Skip to content

Highlights

This page presents some projects developed in previous years that stand out for their innovation or quality.

Projects developed in 2025

Below is a list of some projects developed in 2025:

  • Plasticity Phenomenon: João Lucas and Pedro Pertusi study the phenomenon of loss of brain plasticity in Reinforcement Learning. Video link. This project was published in a paper at the NATIONAL MEETING ON ARTIFICIAL AND COMPUTATIONAL INTELLIGENCE (ENIAC 2025): https://doi.org/10.5753/eniac.2025.14347.
  • Applying Reinforcement Learning to Coverage Path Planning problems: Diego Azenha applied Reinforcement Learning to Coverage Path Planning problems, using the PPO algorithm. Video link.
  • AntHill: In this project André implements an environment composed of ants that need to find food in a given region. In addition, these ants emit pheromones marking the region where they have already passed. The goal is for the ants to cover the entire region to find the food. In the project, he also trains the ants using RL algorithms. Repository link.
  • Training a robot on the ROS2 platform: In this project Felipe Catapano and Rodrigo Patelli train a robotic agent on the ROS2 platform to perform navigation tasks. Video link.
  • Training agents for the iterated prisoner's dilemma: In this project João Lucas and Pedro Pertusi train agents for the iterated prisoner's dilemma. Video link.
  • Curriculum Learning in Reinforcement Learning Environments: In this project Gabriel Valentim investigates the effects of introducing Curriculum Learning (CL) into the reinforcement learning process. Repository link

Projects developed in 2024

Below is a list of some projects developed in 2024:

Published papers

List of articles published by students of this course:

  • CADORNIGA, João; PERTUSI, Pedro; BARTH, Fabrício. Reinforcement Learning and Loss of Plasticity Phenomenon in Coverage Path Planning Environments: An Exploratory Study. In: Proceedings of the 22nd National Meeting on Artificial and Computational Intelligence, p. 1962-1971, 2025. DOI: 10.5753/eniac.2025.14347.
  • Abreu, Leonardo; Carrete, Luis; Castanares, Manuel; Damiani, Enrico; Brancalion, Jose Fernando; Barth, Fabrício Jailson. Exploration and Rescue of Shipwreck Survivors using Reinforcement Learning-Empowered Drone Swarms. Spectrum (Brasília. 2000), v. 26, n. 1, p. 14-20, 2025. DOI: 10.55972/spectrum.v26i1.421.
  • ANDRADE, PEDRO HENRIQUE BRITTO ARAGÃO; RODRIGUES, RICARDO RIBEIRO; FALCÃO, RENATO LAFFRANCHI; DE OLIVEIRA, JORÁS CUSTÓDIO CAMPOS; Brancalion, Jose Fernando; Barth, Fabrício Jailson. Using Deep Reinforcement Learning to Coordinate Autonomous Maritime Search and Rescue Drones. In: The Latin American Workshop on Information Fusion, p. 1-4, 2024.
  • DE OLIVEIRA, JORÁS CUSTÓDIO CAMPOS; ANDRADE, PEDRO HENRIQUE BRITTO ARAGÃO; FALCÃO, RENATO LAFFRANCHI; RODRIGUES, RICARDO RIBEIRO; Brancalion, Jose Fernando; Barth, Fabrício Jailson. Reinforcement Learning Applied to Train Autonomous Maritime Search and Rescue Drones. In: 21st National Meeting on Artificial and Computational Intelligence, p. 328-339, 2024. DOI: 10.5753/eniac.2024.245030.
  • FALCÃO, RENATO LAFFRANCHI; DE OLIVEIRA, JORÁS CUSTÓDIO CAMPOS; ANDRADE, PEDRO HENRIQUE BRITTO ARAGÃO; RODRIGUES, RICARDO RIBEIRO; Barth, Fabrício Jailson; BRANCALION, JOSÉ FERNANDO BASSO. DSSE: An environment for simulation of reinforcementlearning-empowered drone swarm maritime search and rescuemissions. Journal of Open Source Software, v. 9, n. 99, p. 6746-6750, 2024. DOI: 10.21105/joss.06746.
  • Abreu, Leonardo; Carrete, Luis; Castanares, Manuel; Damiani, Enrico; Brancalion, Jose Fernando; Barth, Fabrício Jailson. Exploration and Rescue of Shipwreck Survivors using Reinforcement Learning-Empowered Drone Swarms. In: XXV Simpósio de Aplicações Operacionais em Áreas de Defesa, p. 64-69, 2023.