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 co

In this paper, a single-phase boost type ac-dc converter with power factor correction (PFC) technique is designed and implemented. A current mode control at a constant switching frequency is used as a control strategy for PFC converter. The PFC converter is a single-stage singleswitch boost converter that uses a current shaping technique to reshape the non-sinusoidal input current drawn by the bulky capacitor in the conventional rectifier. This technique should provide an input current with almost free-harmonics, comply with the IEC61000-3-2 limits, and a system operates with near unity power factor. The other function of the boost converter that should be
accomplished is to provide a regulated DC output voltage. The complete designed

Roof in the Iraqi houses normally flattening by a concrete panel. This concrete panel has poor thermal properties. The usage of materials with low thermal conductivity and high specific heat gives a good improvements to the thermal properties of the concrete panel, thus, the indoor room temperature improves. A Mathcad program based on a mathematical model employing complex Fourier series built for a single room building. The model input data are the ambient temperature, solar radiation, and sol-air temperature, which have been treated as a periodic function of time. While, the room construction is constant due to their materials made of it, except the roof properties are taken as a variable generated practically from the

The performance of single and two stage solar concentrator were studied ' " The ratio of the primary to the secondary mirrors diameter is taking to be 0.5, depending on the theoretical calculation for the accumulated energy by the concentrator with ratio between 0.0 to 0.9. The design of the systems were designed and examined by using a ray-tracing program. The efficiency of the single and the two stage concentrators are calculated and compared with and without cooling systems.

The process of controlling a Flexible Joint Robot Manipulator (FJRM) requires additional sensors for measuring the state variables of flexible joints. Therefore, taking the elasticity into account adds a lot of complexity as all the additional sensors must be taken into account during the control process. This paper proposes a nonlinear observer that controls FJRM, without requiring equipment sensors for measuring the states. The nonlinear state equations are derived in detail for the FJRM where nonlinearity, of order three, is considered. The Takagi–Sugeno Fuzzy Model (T-SFM) technique is applied to linearize the FJRM system. The Luenberger observer is designed to estimate the unmeasured states using error correction. The develop

The Assignment model is a mathematical model that aims to express a real problem facing factories and companies which is characterized by the guarantee of its activity in order to make the appropriate decision to get the best allocation of machines or jobs or workers on machines in order to increase efficiency or profits to the highest possible level or reduce costs or time To the extent possible, and in this research has been using the method of labeling to solve the problem of the fuzzy assignment of real data has been approved by the tire factory Diwaniya, where the data included two factors are the factors of efficiency and cost, and was solved manually by a number of iterations until reaching the optimization solution,

This paper deals with constructing mixed probability distribution from mixing exponential