PhD researcher · University of Padova

Alberto Sinigaglia

Researcher in Deep Reinforcement Learning, Neural Networks, and Trustworthy AI. My work spans fair and robust learning, Bayesian methods, and learning-augmented optimization.

Email CV LinkedIn GitHub Stack Overflow Google Scholar

About

Based in Padova, Italy
PhD researcher in Deep Reinforcement Learning, University of Padova (Oct 2023 – ongoing)
Member of AMCO and the Reinforcement Learning Research Lab
MSc in Data Science and BSc in Computer Science — both 110/110 with honors
Research: Deep RL, Trustworthy AI, Fairness, Adversarial Learning, Bayesian ML, and Optimization
Teaching Reinforcement Learning at MSc level and additional Deep Learning classes for PhD students

Experience

Quantitative Research InternJun 2026 – Sep 2026

G-Research · London

Developed point-in-time deep learning models for mid-frequency market return forecasting

Applied Scientist InternNov 2025 – Apr 2026

Amazon · Luxembourg

Agentic integration of AWS pipelines using MCP
Metaheuristic search with pessimistic Graph Neural Network ensembles
Autoregressive Q-policies for spare-part scheduling

PhD ResearcherOct 2023 – ongoing

BMCS · University of Padova

Deep Reinforcement Learning, Multi-Agent RL, Fairness, Bayesian ML, and Adversarial Robustness

Professor AssistantOct 2023 – ongoing

University of Padova

Reinforcement Learning course for the MSc in Control Systems Engineering
Additional classes for the PhD Deep Learning course

Main Publications

ICML 2025

Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations

Davide Sartor*, Alberto Sinigaglia* et al.

NeurIPS 2025

Simple and Effective Specialized Representations for Fair Classifiers

Alberto Sinigaglia*, Davide Sartor* et al.

IEEE Transactions on Automation Science and Engineering · 2025

Edge Delayed Deep Deterministic Policy Gradient: Efficient Continuous Control for Edge Scenarios

Alberto Sinigaglia, Niccolò Turcato et al.

Amazon Internal Conference · Oral Presentation · 2026 also available on arXiv ↗

Learning-Augmented Optimization for Strategic Two-Echelon Spare Parts Network Design

Donato Maragno, Marco Caserta, Alberto Sinigaglia et al.

* Equal contribution.

Awards & Service

2019–20224× “1000 e 1 lode” scholarship recipient — awarded to the top 3% of students
2025Web Chair · IFAC Joint Conference on Computers, Cognition and Communication
2025Associate Editor · IFAC Joint Conference on Computers, Cognition and Communication