Zobrazeno 1 - 10
of 463
pro vyhledávání: '"Braga, Pedro"'
Autor:
Machado, Mateus G., Melo, João G., Zanchettin, Cleber, Braga, Pedro H. M., Cunha, Pedro V., Barros, Edna N. S., Bassani, Hansenclever F.
This work investigates the potential of Reinforcement Learning (RL) to tackle robot motion planning challenges in the dynamic RoboCup Small Size League (SSL). Using a heuristic control approach, we evaluate RL's effectiveness in obstacle-free and sin
Externí odkaz:
http://arxiv.org/abs/2404.15410
Autor:
Braga, Pedro, Chionas, Georgios, Leonardos, Stefanos, Krysta, Piotr, Piliouras, Georgios, Ventre, Carmine
Maximal Extractable Value (MEV) has emerged as a new frontier in the design of blockchain systems. The marriage between decentralization and finance gives the power to block producers (a.k.a., miners) not only to select and add transactions to the bl
Externí odkaz:
http://arxiv.org/abs/2402.15849
Reinforcement learning (RL) has shown great promise with algorithms learning in environments with large state and action spaces purely from scalar reward signals. A crucial challenge for current deep RL algorithms is that they require a tremendous am
Externí odkaz:
http://arxiv.org/abs/2212.08131
Most reinforcement learning algorithms take advantage of an experience replay buffer to repeatedly train on samples the agent has observed in the past. Not all samples carry the same amount of significance and simply assigning equal importance to eac
Externí odkaz:
http://arxiv.org/abs/2208.10483
Autor:
Quintino, Cláudio, Malheiros-Lima, Milene R., Ghazale, Poliana Peres, Braga, Pedro Paulo Pereira, Maia, Octávio A.C., de Oliveira, Carlos Eduardo Gonçalves, Andrade, Felipe Waks, Schoorlemmer, Guus H., Moreira, Thiago S., da Matta, David Henriques, Colugnati, Diego Basile, Pansani, Aline Priscila
Publikováno v:
In Epilepsy & Behavior August 2024 157
Autor:
Martins, Felipe B., Machado, Mateus G., Bassani, Hansenclever F., Braga, Pedro H. M., Barros, Edna S.
Reinforcement learning is an active research area with a vast number of applications in robotics, and the RoboCup competition is an interesting environment for studying and evaluating reinforcement learning methods. A known difficulty in applying rei
Externí odkaz:
http://arxiv.org/abs/2106.12895
Autor:
Khattar, Gabriel, Vaz, Stephanie, Braga, Pedro Henrique Pereira, Macedo, Margarete, da Silveira, Luiz Felipe Lima
Publikováno v:
Diversity and Distributions, 2022 Sep 01. 28(9), 1820-1831.
Externí odkaz:
https://www.jstor.org/stable/48682398
Autor:
Pena, Carlos H. C., Machado, Mateus G., Barros, Mariana S., Silva, José D. P., Maciel, Lucas D., Ren, Tsang Ing, Barros, Edna N. S., Braga, Pedro H. M., Bassani, Hansenclever F.
The IEEE Very Small Size Soccer (VSSS) is a robot soccer competition in which two teams of three small robots play against each other. Traditionally, a deterministic coach agent will choose the most suitable strategy and formation for each adversary'
Externí odkaz:
http://arxiv.org/abs/2011.11785
Autor:
Bassani, Hansenclever F., Delgado, Renie A., Junior, José Nilton de O. Lima, Medeiros, Heitor R., Braga, Pedro H. M., Machado, Mateus G., Santos, Lucas H. C., Tapp, Alain
This article introduces an open framework, called VSSS-RL, for studying Reinforcement Learning (RL) and sim-to-real in robot soccer, focusing on the IEEE Very Small Size Soccer (VSSS) league. We propose a simulated environment in which continuous or
Externí odkaz:
http://arxiv.org/abs/2008.12624