Mina Razghandi
Papers
1
Total Citations
5
H-Index
1
About
Mina Razghandi is a rising researcher at the intersection of artificial intelligence, multi-agent systems, and security. Her primary focus lies in developing scalable, decentralized solutions for complex strategic interactions, particularly in security games. Her most-cited work, "Learning Distributed Cooperative Policies for Security Games via Deep Reinforcement Learning" (2019, 5 citations), tackles a critical limitation of traditional security game solvers: their reliance on centralized integer linear programming (ILP), which fails in multi-agent, real-world settings. Razghandi’s contribution is pioneering a deep reinforcement learning framework that enables agents to learn cooperative, distributed policies without a central coordinator, making security resource allocation more adaptive and efficient. This work bridges game theory and modern machine learning, offering a practical alternative to computationally heavy ILP methods. While her citation count is still growing, her research has already been recognized for its novelty in applying deep RL to multi-agent security domains, laying the groundwork for more resilient, autonomous defense systems. For students and researchers, Razghandi’s work exemplifies how cutting-edge AI can solve long-standing problems in security and game theory.
Research Focus
Key Achievements
Top Papers
- 1