• Title/Summary/Keyword: state value

Search Result 3,872, Processing Time 0.029 seconds

Reinforcement learning Speedup method using Q-value Initialization (Q-value Initialization을 이용한 Reinforcement Learning Speedup Method)

  • 최정환
    • Proceedings of the IEEK Conference
    • /
    • 2001.06c
    • /
    • pp.13-16
    • /
    • 2001
  • In reinforcement teaming, Q-learning converges quite slowly to a good policy. Its because searching for the goal state takes very long time in a large stochastic domain. So I propose the speedup method using the Q-value initialization for model-free reinforcement learning. In the speedup method, it learns a naive model of a domain and makes boundaries around the goal state. By using these boundaries, it assigns the initial Q-values to the state-action pairs and does Q-learning with the initial Q-values. The initial Q-values guide the agent to the goal state in the early states of learning, so that Q-teaming updates Q-values efficiently. Therefore it saves exploration time to search for the goal state and has better performance than Q-learning. 1 present Speedup Q-learning algorithm to implement the speedup method. This algorithm is evaluated. in a grid-world domain and compared to Q-teaming.

  • PDF

Proximate Analysis of Ipomea Batatass L. Grown in Two Different Zones in Imo State

  • meoka, N.U.;Ogbonnaya, C.I.;Ohazurike, N.C.
    • The Korean Journal of Food & Health Convergence
    • /
    • v.5 no.1
    • /
    • pp.13-19
    • /
    • 2019
  • Proximate analysis of Ipomea batatass L. grown in two different locations in Imo State were investigated. Standard soil analytical method was used to determine the physiochemical contents of the two soil sample collected from Mgbidi and Orji Ipomea batatass L. farm land. The soil sand from Ipomea batatass L. root in Orji farm recorded highest percentage value of 75.00% compared to the soil sand Ipomea batatass L. root in Mgbidi farm with 27.00% value. The percentage value of silt was different as the soil Ipomea batatass L. root in Mgbidi farm had high value of 29.40% while soil silt of Ipomea batatass L. root in Orji farm had 13.40%. The soil clay, pH, Phosphorus and Nitrogen from Ipomea batatass L. root in Mgbidi farm recorded highest percentage value of 43.60%, 5.7, 23.20 and 0.35 compared to the soil sand Ipomea root in Orji farm with 11.60%, 5.4, 16.70 and 0.09 value respectively. Ca, Mg, K, and Na analyzed followed the same trend as the soil from Ipomea root in Mgbidi farm had high percentage value of Ca (10.00), Mg (1.60), K (0.54) and Na (0.43) respectively. The systematic study of physiochemical of the Ipomea soils could help in understanding the nutritional composition, the basic characteristics of the soils and the constraints associated with the management of the soils from the two locations.

Development of Fault Detector for Series Arc Fault in Low Voltage DC Distribution System using Wavelet Singular Value Decomposition and State Diagram

  • Oh, Yun-Sik;Han, Joon;Gwon, Gi-Hyeon;Kim, Doo-Ung;Kim, Chul-Hwan
    • Journal of Electrical Engineering and Technology
    • /
    • v.10 no.3
    • /
    • pp.766-776
    • /
    • 2015
  • It is well known that series arc faults in Low Voltage DC (LVDC) distribution system occur at unintended points of discontinuity within an electrical circuit. These faults can make circuit breakers not respond timely due to low fault current. It, therefore, is needed to detect the series fault for protecting circuits from electrical fires. This paper proposes a novel scheme to detect the series arc fault using Wavelet Singular Value Decomposition (WSVD) and state diagram. In this paper, the fault detector developed is designed by using three criterion factors based on the RMS value of Singular value of Approximation (SA), Sum of the absolute value of Detail (SD), and state diagram. LVDC distribution system including AC/DC and DC/DC converter is modeled to verify the proposed scheme using ElectroMagnetic Transient Program (EMTP) software. EMTP/MODELS is also utilized to implement the series arc model and WSVD. Simulation results according to various conditions clearly show the effectiveness of the proposed scheme.

A VSR $\bar{X}$ Chart with Multi-state VSS and 2-state VSI Scheme

  • Lee, Jae-Heon;Park, Chang-Soon
    • Journal of Korean Society for Quality Management
    • /
    • v.32 no.4
    • /
    • pp.252-264
    • /
    • 2004
  • Variable sampling Interval (VSI) control charts vary the sampling interval according to value of the control statistic while the sample size is fixed. It is known that control charts with 2-state VSI scheme, which uses only two sampling intervals, give good statistical properties. Variable sample size (VSS) control charts vary the sample size according to value of the control statistic while the sampling interval is fixed. In the VSS scheme no optimal results are known for the number of sample sizes. It is also known that the variable sampling rate (VSR) $\bar{X}$ control chart with 2-state VSS and 2-state VSI scheme leads to large improvements In performance over the fixed sampling rate (FSR) $\bar{X}$ chart, but the optimal number of states for sample size Is not known. In this paper, the VSR Χ charts with multi-state VSS and 2-state VSI scheme are designed and compared to 2-state VSS and 2-state VSI scheme. The multi-state VSS scheme is considered to, achieve an additional improvement by switching from the 2-state VSS scheme. On the other hand, the multi-state VSI scheme is not considered because the 2-state scheme is known to be optimal. The 3-state VSS scheme improves substantially the sensitivity of the $\bar{X}$ chart especially for small and moderate mean shifts.

STABILITY OF POSITIVE STEADY-STATE SOLUTIONS IN A DELAYED LOTKA-VOLTERRA DIFFUSION SYSTEM

  • Yan, Xiang-Ping;Zhang, Cun-Hua
    • Journal of the Korean Mathematical Society
    • /
    • v.49 no.4
    • /
    • pp.715-731
    • /
    • 2012
  • This paper considers the stability of positive steady-state solutions bifurcating from the trivial solution in a delayed Lotka-Volterra two-species predator-prey diffusion system with a discrete delay and subject to the homogeneous Dirichlet boundary conditions on a general bounded open spatial domain with smooth boundary. The existence, uniqueness and asymptotic expressions of small positive steady-sate solutions bifurcating from the trivial solution are given by using the implicit function theorem. By regarding the time delay as the bifurcation parameter and analyzing in detail the eigenvalue problems of system at the positive steady-state solutions, the asymptotic stability of bifurcating steady-state solutions is studied. It is demonstrated that the bifurcating steady-state solutions are asymptotically stable when the delay is less than a certain critical value and is unstable when the delay is greater than this critical value and the system under consideration can undergo a Hopf bifurcation at the bifurcating steady-state solutions when the delay crosses through a sequence of critical values.

A Alternative Environmental Value Education Program through GENSANGGAI in JAPAN (연찬방식을 통한 대안적 환경가치교육방안)

  • 김태경
    • Hwankyungkyoyuk
    • /
    • v.12 no.1
    • /
    • pp.322-334
    • /
    • 1999
  • In environmental value education, the difference between Ecological and Economic view-point about environmentmust should be considered. Usually, although the differences are unavoidable, because our lifes are inclined to Economic life. But this propensity have become great obstacles to Environmental value education by diluting the fundamental reasons which the nature should be preserved. Furthermore we can't say that environmental problems are not solved just by economic approach, owing to its limits of solving by incentives. So we can say that it is very important to have equalized view-points in the relations of economics and ecology for balanced environmental value education. This study is to alternative environmental value education program, to have equalized view-points in the relations of economics and ecology through the small community located in Japan. The exact name of that program is GENSANGGAI. They have persued to attain a spiritual state of complete absence of ego through this program, and this spiritual state can be important environmental value educaton goal, which make the student to see the evironment with equalized view-points in the interdependence between economics and ecology. we can say that this program can be a kind affective (sentimentally perceived) environmental education program. It can be good environmental education program in affective domain. we can say that equalized view-points is to attain a spiritual state of complete absence of ego. This program is some similar to Kohlberg's latter term theory and Open educationin theory in substantial aspect, he persued Just Community Approach through Kibbutz in Israel. From the basis of his theory, if the GENSANGGAI program, which means harmony between socialization and development of moral stage, individualism and communism.

  • PDF

Identification of Parameter Errors in Electric Power Systems by WLAV State Estimation (WLAV 상태추정에 의한 전력계통 파라미터 에러 추정에 관한 연구)

  • Kim, Hong-Rae;Gwon, Hyeong-Seok;Kim, Dong-Jun
    • The Transactions of the Korean Institute of Electrical Engineers A
    • /
    • v.49 no.9
    • /
    • pp.451-458
    • /
    • 2000
  • This paper addresses the issues of the parameter error detection and identification in electric power systems. In this paper, the parameter error identification and estimation is carried out as part of the state estimation. A two stage estimation procedure is used to detect and identify the parameter errors. The suspected parameters are identified by the WLAV state estimator as the first stage. A new WLAV state estimator adding the suspected system parameters in the state vector is used to estimate the exact value of parameter errors. Supporting examples are given by using IEEE 14 bus system.

  • PDF

A design of target tracking filter using bearing-only (방위각만을 이용한 표적 추적 필터 설계)

  • 이양원;김경기;김영수
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 1987.10b
    • /
    • pp.562-565
    • /
    • 1987
  • This paper addresses the development of the estimation algorithm to acquire target position, velocity and course using bearing-only measurements in two dimensional environment. System state equations are derived from modified polar coordinates instead of existing Cartesian coordinates system. The Extended Kalman Filter is used to constitute the estimation algorithm because of state equation's nonlinearity. The computer simulation is done to verify the performance of derived algorithm. Simulation result showed that estimated state value of filter was converged to the true value in 10 minutes.

  • PDF

Effects of cultivar and harvest days after planting on dry matter yield and nutritive value of teff

  • Saylor, Benjamin A;Min, Doohong;Bradford, Barry J
    • Journal of Animal Science and Technology
    • /
    • v.63 no.3
    • /
    • pp.510-519
    • /
    • 2021
  • One of the most pressing issues facing the dairy industry is drought. In areas where annual precipitation is low, irrigation for growing feed presents the greatest water-utilization challenge for dairy producers. Here, we investigated the effects of cultivar and harvest days after planting (DAP) on dry matter (DM) yield and nutritive value of teff (Eragrostis tef), a warm-season annual grass native to Ethiopia that is well adapted to drought conditions. Eighty pots were blocked by location in a greenhouse and randomly assigned to four teff cultivars (Tiffany, Moxie, Corvallis, and Dessie) and to five harvest times (40, 45, 50, 55, or 60 DAP). Cultivars had no effect on DM yield and nutritive value. As harvest time increased from 40 to 60 DAP, DM yield and ash-free neutral detergent fiber (aNDFom) concentrations increased, while crude protein (CP) concentrations and in vitro NDF digestibility decreased. To assess carryover effects of time of harvest on yield and nutritive value, two additional cuttings were taken from each pot. Increasing first-cutting harvest time decreased CP concentrations in the second cutting and reduced DM yields in the second and third cutting. Harvesting teff between 45 and 50 DAP best optimized forage yield and nutritive value in the first and subsequent cuttings.

H.P.L. Value in Serum of Normal Pregnancy and Pospartum State by Hemagglutination-Inhibition Reaction (정상(正常) 임산부(妊産婦)의 혈청중(血淸中) H.P.L.의 면역학적(免疫學的) 측정(測定)에 관(關)한 연구(硏究))

  • Chung, Ae-Rhee;Shin, Myun-Woo
    • Clinical and Experimental Reproductive Medicine
    • /
    • v.3 no.1
    • /
    • pp.13-19
    • /
    • 1976
  • Serum levels of human placental lactogen have been measured by hemagglutination-inhibition reaction in 67 normal pregnant state and in 15 postpartum 24 hour state, HAIR is less sensitive and reliable method than radioimmunoassay, but simple, rapid, less expensive and fairly accurate, so it is more helpful in screening of large antenatal population with or without high risk complications. 1) Sensitivity of HPL-HAIR test kit was $0.1{\mu}g$/ml of H.P.L. serum level and had no cross reaction to HCG or male serum or non-pregenant female or newborn infant, 2) H.P.L. value was around $2{\mu}g$/ml until 24th week of pregnancy and rose to $6{\sim}8$ ${\mu}g$/ml continuously until about 36th week of pregnancy and then slightly decreased or stationary. 3) H.P.L. value in postpartum 24 hour state was undetectable. 4) There was poor correlation between maternal serum H.P.L. value at term and baby weight.

  • PDF