Lorenzo Bernasconi
Papers
1
Total Citations
13
H-Index
1
About
Lorenzo Bernasconi is a rising researcher in robotics and artificial intelligence, whose work focuses on advancing sample-efficient learning for autonomous systems. His primary research areas include Quality-Diversity (QD) algorithms, reinforcement learning, and robot skill acquisition. Bernasconi’s major contribution is the development of Dynamics-Aware Quality-Diversity (DA-QD), a novel framework that integrates dynamics models into QD optimization to dramatically reduce the number of physical robot evaluations needed for discovering diverse skill repertoires. His seminal 2022 paper on this topic, which has already garnered 13 citations, demonstrates how robots can learn complex behaviors more efficiently by predicting outcomes before execution. This work bridges the gap between exploration-driven QD methods and model-based learning, offering a practical path toward scalable robot learning in real-world environments. Bernasconi’s research is notable for its potential to accelerate autonomous skill acquisition in robotics, making it highly relevant for students and researchers interested in lifelong learning, evolutionary robotics, and efficient policy search.
Research Focus
Key Achievements
Top Papers
- 1Dynamics-Aware Quality-Diversity for Efficient Learning of Skill Repertoires13 citations · 2022