• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제6권3호
• /
• pp.264-269
• /
• 2006

This paper presents the strategy for searching a hidden object in an unknown area for using by multiple distributed autonomous robotic systems (DARS). To search the target in Markovian space, DARS should recognize th ε ir surrounding at where they are located and generate some rules to act upon by themselves. First of all, DARS obtain 6-distances from itself to environment by infrared sensor which are hexagonally allocated around itself. Second, it calculates 6-areas with those distances then take an action, i.e., turn and move toward where the widest space will be guaranteed. After the action is taken, the value of Q will be updated by relative formula at the state. We set up an experimental environment with five small mobile robots, obstacles, and a target object, and tried to research for a target object while navigating in a un known hallway where some obstacles were placed. In the end of this paper, we present the results of three algorithms - a random search, an area-based action making process to determine the next action of the robot and hexagon-based Q-learning to enhance the area-based action making process.

• 수산해양교육연구
• /
• 제22권3호
• /
• pp.431-444
• /
• 2010

This research aims at developing a teachers' training program to reinforce teachers' capability to perform the action learning program. To accomplish this goal, the key value of the training program based on action learning, the process of the core learning activities, and the elements to support learners and facilitators respectively were deducted on the foundation of documentary research and case study, based on which, the program was developed through the formative test by professionals and application to the field. This research was applied to 105 middle or high school teachers, the participants of the in-service training on creative problem solving hosted by B metropolitan city for one week (30 hours) from 9 a.m. on Monday, January 25th, 2010 to 4 p.m. on Friday, January 29th. The result of this research is as follows. First, as for the key values of this study, (1) the team-based learning centered on the trainees, not lecturers-oriented, knowledge-transmitting training, is possible, (2)for each process, guidelines, related information, tools, and various kinds of media are supported just in time, and (3)a focus is given on fostering facilitators centered on teachers. Second, the process of the core learning activities of the teachers' training program based on action learning consists of the procedure of a prior lecture${\rightarrow}$break${\rightarrow}$investigation into problems${\rightarrow}$clarification of problems${\rightarrow}$drawing possible solutions${\rightarrow}$decision on the priority${\rightarrow}$making an action plan${\rightarrow}$performance${\rightarrow}$evaluation, and on each stage, the contents for the activities of teachers and learners and detailed supportive elements are offered.

• 한국멀티미디어학회논문지
• /
• 제12권12호
• /
• 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.

• 한국콘텐츠학회논문지
• /
• 제9권10호
• /
• pp.51-58
• /
• 2009

강화학습은 최적의 행동정책을 구하는 최적화 문제로 주어진 환경과의 상호작용을 통해 받는 보상 값을 최대화하는 것이 목표이다. 특히 단일 에이전트에 비해 상태공간과 행동공간이 매우 커지는 다중 에이전트 시스템인 경우 효과적인 강화학습을 위해서는 적절한 행동 선택 전략이 마련되어야 한다. 본 논문에서는 멀티에이전트의 효과적인 행동 선택과 학습의 수렴속도를 개선하기 위하여 퍼지 추론 기반의 멀티에이전트 강화학습 모델을 제안하였다. 멀티 에이전트 강화학습의 대표적인 환경인 로보컵 Keepaway를 테스트 베드로 삼아 다양한 비교 실험을 전개하여 에이전트의 효율적인 행동 선택 전략을 확인하였다. 제안된 퍼지 추론 기반의 멀티에이전트 강화학습모델은 다양한 지능형 멀티 에이전트의 학습에서 행동 선택의 효율성 평가와 로봇축구 시스템의 전략 및 전술에 적용이 가능하다.

• 한국컴퓨터그래픽스학회논문지
• /
• 제27권5호
• /
• pp.55-61
• /
• 2021

물리 시뮬레이션 기반의 캐릭터 동작 제어 문제를 강화학습을 이용하여 해결해나가는 연구들이 계속해서 진행되고 있다. 강화학습을 사용하여 문제를 풀기 위해서는 네트워크 구조, 하이퍼파라미터 튜닝, 상태(state), 행동(action), 보상(reward)이 문제에 맞게 적절히 설정이 되어야 한다. 많은 연구들에서 다양한 조합으로 상태, 행동, 보상을 정의하였고, 성공적으로 문제에 적용하였다. 상태, 행동, 보상을 정의함에 다양한 조합이 있다보니 학습 성능을 향상시키는 최적의 조합을 찾기 위해서 각각의 요소들이 미치는 영향을 분석하는 연구도 진행되고 있다. 우리는 지금까지 이뤄지지 않았던 상태 표현 방식에 따른 강화학습성능에 미치는 영향을 분석하였다. 첫째로, root attached frame, root aligned frame, projected aligned frame 3가지로 좌표계를 정의하였고, 이에 대해 표현된 상태를 이용하여 강화학습에 미치는 영향을 분석하였다. 둘째로, 상태를 정의 할 때, 관절의 위치, 각도로 다양하게 조합하는 경우에 학습성능에 어떠한 영향을 미치는지 분석하였다.

• Asia pacific journal of information systems
• /
• 제32권2호
• /
• pp.226-248
• /
• 2022

The existing model for sentiment analysis of product reviews learned from past data and new data was labeled based on training. But new data was never used by the existing system for making a decision. The proposed Aspect-based multi-agent Deep Reinforcement learning Sentiment Analysis (ADRSA) model learned from its very first data without the help of any training dataset and labeled a sentence with aspect category and sentiment polarity. It keeps on learning from the new data and updates its knowledge for improving its intelligence. The decision of the proposed system changed over time based on the new data. So, the accuracy of the sentiment analysis using deep reinforcement learning was improved over supervised learning and unsupervised learning methods. Hence, the sentiments of premium customers on a particular site can be explored to other customers effectively. A dynamic environment with a strong knowledge base can help the system to remember the sentences and usage State Action Reward State Action (SARSA) algorithm with Bidirectional Encoder Representations from Transformers (BERT) model improved the performance of the proposed system in terms of accuracy when compared to the state of art methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권2호
• /
• pp.483-503
• /
• 2014

In this paper, human action recognition using pyramid histograms of oriented gradients and collaborative multi-task learning is proposed. First, we accumulate global activities and construct motion history image (MHI) for both RGB and depth channels respectively to encode the dynamics of one action in different modalities, and then different action descriptors are extracted from depth and RGB MHI to represent global textual and structural characteristics of these actions. Specially, average value in hierarchical block, GIST and pyramid histograms of oriented gradients descriptors are employed to represent human motion. To demonstrate the superiority of the proposed method, we evaluate them by KNN, SVM with linear and RBF kernels, SRC and CRC models on DHA dataset, the well-known dataset for human action recognition. Large scale experimental results show our descriptors are robust, stable and efficient, and outperform the state-of-the-art methods. In addition, we investigate the performance of our descriptors further by combining these descriptors on DHA dataset, and observe that the performances of combined descriptors are much better than just using only sole descriptor. With multimodal features, we also propose a collaborative multi-task learning method for model learning and inference based on transfer learning theory. The main contributions lie in four aspects: 1) the proposed encoding the scheme can filter the stationary part of human body and reduce noise interference; 2) different kind of features and models are assessed, and the neighbor gradients information and pyramid layers are very helpful for representing these actions; 3) The proposed model can fuse the features from different modalities regardless of the sensor types, the ranges of the value, and the dimensions of different features; 4) The latent common knowledge among different modalities can be discovered by transfer learning to boost the performance.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 D
• /
• pp.2834-2836
• /
• 2000

This paper introduces the behavior-based learning controller for mobile robot using topological map. When the mobile robot navigates to the goal position, it utilizes given information of topological map and its location. Under navigating in unknown environment, the robot classifies its situation using ultrasonic sensor data, and calculates each motor schema multiplied by respective gain for all behaviors, and then takes an action according to the vector sum of all the motor schemas. After an action, the information of the robot's location in given topological map is incorporated to the learning module to adapt the weights of the neural network for gain learning. As a result of simulation, the robot navigates to the goal position successfully after iterative gain learning with topological information.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제50권11호
• /
• pp.522-531
• /
• 2001

Recently conventional artificial intelligence(AI) approaches have been employed to build action selectors for the autonomous mobile robot(AMR). However, in these approaches, the decision making process to choose an action from multiple competence modules is still an open question. Many researches have been focused on the reactive planning systems such as the biological immune system. In this paper, we attempt to construct an action selector for an AMR based on the artificial immune network and internet. The information from vision sensors is used for antibody. We propose a learning method for artificial immune network using evolutionary algorithm to produce antibody automatically. The internet environment for an AMR action selector shows the usefulness of the proposed learning artificial immune network application.

• 디지털융복합연구
• /
• 제19권6호
• /
• pp.73-83
• /
• 2021

본 연구는 합리적행위이론을 기반으로 액션러닝 기반 창의성 프로그램을 이수한 학생들의 문제해결의도에 영향을 주는 요인들을 파악하고 이들 요인들 간의 영향관계를 살펴보았다. 연구결과, 첫째 문제해결에 대한 주관적 규범은 문제해결의도에 긍정적 영향을 주었고, 둘째 문제해결에 대한 태도는 문제해결의도와 유의미한 영향관계가 있는 것으로 나타났다. 셋째 액션러닝방법론을 적용한 특허출원교육 프로그램의 참여경험이 있는 학생의 경우 문제해결에 대한 태도와 문제해결의도와의 관계에 있어 긍정적 영향효과를 주는 것으로 파악되었다. 이러한 연구결과는 대학생들의 창의성 기반이 되는 문제해결의도를 제고하기 위해서 대학 내 문제해결에 대한 긍정적 가치 공유의 확산과 아울러 학생들 자기주도적 문제해결에 대한 긍정적 자세를 갖게 하는 것이 중요함을 확인하였다.