Currently, my primary research interest is in Multi-Objective Reinforcement Learning (MORL), an extension of classical Reinforcement Learning in which an agent simultaneously optimizes multiple, often competing objectives. Rather than seeking a single optimal solution, MORL aims to identify a set of solutions representing diverse trade-offs between objectives, thereby enabling decision systems that accommodate various requirements. A key aspect of my research involves effectively integrating evolutionary algorithms with Reinforcement Learning methods to address complex multi-objective decision problems efficiently, thus facilitating optimal compromises among competing objectives.

I am also interested in Multi-Agent Reinforcement Learning (MARL), which explores how multiple autonomous agents interact and learn either collaboratively or competitively. A particularly interesting area is the combination of MARL with MORL, which enables the creation of systems in which multiple agents simultaneously pursue and optimize multiple objectives.