Mazyar Taghavi is a researcher in applied mathematics, artificial intelligence, and multi-agent reinforcement learning, affiliated with the Iran University of Science and Technology and Payame Noor University. With dual graduate degrees in applied mathematics and artificial intelligence, he has developed expertise at the intersection of optimization, quantum-inspired computation, intelligent robotics, and autonomous multi-agent systems. His professional experience includes certified research and teaching assistant roles, contributions to national research projects in optimization, optimal control, and AI for social good, and active participation in collaborative scientific initiatives. His research focuses on advanced mathematical modeling, deep and multi-agent reinforcement learning, quantum and neuromorphic computing, and optimal control, resulting in publications across Springer, IEEE, Elsevier, and other scholarly platforms, covering areas such as quantum-inspired MARL, UAV coordination, connected autonomous vehicles, swarm intelligence, and stochastic decision-making. He has delivered keynote speeches and contributed to academic dissemination through invited talks, supported by recognitions that include certified academic roles, society memberships, editorial and peer-review activities, and participation in advanced scientific training programs. His research impact includes 1 citation, 2 documents, and an h-index of 1.
Profiles: Scopus | ORCID | Google Scholar
Featured Publications
1. Taghavi M., Vahidi J., Quantum-inspired multi-agent reinforcement learning for exploration–exploitation optimization in UAV-assisted 6G network deployment. Quantum Mach. Intell., 7(2), 111.
2. Taghavi M., Farnoosh R., Quantum computing and neuromorphic computing for safe, reliable, and explainable multi-agent reinforcement learning: optimal control in autonomous intelligent agents. Iran J. Comput. Sci., 8(3), 1–17.
3. Taghavi M., Farnoosh R., Latent variable modeling in multi-agent reinforcement learning via expectation–maximization for UAV-based wildlife protection. J. Artif. Intell. Mach. Learn. (JAIM), 3(2).
4. Taghavi M., Vahidi J., Q-CMAPO: A quantum-classical framework for balancing exploration and exploitation in multi-agent reinforcement learning. Res. Square, rs-7111581/v1.
5. Taghavi M., Vahidi J., MARL-CC: A mathematical framework for multi-agent reinforcement learning in connected autonomous vehicles: addressing nonlinearity, partial observability, and credit assignment for optimal control.
Mazyar Taghavi’s work advances the scientific foundations of multi-agent reinforcement learning by integrating mathematical modeling, quantum-inspired optimization, and intelligent autonomous systems. His research supports safer, robotics, and smart infrastructures, contributing to technological innovation with real-world impact. He envisions developing intelligent, reliable, and explainable AI systems that drive next-generation autonomy across science, society, and industry.