I build causal representations to predict and explain the outcomes of tasks decision under uncertainty, for instance, judging over subjective information (opinions, beliefs) or over stochastic or adversarial environments (action-state transitions and rewards). I study how causal representations can support sequential decision making (via multi-armed bandits and reinforcement learning) with the specific concerns such as (1) how to aggregate conflicting information, (2) how to decide if more information is necessary for making a decision, and (3) who should ideally acquire/provide that information. I am particularly interested in the cases software engineers and autonomous agents are both providers and consumers of information.

More recently, I have been investigating these concerns under the topic of transfer learning and combining symbolic and learning-based methods (neuro-symbolic) to determine how fragments of information can be taken as knowledge to be reused, updated, extended, or forgotten.

Topics

• Theory: Decision Theory, Voting, Utility theory.
• Probabilistic Models: Causal Inference, Reinforcement Learning, Multi-Armed Bandits, Bayesian Inference, Markov Models, and Bayesian Optimization.
• Empirical research: Quasi-experimental and Observational studies,Time series, and Sensitivity analysis.
• Application domains: Crowdsourcing, Software Debugging, Self-Adaptive Systems, Traffic-Signal Control, Multi-Agent Systems.
• Tools/Languages: R, Python, Java, Scala, Rust.

Projects

I am grateful to have the opportunity to work with many brilliant graduate and undergraduate students in individual and group research projects. Follow some of recent research projects that I have coordinated:

• Cross-Snapshot Attention for Identifying Graph Propagation Patterns in Dynamic Real-World Networks
• Robust Multi-Agent Reinforcement Learning for Self-Adaptive Systems
• Machine Learning-Based Control for Self-Adaptive Systems
• Digital Assistant for Design Thinking Artifact Repository

Courses that I have been teaching:

Summer 2026

• Research Methods in Software Engineering
• Automated Scientific Discovery Tools in Software Engineering Research
• Mechanistic Interpretability for Self-Improving Cyber-Physical Systems

Winter 2025/2026

• Reinforcement Learning with Guarantees via Automated Verification
• Robotic Sensing and Knowledge Transfer Learning in Safety-Critical Environments

Summer 2025

• Introduction to Software Engineering
• Automated Software Engineering: Trends and Challenges for using AI

Winter 2024/2025

• Advanced Topics in Software Engineering: Automation and AI 
• Software Engineering with Machine Learning: Tools and Methods 

Winter 2023

• Meta-Reinforcement Learning for Self-Adaptive Systems 
• Graph Neural Networks for Knowledge Graph Systems 
• Probabilistic Models: Modeling, Learning and Analysis 

Summer 2022

• Multi-Agent Reinforcement Learning on Self-Adaptive Systems 
• Machine Learning on Spatio-Temporal Graphs 

Winter 2022

• Graph Neural Networks 
• Adversarial Self-Supervised Learning with Digital Twins 
• AI Ethics Engineering

Summer 2021

• Quantum Programming with Applications to Machine Learning
• Machine Learning-Based Control of Dynamical Systems 
• Highly Scalable Systems 

Winter 2021

• Graph Neural Networks 
• Markov Models: Modeling, Learning, and Analysis 

Summer 2020

• Online Learning for Self-Healing and Self-Optimization 

Summer 2019

• Advanced Topics in Self-Adaptive Systems: Online Machine Learning 

Summer 2018

• Predictions based on Graphs and Machine Learning 

My Google Scholar - link