جستجوی مقالات مرتبط با کلیدواژه « یادگیری تقویتی » در نشریات گروه « فناوری اطلاعات »

Energy consumption in data centers and systems is increasing rapidly, which is a fundamental issue in the present age. An important advantage of distribution systems is cost savings because they do not require the initial installation and commissioning of resources and are scalable and flexible, but Load balance and scheduling are a challenge in distribution systems. This paper presents a method for scheduling tasks on dynamically available resources and the system uses continuous learning for best performance. In the proposed method, the Actor-Critic is used to improve decision making in reinforcement learning to extract the rules of distribution and use them in reinforcement learning to improve and facilitate energy efficiency goals. The proposed method was compared with the method presented in the same work in terms of "Completion time of all tasks " and "energy consumption" criteria. In th e evaluations, the energy consumption of the proposed method was more appropriate than the compared method. In environments where queue length is formed and resources and requests change rapidly, this energy consumption increases slightly due to the increasing number of scenarios and continuous learning. In general, the proposed method is suitable for stable environments, low changes or more balanced time intervals Because the learning process takes time.

This paper mainly aims to determine the optimal drug dosage for the purpose of reducing the population of cancer cells in melanoma patients. To do so, Reinforcement Learning method and the eligibility traces algorithm are employed, giving us the advantage of creating a compromise between the two algorithms of the reinforcement learning, being Monte-Carlo and Temporal Difference. Furthermore, it can be said that using this approach, there was no need to employ a mathematical model in the whole process. However, as its implementation on the real system was not possible, a delayed nonlinear mathematical model is used to investigate the performance of the proposed controller and simulate the behavior of the environment. It should be noted this mathematical model made use of no control method. This is the first time that population control of cancer cells is applied and tested on this model. To know of the optimal dosage of the drug, it should be mentioned that the drug is required to prevent the side effects on healthy/normal cells as much as possible. According to the obtained results, the eligibility traces algorithm is able to control and reduce the population of cancer cells through injecting the sub-optimal drug dose. This will increase the level of immunity in our body. Finally, to demonstrate the advantage of a selective method of increasing the rate of cancer cell death, this method is compared with the Q-learning algorithm and optimal control. By applying the fault to the sensor, the performance of the proposed controller to reduce cancer cells was investigated. The adaptability of the proposed method with the environment changes is checked afterwards. To this end, uncertainty in the system parameters and initial conditions are applied and the population of cancer cells are controlled in five melanoma patients. Moreover, having added noise to the system, it was shown that the eligibility traces algorithm is able to control the population of cancer cells and make it reach zero. Additionally, the convergence speed of both eligibility traces algorithm and Q learning algorithm in reducing the number of cancer cells for different learning rates was investigated.

Nowadays, the prisoner’s dilemma is one of the primary and important issues in game theory. In this dilemma, there is a Nash Equilibrium, and if the agents behave rationally, they play at point; For this purpose, the agents choose defection between the two actions of cooperation and defection to achieve greater profit. However there is a better point for the agents than the Nash Equilibrium, it is that both agents choose the cooperation. However there is a better point for the agents than the Nash Equilibrium, it is that both agents choose the cooperation. Therefore, in order to increase the rate of cooperation of the agents, the prisoner's dilemma has been considered as iterated prisoner's dilemma with a reinforcement learning approach. The results of the article show that the desired approach let has increased the rate of cooperation of the agents, and if one agent choose the cooperation, the other agent also chooses cooperation and vice versa.