Postdoc Machine Learning Researcher Advanced Institute for Artificial Intelligence - AI2
São Paulo State University (UNESP), Brazil
Last Update in: December 15th, 2019.
Currently, I am a Postdoc Machine Learning Researcher at the Advanced Institute for Artificial Intelligence (AI2). I hold Ms.c. and Ph.D. degrees from the University of São Paulo, Brazil, where I was advised by Professor Anna Reali Costa. During 2018-2019, I was a Visiting Researcher at the University of Texas at Austin, where I worked with Professor Peter Stone. I also interned at Borealis AI, where I did research related to my thesis topic with Matthew Taylor.
Transfer Learning in Multiagent Reinforcement Learning Systems
Reinforcement Learning is a powerful and autonomous tool to train intelligent agents.
This learning is initially performed by successive interactions between agents and the environment in a trial and error manner until the agent has enough information to perform its tasks.
However, when multiple agents are present in the same environment some sort of coordination is required since the environment becomes non-stationary. Centralized approaches are usually infeasible, as the state space can be huge even for simple problems.
Thus, distributed approaches are required for many Multiagent domains.
This research aims to develop a framework to accelerate learning in Multiagent Reinforcement Learning Systems by applying Transfer Learning, which has been successfully applied in Single Agent domains but has no robust algorithm to complex Multiagent domains.
Automated Bee Species Identification through Wing Images
Bees have a huge importance to pollination, which motivated research focused on their conservation.
However, some bee species are so similar that only a few specialized taxonomists are able to make a proper discrimination.
This project studied computer vision and machine learning methods applied to bee wing images to discriminate bee species.
I'm not working on this project as a first author anymore, but I've been advising undergraduate research projects on this topic.
HLF Outstanding Young Researcher, invited to the 6th Heidelberg Laureate Forum (HLF), 2018.
BRACIS Best Paper Award 1st place: "Object-Oriented Reinforcement Learning in Cooperative Multiagent Domains", Brazilian Conference on Intelligent Systems (BRACIS), 2016.
AAAI Best Student Poster - Honarable Mention, "An Advising Framework for Multiagent Reinforcement Learning Sytems", AAAI Conference on Artificial Intelligence, 2017.
WPG-EC Distinguished Research Project Workshop on Graduate studies in Computer Engineering of the University of São Paulo (WPG-EC), 2013, 2014, 2017.
Hackaton First Place: 311 Calls and 500 Cities Data Science Hackaton, The University of Texas at Austin, 2018.
Music I've been playing electric guitar since I was 15 years old. Even though I'm far from claiming to be in a professional level, you can count on me if you want to have fun playing some old good heavy metal.
Horror Movies I was just a little boy when I first watched "Night of the living dead". Thereafter I cannot spend a week without watching a B movie (specially the brain-eater zombie ones).