Lorenzo Mazzotti
Papers
1
Total Citations
1
H-Index
1
About
Lorenzo Mazzotti is a researcher at the intersection of reinforcement learning, haptic feedback, and intelligent control systems. His work focuses on developing model-free approaches that enable machines to learn complex physical tasks through direct interaction with their environment. Mazzotti’s most cited paper, “Solving the Wire Loop Game with a reinforcement-learning controller based on haptic feedback” (2024), demonstrates a novel method for training agents to perform delicate, contact-rich operations without explicit programming. By integrating tactile sensing with deep reinforcement learning, his controller autonomously masters the classic wire loop game—a task requiring precise force modulation and obstacle avoidance. This contribution highlights the potential of haptic-driven AI to replace traditional model-based control in scenarios where system dynamics are too complex to predefine. Though early in his career, Mazzotti’s work is gaining traction among researchers interested in embodied intelligence, human-robot collaboration, and adaptive control. His approach promises to simplify the design of robotic systems for surgery, assembly, and rehabilitation, where touch-based learning can dramatically reduce engineering effort while improving robustness.
Research Focus
Key Achievements
Top Papers
- 1