Lucas Alegre
Professor at Federal University of Rio Grande do Sul
Rio Grande do Sul, Brazil
Summary
🤩
Rockstar🎓
Top SchoolLucas Alegre is a professor and AI researcher at UFRGS with nine years of experience specializing in reinforcement learning, multi-objective decision-making, and traffic signal control. He holds a PhD with distinction for work on sample-efficient multi-task and multi-objective RL and has translated research into open-source impact as creator of MO-Gymnasium and project manager at the Farama Foundation. His contributions include RL environments for SUMO traffic simulation and practical controllers integrated with Gymnasium, PettingZoo and popular RL libraries, reflecting a focus on reproducible, applied research. Lucas blends academic rigor with engineering practice—publishing in venues like AAMAS and IEEE T-ITS and interning at Disney Research and TU Berlin—while mentoring the next generation of ML practitioners in Brazil.
9 years of coding experience
6 years of employment as a software developer
Doctor of Philosophy - PhD, Computer Science, A - with distinction, Doctor of Philosophy - PhD, Computer Science, A - with distinction at Federal University of Rio Grande do SulHighschool, Highschool at Colégio Anchieta
Portuguese, English, Spanish
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (7)
openai-gym10
machine-learning10
sumo10
python10
reinforcement-learning10
gymnasium9
deep-reinforcement-learning9
Programming languages (7)
Github contributions (5)
LucasAlegre/sumo-rl
Dec 2018 - Nov 2022
Reinforcement Learning environments for Traffic Signal Control with SUMO. Compatible with Gymnasium, PettingZoo, and popular RL libraries.
Role in this project:
ML Engineer
ML EngineerContributions:8 releases, 5 reviews, 146 commits in 3 years 11 months
Contributions summary:Lucas appears to be involved in the development and implementation of reinforcement learning algorithms within the SUMO traffic simulation environment. Their contributions include creating a `SumoEnvironment` class, defining state and action spaces for traffic signal control, and integrating Q-learning agents. They also refactored the environment code, implemented reward function logic, and added the ability to generate and visualize traffic data, indicating a focus on building and evaluating RL-based traffic control systems.
signalpythongymnasiumdeep-reinforcement-learningsumo
maslab-ufrgs/system_optimum_solver
Oct 2017 - Sep 2018
Contributions:35 commits, 26 pushes, 1 branch in 11 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.