I am an Assistant Professor in the Department of Industrial and Management Systems Engineering at the University of South Florida, where I lead the Learning-enabled Autonomy (LEA) Lab.
Prior to joining USF, I was a Postdoctoral Research Associate in the Department of Computer Science at Purdue University. I received my Ph.D. in Systems Engineering from Boston University, my M.Sc. in Systems and Control from Delft University of Technology (TU Delft), and my B.Sc. in Automation Engineering through a joint program between Tongji University and the University of Bologna.
My research focuses on reinforcement learning and policy learning for sequential decision-making. I am broadly interested in developing learning methods that enable intelligent systems to make decisions efficiently, safely, and reliably, with a particular emphasis on incorporating physical structure, control-theoretic principles, and domain knowledge when available.
Learning-enabled Autonomy Lab
The LEA Lab develops learning-enabled methods for autonomous and sequential decision-making. Our research spans reinforcement learning, control theory, optimization, formal methods, and robotics, with the goal of developing intelligent systems that can learn efficiently, reason about complex objectives, and make safe and effective decisions in the real world.
Learn more about our research → Meet the lab →
Selected Publications
Physics-informed Reinforcement Learning
Goal Reaching with Eikonal-Constrained Hierarchical Quasimetric Reinforcement Learning
Vittorio Giammarino and Ahmed H. Qureshi. ICLR 2026.
PaperPhysics-informed Value Learner for Offline Goal-Conditioned Reinforcement Learning
Vittorio Giammarino, Ruiqi Ni, and Ahmed H. Qureshi. NeurIPS 2025.
Paper
Formal Methods for Policy Learning
- Automaton Constrained Q-Learning
Anastasios Manganaris, Vittorio Giammarino, and Ahmed H. Qureshi. NeurIPS 2025.
Paper
Visual Imitation
- Adversarial Imitation Learning from Visual Observations using Latent Information
Vittorio Giammarino, James Queeney, and Ioannis Ch. Paschalidis. Transactions on Machine Learning Research, 2024.
Paper
Learning and Control for Transportation
- Reinforcement Learning-based Receding Horizon Control using Adaptive Control Barrier Functions for Safety-Critical Systems
Ehsan Sabouni, H. M. Sabbir Ahmad, Vittorio Giammarino, Christos G. Cassandras, Ioannis Ch. Paschalidis, and Wenchao Li. CDC 2024.
Paper
More selected publications →
Complete publication list on Google Scholar →
News
August 2026 — I joined the University of South Florida as an Assistant Professor in the Department of Industrial and Management Systems Engineering and launched the Learning-enabled Autonomy (LEA) Lab.
June 2026 — Our paper “Provably Efficient Off-Policy Adversarial Imitation Learning with Convergence Guarantees” was published in TMLR.
May 2026 — My research was featured by Boston University Engineering: “Building Smarter, Safer AI: Vittorio Giammarino’s Research Journey”.
May 2026 — Our paper “Beyond Domain Randomization: Event-Inspired Perception for Visually Robust Adversarial Imitation from Videos” was presented at ICRA 2026.
April 2026 — Our workshop “Hybrid Architectures for Embodied Autonomy: Bridging Learning, Planning, and Control” was accepted to IROS 2026.
April 2026 — Our paper “Goal Reaching with Eikonal-Constrained Hierarchical Quasimetric Reinforcement Learning” was presented at ICLR 2026.
Join the LEA Lab
Prospective Ph.D. Students
I am recruiting 2–3 Ph.D. students to join the LEA Lab, with anticipated start dates between Spring and Fall 2027. I am looking for motivated and curious students interested in working at the intersection of Reinforcement Learning, Control Theory, Optimization, and Robotics. Students with relevant experience are especially encouraged to apply. Feel free to contact me for more information.
Current USF Students
Admitted USF PhD Students: If you have already been admitted and are looking for an advisor, please email me directly. I am able to directly advise students in the IMSE department and can co-advise students in other departments.
Masters/Undergraduate students: If you are interested in working with me, please send me an email with your CV and a brief description of your interests, and include [Prospective Masters/Undergraduate Student] in the subject respectively. I am particularly interested in working with students who are excited about high-risk, high-reward projects in AI for physical systems, and who are eager to learn and contribute to our research projects.
For any other inquiries, contact me at vittoriog@usf.edu.