Sotabase

Career

· Applied Scientist, Microsoft2021–
· Software Engineer, Microsoft2020–2021
· Software Development Engineer Intern, Amazon Web Services2018–2018
· Student Ambassador For Artificial Intelligence, Intel Corporation2018–2020
· Software Engineer, VTEX The True Cloud Commerce Platform2018–2018
· Research Collaborator, Grupo de Pesquisas em Engenharia de Software - ITA2017–2017
· Artificial Intelligence Researcher, Inteligência Artificial & Deep Learning Brasil2017–
· Co-Founder, Escola Pirata2016–2016
· Software Developer Product Designer (Intern), Pearson2016–2016
· Co Founder Sofware Developer, For Any Reality - ∀R2015–2015

Publications (21)

Transformers are Meta-Reinforcement Learners
International Conference on Machine Learning · 2022
64
cited
Housing Prices Prediction with a Deep Learning and Random Forest Ensemble
Anais do Encontro Nacional de Inteligência Artificial e Computacional (ENIAC 2019) · 2019
49
cited
Learning Humanoid Robot Running Skills through Proximal Policy Optimization
Latin American Robotics Symposium · 2019
26
cited
Learning Humanoid Robot Running Motions with Symmetry Incentive through Proximal Policy Optimization
Journal of Intelligent and Robotic Systems · 2021
24
cited
MARS-Gym: A Gym framework to model, train, and evaluate Recommender Systems for Marketplaces
2020 International Conference on Data Mining Workshops (ICDMW) · 2020
17
cited
Deep Bayesian Active Learning for Preference Modeling in Large Language Models
Neural Information Processing Systems · 2024
16
cited
Multiagent Reinforcement Learning for Strategic Decision Making and Control in Robotic Soccer Through Self-Play
IEEE Access · 2022
16
cited
Contextual Meta-Bandit for Recommender Systems Selection
ACM Conference on Recommender Systems · 2020
15
cited
Uncertainty-Aware Step-wise Verification with Generative Reward Models
arXiv.org · 2025
13
cited
Learning Humanoid Robot Motions Through Deep Neural Networks
arXiv.org · 2019
9
cited
Bottom-Up Meta-Policy Search
arXiv.org · 2019
6
cited
InfoQuest: Evaluating Multi-Turn Dialogue Agents for Open-Ended Conversations with Hidden Context
arXiv.org · 2025
5
cited
Sliding Puzzles Gym: A Scalable Benchmark for State Representation in Visual Reinforcement Learning
International Conference on Machine Learning · 2024
5
cited
PulseRL: Enabling Offline Reinforcement Learning for Digital Marketing Systems via Conservative Q-Learning
2021
3
cited
Iterative Deployment Improves Planning Skills in LLMs
arXiv.org · 2025
Learning Without Critics? Revisiting GRPO in Classical Reinforcement Learning Environments
arXiv.org · 2025
Partial Reasoning in Language Models: Search and Refinement Guided by Uncertainty
2026
Reinforcement Learning for Debt Pricing: A Case Study in Financial Services
Residual Reinforcement Learning to Generate a Closed-Loop Policy from a Keyframe Kick Motion
2025 Brazilian Symposium on Robotics (SBR) and 2025 Workshop on Robotics in Education (WRE) · 2025
Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM Reasoning
arXiv.org · 2025
Sotabase
Luckeciano Carvalho Melo | Researcher Profile | Sotabase | Sotabase