• International Journal of Air-Conditioning and Refrigeration
• /
• 제14권4호
• /
• pp.138-146
• /
• 2006

Recently, a technology based on the proportional integral (PI) control have grown rapidly owing to the needs for the robust capacity of the controllers from industrial building sectors. However, PI controller generally requires tuning of gains for optimal control when the outside weather condition changes. The present study presents the possibility of reinforcement learning (RL) control algorithm with PI controller adapted in the HVAC system. The optimal design criteria of RL controller was proposed in the environment chamber experiment and a theoretical analysis was also conducted using TRNSYS program.

• 전자통신동향분석
• /
• 제34권6호
• /
• pp.87-99
• /
• 2019

Reinforcement learning is a type of machine learning paradigm that forces agents to repeat the observation-action-reward process to assess and predict the values of possible future action sequences. This allows the agents to incrementally reinforce the desired behavior for a given observation. Thanks to the recent advancements of deep learning, reinforcement learning has evolved into deep reinforcement learning that introduces promising results in various control and optimization domains, such as games, robotics, autonomous vehicles, computing, industrial control, and so on. In addition to this trend, a number of programming libraries have been developed for importing deep reinforcement learning into a variety of applications. In this article, we briefly review and summarize 10 representative deep reinforcement learning libraries and compare them from a development project perspective.

• 한국멀티미디어학회논문지
• /
• 제21권2호
• /
• pp.250-260
• /
• 2018

In order to control the quadcopter using reinforcement learning, hovering of 1-axial drones prototype is implemented through reinforcement learning. A complementary filter is used to measure the correct angle, and the range of angles is from -180 degrees to +180 degrees using modified complementary filter. The policy gradient method is used together with the REINFORCE algorithm for reinforcement learning. The prototype learned in this way confirmed the difference in performance depending on the length of the episode.

• 설비공학논문집
• /
• 제16권11호
• /
• pp.1068-1076
• /
• 2004

Technology on the proportional integral (PI) control have grown rapidly owing to the needs for the robust capacity of the controllers from industrial building sectors. However, PI controller requires tuning of gains for optimal control when the outside weather condition changes. The present study presents the possibility of reinforcement learning (RL) control algorithm with PI controller adapted in the HVAC system. The optimal design criteria of RL controller was proposed in the Environment Chamber experiment and a theoretical analysis was also conducted using TRNSYS program.

• International Journal of Control, Automation, and Systems
• /
• 제1권2호
• /
• pp.236-242
• /
• 2003

This paper presents a cooperation strategy between a human operator and autonomous robots for an interactive robot soccer game, The interactive robot soccer game has been developed to allow humans to join into the game dynamically and reinforce entertainment characteristics. In order to make these games more interesting, a cooperation strategy between humans and autonomous robots on a team is very important. Strategies can be pre-programmed or learned by robots themselves with learning or evolving algorithms. Since the robot soccer system is hard to model and its environment changes dynamically, it is very difficult to pre-program cooperation strategies between robot agents. Q-learning - one of the most representative reinforcement learning methods - is shown to be effective for solving problems dynamically without explicit knowledge of the system. Therefore, in our research, a Q-learning based learning method has been utilized. Prior to utilizing Q-teaming, state variables describing the game situation and actions' sets of robots have been defined. After the learning process, the human operator could play the game more easily. To evaluate the usefulness of the proposed strategy, some simulations and games have been carried out.

• 한국콘텐츠학회논문지
• /
• 제21권1호
• /
• pp.531-540
• /
• 2021

사이버 상의 공격과 범죄가 기하급수적으로 증가와 해킹 공격들이 지능화, 고도화되면서 해킹 공격방법 및 루트가 복자하고 예측 불가능하게 진화하고 있어 실시간으로 범죄 발생을 예측, 예방과 대규모의 지능적인 해킹 공격에 대한 선제적 대응력 강화하기 위해 스스로 학습해 이상 징후를 감시 및 공격을 차단하여 대응하는 인공지능을 활용한 차세대 보안 시스템 구축을 통한 인공지능기반 보안관제 플랫폼 개발 방안을 제시하고자 한다. 인공지능기반 보안관제 플랫폼은 데이터 수집, 데이터 분석, 차세대 보안체계 운영, 보안체계 관리 등의 기반으로 개발되어야 한다. 빅데이터 기반과 관제시스템, 외부위협정보를 통한 데이터 수집 단계, 수집된 데이터를 전처리 후 정형화시켜 딥러닝 기반 알고리즘을 통해 정·오탐 선별과 이상행위 분석 등을 수행하는 데이터 분석 단계, 분석된 데이터로 통해 예방·관제·대응·분석과 유기적 순환구조의 보안체계를 운영하여 신규위협에 대한 처리범위 및 속도향상을 높이고 정상기반과 비정상행위 식별 등을 강화시키는 차세대 보안체계 운영, 그리고 보안위협 대응 체계 관리, 유해IP 관리, 탐지정책 관리, 보안업무 법제도 관리이다. 이를 통해 방대한 데이터를 통합적으로 분석하고 빠른 시간에 선제적으로 대처가 될 수 있도록 방안을 모색하고자 한다.

• 한국가스학회지
• /
• 제27권2호
• /
• pp.49-56
• /
• 2023

4차 산업혁명으로 인공지능(AI, Artificial Intelligence) 관련 기술이 고도로 성장함에 따라 여러 분야에서 AI를 접목하는 사례가 증가하고 있다. 주요 원인은 정보통신기술이 발달됨에 따라 기하급수적으로 증가하는 데이터를 사람이 직접 처리·분석하는데 현실적인 한계가 있고, 새로운 기술을 적용하여 휴먼 에러에 대한 리스크도 감소시킬 수 있기 때문이다. 이번 연구에서는 '원격 전위 측정용터미널(T/B, Test Box)'로부터 수신된 데이터와 해당시점의 '원격 정류기' 출력을 수집 후, AI가 학습하도록 하였다. AI의 학습 데이터는 최초 수집된 데이터의 회기분석을 통한 데이터 전처리로 확보하였고, 학습모델은 심층 강화학습(DRL, Deep Reinforce-ment Learning) 알고리즘 중(中) Value기반의 Q-Learning모델이 적용하였다. 데이터 학습이 완료된 AI는 실제 도시가스 공급지역에 투입하여, 수신된 원격T/B 데이터를 기반으로 AI가 적절하게 대응하는지 검증하고, 이를 통해 향후 AI가 전기방식 관리에 적합한 수단으로 활용될 수 있는지 검증하고자 한다.

• 한국환경교육학회지:환경교육
• /
• 제11권1호
• /
• pp.237-250
• /
• 1998

'Self-esteem' is defined as 'the lived status of one's individual competence and personal worthiness in dealing with the challenges of Life over Time'. High self-esteem is associated with self-confidence, effectively coping, well-being, and responsibility and it is essential for the responsible choice and determination of environments. The purposes of this study were to develop a strategy to enhance the self-esteem and to verify the effects. A new strategy, 'Cognitive Restructuring Strategy' was based on the characteristics of self-esteem and the key idea of this was to eliminate negative thoughts and to reinforce affirmative thoughts. We developed the statement to embody this strategy and applied to the experimental group. According to the results, self-esteem for the control group(155) did not changed but that for the experimental group(158) was significantly enhanced. Continuously, environmental learning instructions of 3 units were carried out on two groups. By applying the t-test, achievement-test scores for the experimental group per unit were significantly higher than those of the control group as regards the four respective goals of EE. Therefore this strategy and statement are helpful in enhancing self-esteem and it was found that 'self-esteem' is a influential factor to form environmental responsible behaviors(ERB).