Max Robotics — Global Service Robot Directory + US Certification

About

Rabeb Mizouni’s research sits at the intersection of multi-agent systems, deep reinforcement learning, and next-generation networked applications. She is best known for pioneering the use of Multi-Agent Deep Reinforcement Learning (MADRL) with Proximal Policy Optimization for target localization, where swarms of mobile sensing agents—such as UAVs and robots—collaboratively search for and pinpoint targets. Her 2022 paper on this topic has garnered 68 citations, establishing a foundational approach that combines learning efficiency with real-world deployability. Building on this, her 2023 work introduced demonstration cloning to accelerate agent training, achieving 34 citations and further advancing autonomous search-and-rescue and surveillance systems. In parallel, Mizouni has made significant contributions to Tactile Internet applications, particularly remote robotic surgery. Her research on joint placement and scheduling of Virtual Network Function Forwarding Graphs (VNF-FGs) addresses the ultra-low-latency and multimodal data challenges critical for telesurgery. By developing deterministic and dynamic resource allocation policies, she has enabled cost-effective, high-reliability surgical networks. Her work is characterized by a rare ability to bridge theoretical reinforcement learning with pressing engineering problems, making her a leading voice in autonomous multi-agent coordination and latency-critical networked systems.