorgi's phenomenological analysis as for the methodology. 3 people participated in the research - a high school student, a university student, and an adult office worker - all of whom with experiences of guild leading on online games. To achieve the goal of this study, this study based the subjects' experience to analyze how online game guild activities have affected leadership on the subjects' real lives. As a result, timidity turned into initiation; not only leadership, but also decision making ability and coworking ability, as well as problem solving ability have shown improvement. Through this study, one can see that among the elements of online game, experience in guild activities is providing opportunities for enhancing leadership and possibilities for improving various other abilities. I hope more researchers continue studying interesting and diverse powers of online games based on this study.

• Journal of Korean Academy of Nursing
• /
• v.33 no.2
• /
• pp.189-199
• /
• 2003

Purpose: The purposes of this study is to develop an educational program to prevent sexual abuse of children and to improve the physical and mental health of children by providing a rape-free environment and safety education. This program will provide parents and children with information on how to prevent sexual abuse in children. Children learn specific methods to avoid being victimized both at home and outside the home through a learning game and simulation, which is based on problem solving. Method: This program was developed based on a literature reviews, surveys and negotiation process. School- aged-children, parents, and teachers were interviewed to reveal their educational needs based on their experiences related to sexual abuse. Result: This program includes useful subjects such as safety education, early detection of sexual abuse, crisis management, resource persons, and phone numbers of available hospital. Counseling is provided by researcher or by a pediatric psychiatrist if needed. Conclusion: This program could be adequately utilized for prevention of sexual abuse of children. It also will provide an intervention strategy for abused children. This educational program was distributed to all of the elementary school through the Ministry of Education and Human Resources Development.

• Journal of Digital Contents Society
• /
• v.11 no.3
• /
• pp.349-356
• /
• 2010

This study was to develop improving vocational basic skill program and content which are basic of instruction-learning ability for the vocational education substantiality. To pursue this goal, 'self-development capability' among vocational basic skills was developed through the research methodology and procedure. The interpersonal relation capability was selected as one of vocational basic skill areas when it was more effective by e-learning contents through literature review, expert conference etc. The self-development capability can be self-control and development under performing business tasks. In this study, self-development capability was programmed a interpersonal scheme, a cooperative capability, a leadership capability, a conflict management, negotiation capability, and a customer service capability. Especially this program was developed as a form of e-Learning contents focusing on improving problem solving under real case using multimedia strategies such as movies, simulation, game.

• The KIPS Transactions:PartD
• /
• v.12D no.1 s.97
• /
• pp.81-90
• /
• 2005

Given a model and a property, model checking determines whether the model satisfies the property. In case the model does not satisfy the property model checking gives a counterexample which explains where the violation occurs. Since counterexamples are useful for model debugging as well as model understanding, counterexample generation is one of the indispensable components in the model checking tool. This paper presents efficient counterexample generation techniques when a safety property is falsified. These techniques are used to solve Push Push games which consist of 50 games. As a result, all the games are solved with the proposed techniques. However, with the original NuSMV, 42 games are solved but 8 failed. In addition, we obtain $86{\%}$ time improvement and $62{\%}$ space improvement compared to the original NuSMV in solving the game.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.6
• /
• pp.1575-1582
• /
• 1998

In this paper. we design and evaluate a cooperating model that increase problem solving ability by selecting proper cooperating partners under changing situation. In this model, to decide cooperation direction and extent, we have used a payoff function and then divided the group into two parts, cooperation part and non-cooperation part. To control these reconfigured groups at group level, group intention is used as a control media instead of existing data and goal. Group intention is abstractive and comprehensive and represents collection of strategies. Group intention is changed based on resources, information, and cooperation situation on group intention hierarchy. Two layered control is possible : first constraint with group intentions(group level) and then select a strategy under the constraint. These approaches are tested and evaluated on pursuit game testbed.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.23 no.4
• /
• pp.399-406
• /
• 2020

In this paper, we propose a time-varying proportional navigation guidance law that determines the proportional navigation gain in real-time according to the operating situation. When intercepting a target, an unidentified evasion strategy causes a loss of optimality. To compensate for this problem, proper proportional navigation gain is derived at every time step by solving an optimal control problem with the inferred evader's strategy. Recently, deep reinforcement learning algorithms are introduced to deal with complex optimal control problem efficiently. We adapt the actor-critic method to build a proportional navigation gain network and the network is trained by the Proximal Policy Optimization(PPO) algorithm to learn an evasion strategy of the target. Numerical experiments show the effectiveness and optimality of the proposed method.

• Smart Media Journal
• /
• v.10 no.2
• /
• pp.55-60
• /
• 2021

In this research, we design and perform experiment to investigate whether neuronal activity patterns elicited while solving game tasks are spontaneously reactivated in during sleep. In order to recognize human activity EEG-fMRI signals are used at the same time. Experimental results shows that reward for the success of tasks performed before sleeping have an effect on sleep brain activity. The study uncovers a neural mechanism whereby rewarded life experiences are preferentially replayed and consolidated while we sleep.