https://rodrigoclira.github.io/tags/phd/ Phd HugoBlox Kit (https://hugoblox.com)pt-brThu, 22 Jun 2023 10:18:25 -0300 https://rodrigoclira.github.io/media/icon_hu_b22adc9a7ee7cc2a.png https://rodrigoclira.github.io/tags/phd/ https://rodrigoclira.github.io/blog/2023/rl-material/ Thu, 22 Jun 2023 10:18:25 -0300 https://rodrigoclira.github.io/blog/2023/rl-material/ <p>Eu estou usando Aprendizam Por Reforço (do inglês, Reinforcement Learning) na minha tese de doutorado e no processo de aprendizado eu acabei encontrando muitos materias interessantes na internet. Resolvi fazer uma listagem deles para deixar público e também me ajudar em consultas futuras.</p> <hr> <p>Para quem estiver procurando conhecimento teórico, eu sugiro os livros:</p> <ul> <li> de Sutton e Barto</li> <li> de Szepesvari</li> </ul> <p>Para quem quiser conhecer um pouco da teoria ao mesmo tempo que desenvolve projetos práticos com Python:</p> <ul> <li> <p> do Hugginfaces</p> </li> <li> <p> com RLLib</p> </li> <li> <p> do Dibya.</p> </li> <li> <p> </p> </li> </ul> <p>* Há também o curso que eu não realizei.</p> <p>Disciplinas em instituições:</p> <ul> <li> </li> <li> </li> <li> </li> <li> </li> </ul> https://rodrigoclira.github.io/blog/2021/lacci2021/ Sun, 26 Sep 2021 23:57:14 -0300 https://rodrigoclira.github.io/blog/2021/lacci2021/ <p>O artigo &ldquo;Modelling the Social Interactions in Grey Wolf Optimizer&rdquo; foi aceito no .</p> <p>Autores: <strong>Rodrigo C. Lira</strong>, Mariana Macedo, Hugo Valadares Siqueira. Ronaldo Menezes, Carmelo Bastos-Filho</p> <p>Abstract: &ldquo;Swarm Intelligence has been successfully used forsolving high-dimensional and multimodal optimization problems.However, the wide range of swarm-based techniques, operators,and parameters requires prior knowledge before applying themto real-world problems. Because of this, we have been study-ing the meso-level characteristics that emerge from the socialinteractions within the swarm to understand each swarm-basedtechnique’s unique characteristics. In this paper, we model andstudy the interaction network of the Grey Wolf Optimizer (GWO)to capture its social behaviour. We used Portrait divergence tocompare the similarity between network structures over exper-iments, simulations and iterations of the GWO. We also usedKullback divergence to compare the probability distributions ofthe network flows varying over experiments, simulations anditerations of the GWO. Furthermore, we discovered we couldidentify the GWO convergence using the interaction networkapproach. Comparing different simulations, we found that thewolves communicate using a stable network structure but notnecessarily a stable network flow indicating variance in thenumber of highly influential wolves. We also point out patternsfound in GWO that appears to be similar to other swarm-basedalgorithms (GPSO and FSS).&rdquo;</p>