• Journal of Korea Multimedia Society
• /
• v.9 no.5
• /
• pp.649-657
• /
• 2006

Reinforcement Learning is a computational approach to learning whereby an agent take an action which maximize the total amount of reward it receives among possible actions within current state when interacting with a uncertain environment. Q-learning, one of the most active algorithm in Reinforcement Learning, is consist of rewards which is obtained when an agent take an action. But it has the problem with mapping real world to discrete states. When state spaces are very large, Q-learning suffers from time for learning. In constant, when the state space is reduced, many state spaces map to single state space. Because an agent only learns single action within many states, an agent takes an action monotonously. In this paper, to reduce time for learning and complement simple action, we propose the Q-learning using influence map(QIM). By using influence map and adjacent state space's learning result, an agent could choose proper action within uncertain state where an agent does not learn. When this paper compares simulation results of QIM and Q-learning, we show that QIM effects as same as Q-learning even thought QIM uses 4.6% of the Q-learning's state spaces. This is because QIM learns faster than Q-learning about 2.77 times and the state spaces which is needed to learn is reduced, so the occurred problem is complemented by the influence map.

• The Journal of the Korea Contents Association
• /
• v.8 no.1
• /
• pp.308-317
• /
• 2008

The objects real time rendered in the 3D cyber space can interact with each others according to the events which are happened when satisfying some conditions. But to representing the behaviors with these interactions, too many event conditions are considered because each behavior pattern and event must be corresponded in a one-to-one ratio. It leads to problems which increase the system complexity. So, in this paper, we try to physical method based on elasticity force for representing more realistic behaviors of AI fish and apply to the deformable multi-detection sensor, so we suggest the new method which can create the various behavior patterns responding to one evasion event.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.39 no.3
• /
• pp.62-78
• /
• 2002

In this paper, we describe a system that can interact with agents in the virtual space incorporated in the system. This system is constructed by an analysis system for analyzing human gesture and an interact system for interacting with agents in the virtual space using analyzed information. An implemented analysis system for analyzing gesture extracts a head and hands region after taking image sequence of an operator's continuous behavior using CCD cameras. In interact system, we construct the virtual space that exist an avatar which incarnating operator himself, an autonomous object (like a Puppy), and non-autonomous objects which are table, door, window and object. Recognized gesture is transmitted to the avatar in the virtual space, then transit to next state based on state transition diagram. State transition diagram is represented in a graph in which each state represented as node and connect with link. In the virtual space, the agent link an avatar can open and close a window and a door, grab or move an object like a ball, order a puppy to do and respond to the Puppy's behavior as does the puppy.

• Journal of Korea Game Society
• /
• v.11 no.1
• /
• pp.111-120
• /
• 2011

It is important to realistically simulate group behaviors of the multi-agents in virtual worlds. While most researchers have focused on their group behaviors in an open space, this paper studies their group behaviors by using steering force in an enclosed space. Agents have a common target and should move towards it in an enclosed space while avoiding collision with other agents. Under those environments, three possible models of agents are proposed and the six steering forces needed in each model are also proposed. In order to show the correctness of the proposed models, they were simulated. Our simulation results showed that the proposed models only using steering forces operate well in the enclosed space although it requires a different period of time for each agent to arrive at its target depending on the walls and doors.

• Journal of Korean Library and Information Science Society
• /
• v.36 no.4
• /
• pp.177-198
• /
• 2005

The objective of this paper is to obtain the knowledge for spatial Planning of children's library which serves various users. The study method is to observes the children and their parents' space use according to the age step of children in public library, and analyzes it in the relation with the classified 4-types of children's section. Five characteristics were identified. First, children area was influenced by library location and user's characteristics. Second, children area was used various aged group with children. Third, there were different use patterns based upon age. Fourth, various reading space was needed through areas. And, last the behavior and the characteristics of area and furnishings were described.

• The Journal of the Korea Contents Association
• /
• v.16 no.1
• /
• pp.274-284
• /
• 2016

The purpose of this study is to analyze the play behaviour and play environment of children at the Air-bounce space in the theme museum, using user observation and interviewing user behaviour, main methods of user research. Study area is Animation theme museum in Chuncheon City, Kangwon Province, Republic of Korea. Main results show that physical, emotional, cognitive, and social behaviour of playing children in the study area are observed, and this study draws the planning and design related implications of play space such as carrying capacity, waiting room and safety guard and so on. The results of this study can be used in the planning and design process of children's play environment as important guidelines.

• Korean Journal of Culture and Social Issue
• /
• v.10 no.3
• /
• pp.83-101
• /
• 2004

This study investigated the effects of social presence as means of self-awareness and interpersonal-awareness on the cyber-aggressive behavior. The cyber-aggressive behavior (flaming and direct aggression use of character) should be differ from existence of social presence and type of social presence of internet users. To test hypothesis, an experiment was executed a field study on cyberspace, an on-line game, "fortress 2 blue forever". I made a chat-room in the game site to conduct an experiment to 107 person who entered the chat-room and blinded ignorance of this situation made by researchers. As the subjects enter the chat-room, he chats with 3 researchers who were waiting before he gets in. The social presence was operated with 3 phases by the contents of the chat (①control group; nothing, ②experimental group 1; reaction about other people ③experimental group 2; reaction about other people + self-exposure by an exchange information of their home region). The studies show that, subjects of the control group behaved more aggressively than other subjects of the experimental groups(both flaming and direct aggression use of character). Meantime, I compared experimental group 1 with experimental group 2 to investigate difference between the type of social presence. As the result, subjects of the experimental group 1 behaved more aggressively than experimental group 2 (only flaming, there's no difference in direct aggression use of character).

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.55-57
• /
• 2001

강화학습은 한 에이전트가 자신이 놓여진 환경으로부터의 보상을 최대화할 수 있는 최적의 행동 전략을 학습하는 것이다. 따라서 강화학습은 입력(상태)과 출력(행동)의 쌍으로 명확한 훈련 예들이 제공되는 교사 학습과는 다르다. 특히 Q-학습과 같은 비 모델 기반(model-free)의 강화학습은 사전에 환경에 대한 별다른 모델을 설정하거나 학습할 필요가 없으며 다양한 상태와 행동들을 충분히 자주 경험할 수만 있으면 최적의 행동전략에 도달할 수 있어 다양한 응용분야에 적용되고 있다. 하지만 실제 응용분야에서 Q-학습과 같은 강화학습이 겪는 최대의 문제는 큰 상태 공간을 갖는 문제의 경우에는 적절한 시간 내에 각 상태와 행동들에 대한 최적의 Q값에 수렴할 수 없어 효과를 거두기 어렵다는 점이다. 이런 문제점을 고려하여 본 논문에서는 로봇 축구 시뮬레이션 환경에서 각 선수 에이전트의 동적 위치 결정을 위해 효과적인 새로운 Q-학습 방법을 제안한다. 이 방법은 원래 문제의 상태공간을 몇 개의 작은 모듈들로 나누고 이들의 개별적인 Q-학습 결과를 단순히 결합하는 종래의 모듈화 Q-학습(Modular Q-Learning)을 개선하여, 보상에 끼친 각 모듈의 기여도에 따라 모듈들의 학습결과를 적응적으로 결합하는 방법이다. 이와 같은 적응적 중재에 기초한 모듈화 Q-학습법(Adaptive Mediation based Modular Q-Learning, AMMQL)은 종래의 모듈화 Q-학습법의 장점과 마찬가지로 큰 상태공간의 문제를 해결할 수 있을 뿐 아니라 보다 동적인 환경변화에 유연하게 적응하여 새로운 행동 전략을 학습할 수 있다는 장점을 추가로 가질 수 있다. 이러한 특성을 지닌 AMMQL 학습법은 로봇축구와 같이 끊임없이 실시간적으로 변화가 일어나는 다중 에이전트 환경에서 특히 높은 효과를 볼 수 있다. 본 논문에서는 AMMQL 학습방법의 개념을 소개하고, 로봇축구 에이전트의 동적 위치 결정을 위한 학습에 어떻게 이 학습방법을 적용할 수 있는지 세부 설계를 제시한다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38A no.1
• /
• pp.1-9
• /
• 2013

This paper propose a human action recognition method that uses bag-of-features (BoF) based on CS-LBP (center-symmetric local binary pattern) and a spatial pyramid in addition to the random forest classifier. To construct the BoF, an image divided into dense regular grids and extract from each patch. A code word which is a visual vocabulary, is formed by k-means clustering of a random subset of patches. For enhanced action discrimination, local BoF histogram from three subdivided levels of a spatial pyramid is estimated, and a weighted BoF histogram is generated by concatenating the local histograms. For action classification, a random forest, which is an ensemble of decision trees, is built to model the distribution of each action class. The random forest combined with the weighted BoF histogram is successfully applied to Standford Action 40 including various human action images, and its classification performance is better than that of other methods. Furthermore, the proposed method allows action recognition to be performed in near real-time.

• Proceedings of the Korea Contents Association Conference
• /
• 2010.05a
• /
• pp.428-430
• /
• 2010

가상현실에서 실제 사람처럼 행동하는 가상거주자는 스스로 주변의 상황을 판단하고 평가를 내리게 된다. 이러한 상황에 대한 판단은 얼마나 정확하고 다양한 자료가 주어졌느냐에 따라서 달라지게 된다. 본 논문에서는 Spatio-temporal graph(ST graph)를 사용하여 시간과 공간에 대한 데이터를 정의하고, ontology의 개념을 더하여 다양한 상황에 대한 표현이 가능하게 하였다. 이 표현 방법으로 가상거주자는 어떠한 상황을 마주하더라도 주변 환경이나 공간에 대한 데이터를 가지고 분석하여 필요한 행동을 할 수 있게 될 것이다.