Fabio Somenzi

Dr. Fabio Somenzi is a Professor in the Department of Electrical, Computer & Energy Engineering at the University of Colorado Boulder. His research focuses on formal verification, model checking, decision procedures, and reinforcement learning. He has contributed significantly to the integration of formal methods with reinforcement learning, particularly in handling omega-regular objectives, multi-agent systems, and safety-critical applications.

His recent work emphasizes combining reinforcement learning with formal specifications to ensure correctness and optimize decision-making under uncertainty. He has developed tools like Mungojerrie, which addresses model-free reinforcement learning for linear-time objectives. His research spans theoretical foundations, algorithm design, and practical implementations, with a strong emphasis on modular and compositional approaches.

Key themes in his publications include policy synthesis for temporal logic objectives, reward shaping for formal specifications, and compositional methods for large-scale systems. His work bridges computer science, control theory, and artificial intelligence, addressing challenges in automated reasoning and decision processes.

No scientific awards or grants are explicitly mentioned in the provided information. Dr. Somenzi collaborates on projects involving formal verification of analog circuits, stochastic systems, and abstract interpretation techniques.