Orso Forghieri

I am a Reinforcement Learning PhD student at Ecole Polytechnique, Palaiseau, France, working under the supervision of Erwan Le Pennec, Hind Castel-Taleb, and Emmanuel Hyon.

I hold a Master’s degree from Ecole Normale Superieure Paris Saclay and an Engineering Diploma from Ecole Polytechnique.

Research

My research lies at the intersection of Reinforcement Learning, Dynamic Programming, and Markov Decision Processes, with a focus on scalable decision-making in high-dimensional environments.

I explore methods for state abstraction and hierarchical reinforcement learning, aiming to reduce complexity through divide-and-conquer strategies. These approaches are particularly relevant in applications such as large-scale planning, resource allocation, and network optimization.

Recent work includes abstraction-refinement algorithms and learning-based orchestration methods for dynamic systems, including use cases in edge computing networks.

Side Activities

• Reviewer for ROADEF 2025.
• Alpha tester for the Marmote MDP solver.
• Laboratory Life Council PhD Representative at CMAP, Ecole Polytechnique, 2024-2025.