PhD Position: Geometric optimal control for generative models of physical systems – AI4I

Karlstad University; Torino; In loco; EUR 50.000 - 70.000; Tempo pieno

Descrizione del lavoro

A leading research institute in Italy seeks a PhD candidate for a position in Geometric Optimal Control for generative models of physical systems. The role involves research on reinforcement learning and applications in robotics. Candidates must hold a Master's degree in a relevant field and possess strong skills in machine learning and robotics. This fully funded position offers opportunities for international collaboration and high-impact research.

Servizi

Access to high-performance computing resources

Financial support for conferences

Dynamic research environment

Competenze

• Excellent Master’s degree in a relevant field.
• Strong background in machine learning and robotics.
• Fluent in spoken and written English.

Mansioni

• Explore geometric optimization methods for policy learning in RL.
• Analyze applications in the control of physical systems.
• Develop novel and interpretable RL algorithms.

Conoscenze

Machine learning

Robotics

Python programming

Scientific writing

Formazione

Master’s degree in computer science, physics, mathematics, electrical or mechatronics engineering

Descrizione del lavoro

PhD Position: Geometric optimal control for generative models of physical systems – AI4I

Deadline: December 17th 2025 at 12 (noon – CET)

Hosting Institution: AI4I – The Italian Institute of Artificial Intelligence

Department: PHI Lab

Funding Scheme: This doctorate grant is fully funded by The Italian institute of Artificial Intelligence (AI4I) in collaboration with Università degli Studi di Genova

Position Description

The Italian Institute of Artificial Intelligence (AI4I), in collaboration with Università degli Studi di Genova, invites applications for a PhD position in Geometric optimal control as part of the PhD Programme in Autonomous Systems.

The interpretation of reinforcement learning (RL) as an approximated optimal control problem suggests that the differential geometry can offer a unifying framework for analyzing and formulating policy learning paths as geodesics flows on specific Riemannian manifolds. This geometric perspective opens the following research objectives to be explored during the PhD: (1) RL as latent geodesic flows, where stochastic Riemannian metrics estimated from learned generative models define and/or bias the policy optimization path; (2) Leverage the Riemannian geometry of the Wasserstein space for more stable and efficient policy optimization; and (3) Exploit contact Hamiltonian dynamics and its link to optimal control geodesics into a geometric framework to analyze and design novel and interpretable RL algorithms. The thesis will explore applications of the developed methods in the control of physical systems such as robots or quadrotors, as well as the fine‑tuning of foundational models, among others.

Requirements

Must have skills:

• Excellent Master’s degree in computer science, physics, mathematics, electrical or mechatronics engineering, or a related field
• Strong background in machine learning and robotics
• Good programming skills in Python
• Fluent in spoken and written English
• A team player, but also able to work autonomously
• Experience with scientific writing

Good to have skills:

• Background on (applied) differential geometry
• Publication of peer‑reviewed research papers

References

• A. Testa et al. “Geometric Contact Flows: Contactomorphisms for Dynamics and Control”, ICML, 2025.
• Y. Chen et al. “Optimal Transport in Systems and Control”, Annual Review of Control, Robotics and Autonomous Systems, 2021.

Application Documents

• One‑page cover letter including a short (two‑paragraph) research proposal related to the PhD topic and aligned with your professional interests.
• Bachelor’s and Master’s diplomas with transcripts and grades.

Main Research Site

AI4I – The Italian Institute of Artificial Intelligence
Corso Castelfidardo 22, 10129 Torino, Italy

What We Offer

• Access to high‑performance computing resources and advanced research infrastructure.
• Opportunities for international collaboration and contributions to high‑impact publications.
• A dynamic and interdisciplinary research environment.
• Financial support for attending international conferences and Winter/Summer schools.

Start Date

1st March 2026

How to Apply

Applications for this position are managed by Università degli Studi di Genova. Please apply via the university’s official PhD admissions portal for the AI4I – The Italian Research Institute for Artificial Intelligence. The portal will guide you through the submission of all required documents and your research proposal.