Niloufar Mehrabi
Papers
1
Total Citations
4
H-Index
1
About
Niloufar Mehrabi is a rising researcher at the forefront of multi-agent artificial intelligence, with a particular focus on inverse reinforcement learning (IRL) and decentralized decision-making. Her most notable contribution is the development of **Turbo-IRL**, a groundbreaking framework introduced in her highly cited 2025 paper. This work draws inspiration from turbo decoding—a technique from communications theory—to enable multiple agents to iteratively refine their individual reward functions from a shared, common reward signal. By doing so, Turbo-IRL dramatically accelerates convergence in complex multi-agent systems, solving a long-standing challenge in the field. The paper has already garnered 4 citations, a strong indicator of its early impact and relevance. Mehrabi’s research bridges the gap between theoretical machine learning and practical multi-agent coordination, offering scalable solutions for robotics, autonomous systems, and game theory. Her innovative cross-disciplinary approach—merging information theory with AI—marks her as a promising young scientist to watch.
Research Focus
Key Achievements
Top Papers
- 1