• Title/Summary/Keyword: Q Value

Search Result 1,461, Processing Time 0.024 seconds

Solving Continuous Action/State Problem in Q-Learning Using Extended Rule Based Fuzzy Inference System

  • Kim, Min-Soeng;Lee, Ju-Jang
    • Transactions on Control, Automation and Systems Engineering
    • /
    • v.3 no.3
    • /
    • pp.170-175
    • /
    • 2001
  • Q-learning is a kind of reinforcement learning where the agent solves the given task based on rewards received from the environment. Most research done in the field of Q-learning has focused on discrete domains, although the environment with which the agent must interact is generally continuous. Thus we need to devise some methods that enable Q-learning to be applicable to the continuous problem domain. In this paper, an extended fuzzy rule is proposed so that it can incorporate Q-learning. The interpolation technique, which is widely used in memory-based learning, is adopted to represent the appropriate Q value for current state and action pair in each extended fuzzy rule. The resulting structure based on the fuzzy inference system has the capability of solving the continuous state about the environment. The effectiveness of the proposed structure is shown through simulation on the cart-pole system.

  • PDF

Initial Slot-Count Selection Scheme with Tag Number Estimation in Gen-2 RFID System

  • Lim, In-Taek;Ryu, Young-Tae
    • Journal of information and communication convergence engineering
    • /
    • v.8 no.5
    • /
    • pp.519-523
    • /
    • 2010
  • In Gen-2 RFID system, the initial value of $Q_{fp}$, which is the slot-count parameter of Q-algorithm, is not defined in the standard. In this case, if the number of tags within the reader's identification range is small and we let the initial $Q_{fp}$ be large, the number of empty slot will be large. On the other hand, if we let the initial $Q_{fp}$ be small in spite of many tags, almost all the slots will be collided. As a result, the performance will be declined because the frame size does not converge to the optimal point quickly during the query round. In this paper, we propose a scheme to allocate the optimal initial $Q_{fp}$ through the tag number estimation before the query round begins. Through computer simulations, it is demonstrated that the proposed scheme achieves more stable performance than Gen-2 Q-algorithm.

Performance Analysis of Q-Algorithm According to Weight in Gen-2 RFID System (Gen-2 RFID 시스템에서 가중치에 따른 Q-알고리즘의 성능 분석)

  • Lim, In-Taek
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2011.05a
    • /
    • pp.529-531
    • /
    • 2011
  • In Gen-2 Q-algorithm, the values of weight C, which is the parameter for incrementing or decrementing the slot-count size, are not defined in the standard. In this case, if the reader selects an inappropriate weight, there are a lot of empty or collided slots. As a result, the performance will be degraded because the frame size does not converge to the optimal point quickly during the query round. In this paper, we analyze how the performances of Gen-2 Q-algorithm will be affected by the weight value.

  • PDF

Area-Based Q-learning for Multiple Robots Control (다수 로봇 제어를 위한 면적 기반 Q-learning)

  • Yoon Han-Ul;Jang In-Hoon;Sim Kwee-Bo
    • Proceedings of the Korean Institute of Intelligent Systems Conference
    • /
    • 2005.04a
    • /
    • pp.198-201
    • /
    • 2005
  • 본 논문에서는 다수개의 로봇을 효율적으로 제어하기 위한 면적기반 Q-learning에 대해 논한다. 각 로봇은 $60^{\circ}$의 각을 이루도록 배치된 6개 센서를 가지고 있고 이를 통해 자신과 주변환경 사이의 거리를 센싱한다. 다음으로, 이 획득된 거리 데이터들로부터 6방향의 면적을 계산하여, 이후의 진행에 있어 보다 넓은 행동 반경을 보장해주는 영역으로 이동한다. 이 이동을 어떤 상태에서 다른 상태로의 전이로 간주, 이동 후 다시 6방향의 면적을 계산하여 이전 상태에서 현재 상태로의 행동에 대한 Q-Value를 업데이트 한다. 본 논문의 실험에서는 5개의 로봇을 이용해 장애물 사이에 숨어있는 물체를 찾아내는 것을 시도하였고, 3개의 서로 다른 제어 방법 - 랜덤 탐색, 면적 기반 탐색, 면적 기반 Q-learning 탐색 - 에 따른 결과를 나타내었다.

  • PDF

Investigation of sports for all requirement types of People with intellectual Disability: Focused On Q methodology (지적장애인의 생활체육 요구유형 탐색: Q방법론을 중심으로)

  • Kim, Hye-Min;Kim, So-Hyung;Park, Jin-Woo;Lee, Hyun-Su
    • 한국체육학회지인문사회과학편
    • /
    • v.54 no.1
    • /
    • pp.597-609
    • /
    • 2015
  • The purpose of this research is to analyze requirements for sports for all of the intellectually handicapped and their characteristics. Subjects for this study consisted of 33 undergraduate students who belonged to the department of physical education in P University. The Q-population a total of 28 people were selected including 16 handicapped college students from P welfare center and 12 members from the vocational adjustment class. The card used in Q sort was 27 categories of sports for all suggested by the korea Paralympic Committee. The result of Q-sorting were coded and analysed using QUANL pc program. According to the research result, Firstly, the requirement types of sports for all of the intellectually handicapped revealed to be four types(The eigen values of the five types of attitudes are 5.6, 2.3, 1.9, and 1.7): Secondly, the characteristics for each five types were determined to be experiential-value Pursuing type(type 1), interest-value pursuing type(type 2), purpose0orientation pursign type(type 3) and Safety-oriented pursuing type(type 4). Through the characteristics of each of the five types. Such results of the research suggest that the demand of the mentally ills for sports for all can be diverse and there can be a variety of types based on the background factors.

Analysis on the Secondary Pre-Physical Education Teacher's Recognition for the Learning Athletics Using the Q Methodology (Q방법론을 활용한 중등예비체육교사의 육상운동에 대한 인식 연구)

  • Yu, Young-Seol
    • Journal of the Korea Convergence Society
    • /
    • v.11 no.4
    • /
    • pp.311-321
    • /
    • 2020
  • The purpose of this study was to analyze the recognition of secondary pre-physical education teachers' recognition for the learning athletics using Q methodology. P-sample was composed of 28 pre-secondary P·E teachers. The selected Q samples were arranged in the normal distribution form. The collected data were analyzed by factor analysis through varimax rotation using QUANL PC program. This study found four types of recognition on learning athletics. Type I is defined 'the type of recognition for education value.' Type II is defined 'the type of emphasizing assistant activities.' Type III is defined 'the type of an appeal difficulty to learn athletics skill.' Type IV is defined 'the type of emphasizing the basic movement value.' Based of the results of this study, the implications and direction to future research on athletics activities are suggested.

A Study on the Determination of Bearing Capacity of Polluted Soils with Various Concentrations (농도가 다른 오염지반의 지지력 결정에 관한 연구)

  • 안종필;박상범
    • Journal of the Korean Geotechnical Society
    • /
    • v.15 no.6
    • /
    • pp.57-69
    • /
    • 1999
  • This study investigates the existing theoretical backgrounds for bearing capacity determination according to the plasticity of soils when unsymmetrical surcharge is loaded on polluted soft soils. It also investigates the behavior of the displacement and bearing capacity by unsymmetrical surcharge on the Polluted soft soils. by comparing the analytical results and the actual measurements performed through the model test. Model tests were carried out as follows : soil tank, bearing frame and bearing plate are made for the test ; the water content in soil tank was kept constant while the contaminants in natural soils and polluted material were gradually increased ; unsymmetrical surcharge is increased at regular intervals and then the amounts of settlement, lateral displacement and upheaval are observed. In conclusion, the value of critical surcharge was expressed as $q_{ cr}= 2.78_{Cu}$ which was similar to those $Tschebotarioff(q_{cr}=3.0_{Cu)$ and $Meyerhof(q_{cr}=(B/2H+\pi/2_{Cu})$ had proposed. The value of ultimate capacity was expressed as $q_{ult}=4.84_{Cu}$ which was similar to that of Prandtl.

  • PDF

Partial Discharge Detection and Statistic Value Calculation of Power Cable Using Data Acquisition System (데이터 취득 시스템을 이용한 전력케이블의 부분방전 검출과 통계량 계산)

  • 조경순
    • Journal of the Korea Computer Industry Society
    • /
    • v.3 no.12
    • /
    • pp.1651-1658
    • /
    • 2002
  • Recently power cable used generally in Korea, because installation is very simple and it has high stability. It confirms to the requirements of IEEE std. 404-1993 by factory testing, but many problems of insulated cable systems are caused by internal defects of the joint part which have to be mounted ensile. Especially, fault rates are arise from impurities or voids. A suitable solution for a monitoring of power cable during the after-laying test and service is partial discharge detection. The artificial defects between cable joint(EPR) and insulator(XLPE) interface are considered in this research to investigating the partial discharge characteristics. ${\varphi}$-q-n properties were detected using data acquisition system and Maximum charge($q_{max}$), repetition rate(${\={n}$), average charge(${\={q}$), Unbalance rate of ${\={n}$ and ${\={q}$ are calculated in order to analysis partial discharge properties quantitatively from this statistic value.

  • PDF

Subjectivity of Hope among Korean Middle-Aged Adults (한국 중년성인의 희망에 관한 주관성)

  • Kim, Keum Sook
    • Journal of Digital Convergence
    • /
    • v.11 no.10
    • /
    • pp.629-638
    • /
    • 2013
  • The Purpose of this study was to discover type of hope among korean middle-aged adult and to identify the major threads that structure various patterns of hope experienced by them. It is necessary to understand that experiencing hope of middle-aged adult experiencing numerous problems and loss at the transition of life. Q-methodology involves five steps in its approach. Collected Q-statements are 112 from 200 adults through 4 open-ended questions. Among them, 34 statements were decided as a Q-sample, The Q-sorting was carried out in 21 middle-aged adults. Three types of subjective experiences of hope emerged as : (1) Passive Wish Type, (2) Positive Pragmatic Hope Type, (3) Active Internal Value-Oriented Hope Type.

Improvement on the estimation of workable-quantity per unit time for boring machine (기초공사 천공기계 시간당작업량 산정 개선방안)

  • Ahn, Bang-Ryul
    • Proceedings of the Korean Institute of Building Construction Conference
    • /
    • 2015.05a
    • /
    • pp.138-139
    • /
    • 2015
  • Human productivity of Boring Machine for stack is provided but not its hourly workable quantity(Q-value) in the Equipment ownership cost and expenses section of the Poom-Same that is used for construction cost estimation of public sectors in Korea, which leads to less realistic and subjective estimation for the works. The optimized Q-value of the machine is proposed as a result of thorough investigation into many of its operations.

  • PDF