Imitation learning is an effective method for training an autonomous agent to accomplish a task by imitating expert behaviors in their demonstrations. However, traditional imitation learning methods require a large number of expert demonstrations in order to learn a complex behavior. Such a disadvantage has limited the potential of imitation learning in complex tasks where the expert demonstrations are not sufficient. In order to address the problem, we propose a Generative Adversarial Network-based model which is designed to learn optimal policies using only a single demonstration. The proposed model is evaluated on two simulated tasks in comparison with other methods. The results show that our proposed model is capable of completing considered tasks despite the limitation in the number of expert demonstrations, which clearly indicate the potential of our model.
QJ Rashid, IH Abdul-Abbas, MR Younus, PalArch's Journal of Archaeology of Egypt/Egyptology, 2021 - Cited by 4
DBN Rashid, IMPAT: International Journal of Research in Humanities, Arts, and Literature, 2016 - Cited by 5
Analyzing sentiment and emotions in Arabic texts on social networking sites has gained wide interest from researchers. It has been an active research topic in recent years due to its importance in analyzing reviewers' opinions. The Iraqi dialect is one of the Arabic dialects used in social networking sites, characterized by its complexity and, therefore, the difficulty of analyzing sentiment. This work presents a hybrid deep learning model consisting of a Convolution Neural Network (CNN) and the Gated Recurrent Units (GRU) to analyze sentiment and emotions in Iraqi texts. Three Iraqi datasets (Iraqi Arab Emotions Data Set (IAEDS), Annotated Corpus of Mesopotamian-Iraqi Dialect (ACMID), and Iraqi Arabic Dataset (IAD)) col
... Show MoreThe proliferation of many editing programs based on artificial intelligence techniques has contributed to the emergence of deepfake technology. Deepfakes are committed to fabricating and falsifying facts by making a person do actions or say words that he never did or said. So that developing an algorithm for deepfakes detection is very important to discriminate real from fake media. Convolutional neural networks (CNNs) are among the most complex classifiers, but choosing the nature of the data fed to these networks is extremely important. For this reason, we capture fine texture details of input data frames using 16 Gabor filters indifferent directions and then feed them to a binary CNN classifier instead of using the red-green-blue
... Show MoreBackground: The efficacy of educational strategies is crucial for nursing students to competently perform pediatric procedures like nasogastric tube insertion. Specific Background: This study evaluates the effectiveness of simulation, blended, and self-directed learning strategies in enhancing these skills among nursing students. Knowledge Gap: Previous research lacks a comprehensive comparison of these strategies' impacts on skill development in pediatric nursing contexts. Aims: The study aims to assess the effectiveness of different educational strategies on nursing students' ability to perform pediatric nasogastric tube insertions. Methods: A pre-experimental design was employed at the College of Nursing, University of Baghdad, i
... Show MoreNatural convection in a trapezoidal enclosure with partial heating from below and symmetrical cooling from the sides has been investigated numerically. The heating is simulated by a centrally located heat source on the bottom wall, and four different values of the dimensionless heat source length, 1/5, 2/5, 3/5, 4/5 are considered. The laminar flow field is analyzed numerically by solving the steady, two-dimensional incompressible Navier-Stokes and energy equations. The Cartesian velocity components and pressure on a collocated (non-staggered) grid are used as dependent variables in the momentum equations discretized by finite volume method; body fitted coordinates are used to represent the trapezoidal enclosure, and grid generatio
... Show MoreIn practical engineering problems, uncertainty exists not only in external excitations but also in structural parameters. This study investigates the influence of structural geometry, elastic modulus, mass density, and section dimension uncertainty on the stochastic earthquake response of portal frames subjected to random ground motions. The North-South component of the El Centro earthquake in 1940 in California is selected as the ground excitation. Using the power spectral density function, the two-dimensional finite element model of the portal frame’s base motion is modified to account for random ground motions. A probabilistic study of the portal frame structure using stochastic finite elements utilizing Monte Carlo simulation
... Show MoreTrajectory tracking and vibration suppression are essential objectives in a flexible joint manipulator control. The flexible joint manipulator is an under-actuated system, in which the number of control actions is less than the degree of freedom to be controlled. It is very challenging to control the underactuated nonlinear system with two degree of freedom. This paper presents a hierarchical sliding mode control (HSMC) for a rotary flexible joint manipulator (RFJM). Firstly, the rotary flexible joint manipulator is modeled by two subsystems. Secondly, the sliding surfaces for both subsystems are constructed. Finally, the control action is designed based on the Lyapunov function. Computer simulation results demonstrate the effectiveness of
... Show MoreAs the process of estimate for model and variable selection significant is a crucial process in the semi-parametric modeling At the beginning of the modeling process often At there are many explanatory variables to Avoid the loss of any explanatory elements may be important as a result , the selection of significant variables become necessary , so the process of variable selection is not intended to simplifying model complexity explanation , and also predicting. In this research was to use some of the semi-parametric methods (LASSO-MAVE , MAVE and The proposal method (Adaptive LASSO-MAVE) for variable selection and estimate semi-parametric single index model (SSIM) at the same time .
... Show More