• 전기전자학회논문지
• /
• 제25권4호
• /
• pp.644-649
• /
• 2021

Self-Imitation Learning은 간단한 비활성 정책 actor-critic 알고리즘으로써 에이전트가 과거의 좋은 경험을 활용하여 최적의 정책을 찾을 수 있도록 해준다. 그리고 actor-critic 구조를 갖는 강화학습 알고리즘에 결합되어 다양한 환경들에서 알고리즘의 상당한 개선을 보여주었다. 하지만 Self-Imitation Learning이 강화학습에 큰 도움을 준다고 하더라도 그 적용 분야는 actor-critic architecture를 가지는 강화학습 알고리즘으로 제한되어 있다. 본 논문에서 Self-Imitation Learning의 알고리즘을 가치 기반 강화학습 알고리즘인 DQN에 적용하는 방법을 제안하고, Self-Imitation Learning이 적용된 DQN 알고리즘의 학습을 다양한 환경에서 진행한다. 아울러 그 결과를 기존의 결과와 비교함으로써 Self-Imitation Leaning이 DQN에도 적용될 수 있으며 DQN의 성능을 개선할 수 있음을 보인다.

• Educational Technology International
• /
• 제12권1호
• /
• pp.67-94
• /
• 2011

The major concern of e-learning environment design is to create and improve artifacts that support human learning. To facilitate effective and efficient learning, e-learning environment designers focused on the contemporary information technologies. Web 2.0 services, which empower users and allow the inter-transforming interactions between users and information technologies, have been increasingly changing the way that people learn. By adapting these Web 2.0 technologies in learning environment, educational technology can facilitate learners' abilities to personalize learning environment. The main purpose of this study is to conceptualize comprehensively constructs for understanding the inter-transforming relationships between learner and learning environment and mutable learning environments' impact on the process through which learners learn and strive to shape their learning environment. As results, this study confirms conceptualization of four constructs by incorporating aspects of design that occur in e-learning environments with Web 2.0 technologies. First, learner-designer refers to active and intentional designer who is tailoring an e-learning environment in the changing context of use. Second, learner's secondary design refers to learner's design based on the primary designs by design experts. Third, transactional interaction refers to learner's inter-changeable, inter-transformative, co-evolutionary interaction with technological environment. Fourth, trans-active learning environment refers to mutable learning environment enacted by users.

• 교육시설 논문지
• /
• 제18권6호
• /
• pp.15-23
• /
• 2011

There are growing concerns about designing classroom or school environments influencing teaching and learning activities. However, there are little research on how students perceive the physical characteristic of the classroom and whether physical factors of classroom affects students' learning. The purpose of this study aims to reveal the different perception of college students on their classroom environments depending on where they take class, traditional classroom or newly constructed classroom. Also, the study demonstrates how the difference of classroom environment affects students' learning outcome. The results of this study suggests that classroom should be designed considering the perceptions of the students and their teaching and learning activities.

• 한국컴퓨터정보학회논문지
• /
• 제16권2호
• /
• pp.93-99
• /
• 2011

본 논문에서는 강화학습(RL : Reinforcement Learning) 환경 하에서 정책 기울기 값 기법을 사용하는 적응적인 QoS 라우팅 기법을 제안하였다. 이 기법은 기존의 강화학습 환경 하에 제공하는 기법에 비해 기대 보상값의 기울기 값을 정책에 반영함으로써 빠른 네트워크 환경을 학습함으로써 보다 우수한 라우팅 성공률을 제공할 수 있는 기법이다. 이를 검증하기 위해 기존의 기법들과 비교 검증함으로써 그 우수성을 확인하였다.

• 영어어문교육
• /
• 제17권4호
• /
• pp.375-393
• /
• 2011

Many aspects of e-러닝 and m-러닝 have been conducted in language learning settings while few studies have examined learners'psychological attitudes in both Internet-based languages learning environment. Althoughe-Learning and m-Learningin the content of language learningshares many common aspects, the study that particularly examinesEnglish learners' psychological attitudes from both learning environments has not been conducted. Thus, the purpose of this study is to investigate group difference between e-러닝 and m-러닝 in terms of characteristics of both learning environments, including Contextual Offer, Interactivity, Enjoyment, Usefulness, Easiness, Variety, Connectivity, Satisfaction, and Learning Performance. Results showed that even if there was little difference within and among groups in English learners' feelings, learners have different attitude on Enjoyment, Easiness, and Connectivity.

• 한국초등과학교육학회지:초등과학교육
• /
• 제32권2호
• /
• pp.198-205
• /
• 2013

For assessing classroom environment, numerous instruments were developed and reported the survey results for science students in science education. In this study I translated Constructivist Learning Environment Scales (CLES) were into Korean versions for elementary school teachers, and measured the reliability. The subjects were randomly selected from three departments of an University of Education in a metropolitan city. All of them were 110 students, who would be elementary school teachers. According to the survey results, pre-service teachers for elementary school have recognized constructivistly for learning environments in an actual forms. In a scale of student negotiation they have most constructivistly recognized learning environment, and moderately in scales of relevance, uncertainty and critical view while they have seldom constructivistly recognized in a scale of shared control. Also Korean version CLES would be an reliable instruments for constructivist assessing learning environments.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.489-489
• /
• 2000

Recently, Reinforcement Learning(RL) methods have been used far teaming problems in Partially Observable Markov Decision Process(POMDP) environments. Conventional RL-methods, however, have limited applicability to POMDP To overcome the partial observability, several algorithms were proposed [5], [7]. The aim of this paper is to extend our previous algorithm for POMDP, called Labeling Q-learning(LQ-learning), which reinforces incomplete information of perception with labeling. Namely, in the LQ-learning, the agent percepts the current states by pair of observation and its label, and the agent can distinguish states, which look as same, more exactly. Labeling is carried out by a hash-like function, which we call Labeling Function(LF). Numerous labeling functions can be considered, but in this paper, we will introduce several labeling functions based on only 2 or 3 immediate past sequential observations. We introduce the basic idea of LQ-learning briefly, apply it to maze problems, simple POMDP environments, and show its availability with empirical results, look better than conventional RL algorithms.

• 에너지공학
• /
• 제26권3호
• /
• pp.11-29
• /
• 2017

인공지능 특히 심층신경망기계학습기법(딥러닝)의 제조업분야에서의 이용이 효율적이며 실용적일 수 있다는 인식이 넓게 수용되고 있다 이 보고서는 최근의 신경망기계학습 개발환경을 개관하고 제조업분야에서 활용되고 있는 딥 러닝기술을 개관한다.

• 한국멀티미디어학회논문지
• /
• 제24권11호
• /
• pp.1508-1517
• /
• 2021

In CCTV environments, a lot of learning image data is required to monitor illegal dumping of garbage with a typical image-based object detection using deep learning method. In this paper, we propose a system to monitor unauthorized dumping of garbage by learning the articular points of the person using only a small number of images without immediate use of the image for deep learning. In experiment, the proposed system showed 74.97% of garbage dumping detection performance with only a relatively small amount of image data in CCTV environments.

• 로봇학회논문지
• /
• 제18권2호
• /
• pp.225-232
• /
• 2023

With the recent increase of multiple robots cooperating in smart manufacturing logistics environments, it has become very important how to predict the safety and efficiency of the individual tasks and dynamically assign them to the best one of available robots. In this paper, we propose a novel task policy learner based on deep relational reinforcement learning for predicting the safety and efficiency of tasks in a multi-robot manufacturing logistics environment. To reduce learning complexity, the proposed system divides the entire safety/efficiency prediction process into two distinct steps: the policy parameter estimation and the rule-based policy inference. It also makes full use of domain-specific knowledge for policy rule learning. Through experiments conducted with virtual dynamic manufacturing logistics environments using NVIDIA's Isaac simulator, we show the effectiveness and superiority of the proposed system.