Estratégias de busca reativa utilizando aprendizagem por reforço e algoritmos de busca local

Técnicas de otimização conhecidas como as metaheurísticas tem conseguido resolversatisfatoriamente problemas conhecidos, mas desenvolvimento das metaheurísticas écaracterizado por escolha de parâmetros para sua execução, na qual a opção apropriadadestes parâmetros (valores). Onde o ajuste de parâmetro é essencial testa-se os parâmetrosaté que resultados viáveis sejam obtidos, normalmente feita pelo desenvolvedor que estaimplementando a metaheuristica. A qualidade dos resultados de uma instância1 de testenão será transferida para outras instâncias a serem testadas e seu feedback pode requererum processo lento de “tentativa e erro” onde o algoritmo têm que ser ajustado para umaaplicação especifica. Diante deste contexto das metaheurísticas surgiu a Busca Reativaque defende a integração entre o aprendizado de máquina dentro de buscas heurísticaspara solucionar problemas de otimização complexos. A partir da integração que a BuscaReativa propõe entre o aprendizado de máquina e as metaheurísticas, surgiu a ideia dese colocar a Aprendizagem por Reforço mais especificamente o algoritmo Q-learning deforma reativa, para selecionar qual busca local é a mais indicada em determinado instanteda busca, para suceder uma outra busca local que não pode mais melhorar a soluçãocorrente na metaheurística VNS. Assim, neste trabalho propomos uma implementação reativa,utilizando aprendizado por reforço para o auto-tuning do algoritmo implementado,aplicado ao problema do caixeiro viajante simétrico e ao problema escalonamento sondaspara manutenção de poços.

Técnicas de conformação de feixe em arranjo de antenas utilizando aprendizagem por reforço

Beamforming is a technique widely used in various fields. With the aid of an antenna array, the beamforming aims to minimize the contribution of unknown interferents directions, while capturing the desired signal in a given direction. In this thesis are proposed beamforming techniques using Reinforcement Learning (RL) through the Q-Learning algorithm in antennas array. One proposal is to use RL to find the optimal policy selection between the beamforming (BF) and power control (PC) in order to better leverage the individual characteristics of each of them for a certain amount of Signal to Interference plus noise Ration (SINR). Another proposal is to use RL to determine the optimal policy between blind beamforming algorithm of CMA (Constant Modulus Algorithm) and DD (Decision Direct) in multipath environments. Results from simulations showed that the RL technique could be effective in achieving na optimal of switching between different techniques.

O jogo dos discos: o uso da experimentação como suporte para o ensino da probabilidade

In this paper we propose a class for introducing the probability teaching using the game discs which is based on the concept of geometric probability and which is supposed to determine the probability of a disc randomly thrown does not intercept the lines of a gridded surface. The problem was posed to a group of 3nd year of the Federal Institute of Education, Science and Technology of Rio Grande do Norte - Jo~ao C^amara. Therefore, the students were supposed to build a grid board in which the success percentage of the players had been previously de ned for them. Once the grid board was built, the students should check whether that theoretically predetermined percentage corresponded to reality obtained through experimentation. The results and attitude of the students in further classes suggested greater involvement of them with discipline, making the environment conducive for learning.

O jogo dos discos: o uso da experimentação como suporte para o ensino da probabilidade

In this paper we propose a class for introducing the probability teaching using the game discs which is based on the concept of geometric probability and which is supposed to determine the probability of a disc randomly thrown does not intercept the lines of a gridded surface. The problem was posed to a group of 3nd year of the Federal Institute of Education, Science and Technology of Rio Grande do Norte - Jo~ao C^amara. Therefore, the students were supposed to build a grid board in which the success percentage of the players had been previously de ned for them. Once the grid board was built, the students should check whether that theoretically predetermined percentage corresponded to reality obtained through experimentation. The results and attitude of the students in further classes suggested greater involvement of them with discipline, making the environment conducive for learning.

Obtenção e caracterização de um compósito polimérico de matriz poliéster e reforço/carga de tecido plano de algodão

He was obtained and studied the feasibility of using TPA (Tissue Cotton Plan) screen type, for bagging, with a weight of 207.9 g / m2 in a composite of orthophthalic crystal polyester resin matrix. The process for obtaining the composite was tested against the maximum number of layers that could be used without compromising the processability and manufacturing of CPs in compression mold. Five configurations / formulations were selected and tested at 1, 4, 8, 10 and 12 layers of cotton tissue - TPA. TPA was not subjected to chemical treatment, only by passing a mechanical washing process. The composite in its various configurations / formulations was characterized to determine its physical properties. The properties of the composite were higher viability resistance to bending, approaching the matrix and impact resistance, superiority in relation to the polyester resin. Another property that has shown good result compared to other composite has water absorption. Analyzing all the properties set the settings / formulations with higher viability were TA8 and TA10, by combining good processability and higher mechanical strength, with lower loss compared to polyester resin matrix. The composite showed lower mechanical behavior of the resin matrix for all the formulations studied except the impact resistance. The SEM showed a good adhesion between the layers of TPA and polyester resin matrix, without the presence of micro voids in the matrix confirming the efficient manufacturing process of the samples for characterization. The composite proposed proved to be viable for the fabrication of structures with low requests from mechanical stresses, and as demonstrated for the manufacture of solar and wind prototypes, and packaging, shelving, decorative items, crafts and shelves, with good visual appearance.

Obtenção e caracterização de um compósito polimérico de matriz poliéster e reforço/carga de tecido plano de algodão

He was obtained and studied the feasibility of using TPA (Tissue Cotton Plan) screen type, for bagging, with a weight of 207.9 g / m2 in a composite of orthophthalic crystal polyester resin matrix. The process for obtaining the composite was tested against the maximum number of layers that could be used without compromising the processability and manufacturing of CPs in compression mold. Five configurations / formulations were selected and tested at 1, 4, 8, 10 and 12 layers of cotton tissue - TPA. TPA was not subjected to chemical treatment, only by passing a mechanical washing process. The composite in its various configurations / formulations was characterized to determine its physical properties. The properties of the composite were higher viability resistance to bending, approaching the matrix and impact resistance, superiority in relation to the polyester resin. Another property that has shown good result compared to other composite has water absorption. Analyzing all the properties set the settings / formulations with higher viability were TA8 and TA10, by combining good processability and higher mechanical strength, with lower loss compared to polyester resin matrix. The composite showed lower mechanical behavior of the resin matrix for all the formulations studied except the impact resistance. The SEM showed a good adhesion between the layers of TPA and polyester resin matrix, without the presence of micro voids in the matrix confirming the efficient manufacturing process of the samples for characterization. The composite proposed proved to be viable for the fabrication of structures with low requests from mechanical stresses, and as demonstrated for the manufacture of solar and wind prototypes, and packaging, shelving, decorative items, crafts and shelves, with good visual appearance.

Caracterização de atapulgita visando aplicação para reforço de materiais poloméricos

The clay mineral attapulgite is a group of hormitas, which has its structures formed by microchannels, which give superior technological properties classified the industrial clays, clays of this group has a very versatile range of applications, ranging from the drilling fluid for wells oil has applications in the pharmaceutical industry. Such properties can be improved by activating acid and / or thermal activation. The attapulgite when activated can improve by up to 5-8 times some of its properties. The clay was characterized by X-ray diffraction, fluorescence, thermogravimetric analysis, differential thermal analysis, scanning electron microscopy and transmission electron microscopy before and after chemical activation. It can be seen through the results the efficiency of chemical treatment, which modified the clay without damaging its structure, as well as production of polymer matrix composites with particles dispersed atapugita

Uma aplicação da apredizagem por reforço na otimização da produção em um campo de petróleo

The objective of reservoir engineering is to manage fields of oil production in order to maximize the production of hydrocarbons according to economic and physical restrictions. The deciding of a production strategy is a complex activity involving several variables in the process. Thus, a smart system, which assists in the optimization of the options for developing of the field, is very useful in day-to-day of reservoir engineers. This paper proposes the development of an intelligent system to aid decision making, regarding the optimization of strategies of production in oil fields. The intelligence of this system will be implemented through the use of the technique of reinforcement learning, which is presented as a powerful tool in problems of multi-stage decision. The proposed system will allow the specialist to obtain, in time, a great alternative (or near-optimal) for the development of an oil field known