Max Robotics — Global Service Robot Directory + US Certification

About

Manon Flageat is a computational intelligence researcher specializing in Quality-Diversity (QD) algorithms and evolutionary computation, with a particular focus on their application to robotics and reinforcement learning. Her work sits at the intersection of neuroevolution, MAP-Elites optimization, and real-world robustness — areas that are increasingly critical as autonomous systems face unpredictable, noisy environments. Among her most notable contributions is the development of MAP-Elites with Descriptor-Conditioned Gradients and Archive Distillation, a method that bridges divergent evolutionary search with gradient-based refinement to produce richer, more capable solution collections. Her 2022 benchmark suite for Quality-Diversity in Deep Neuroevolution has provided the research community with standardized tools for evaluating QD algorithms across robot control tasks, helping to accelerate systematic progress in the field. A recurring theme across her work — reflected in papers on behavioral reproducibility and performance-reproducibility trade-offs — is making QD algorithms reliable under uncertainty, a challenge essential for real-world deployment. With citations accumulating across venues spanning 2020 to 2025, Flageat represents an emerging voice in evolutionary robotics, steadily building a cohesive research program that advances both the theoretical foundations and practical applicability of Quality-Diversity optimization.