Fabio Muratore

Papers

Total Citations

170

H-Index

About

Fabio Muratore is a prominent robotics researcher specializing in sim-to-real transfer, reinforcement learning, and domain randomization — the critical challenge of training robot control policies in simulation and successfully deploying them in the real world. His work addresses one of the field's most pressing problems: the prohibitive cost of generating real-world training data for modern deep learning systems. Muratore's most influential contribution, "Robot Learning From Randomized Simulations: A Review" (2022, 101 citations), provides a comprehensive survey of how randomized simulations enable scalable robot learning, positioning him as a key synthesizer of this rapidly evolving field. His earlier work, "Assessing Transferability From Simulation to Reality for Reinforcement Learning" (2019, 58 citations), established rigorous frameworks for evaluating when and how simulated policies can transfer to physical platforms. He further advanced the field with "Bayesian Domain Randomization for Sim-to-Real Transfer" (2020), introducing probabilistic methods to more intelligently bridge the simulation-reality gap. With nearly 170 citations across these core works, Muratore has made substantial contributions to making robot learning safer, faster, and more economically viable — research with profound implications for deploying autonomous systems in real-world environments.