Mehrdad Moharrami
Scholar

Mehrdad Moharrami

Google Scholar ID: 6irb5qMAAAAJ
Assistant Professor, University of Iowa
Markov decision processesReinforcement LearningRandom GraphsNetwork Science
Citations & Impact
All-time
Citations
144
 
H-index
5
 
i10-index
3
 
Publications
20
 
Co-authors
7
list available
Resume (English only)
Academic Achievements
  • Paper titled 'The Planted Spanning Tree Problems: Exact Overlap Characterization via Local Weak Convergence' accepted at COLT 2025
  • Paper titled 'Online Learning in Risk Sensitive constrained MDP' accepted at ICML 2025
  • Paper titled 'A Stackelberg Game Model of Flocking' accepted at IEEE Conference on Decision and Control (July 2024)
  • Paper titled 'Structural Stability of a Family of Group Formation Games' accepted in IEEE Transactions on Network Science (February 2024)
  • Paper titled 'A Policy Gradient Algorithm for the Risk-Sensitive Exponential Cost MDP' accepted in Mathematics of Operations Research (January 2024)
  • Paper titled 'Rarest-First with Probabilistic-Mode-Suppression' accepted in IEEE Transactions on Information Theory (December 2023)
  • Paper titled 'Performance Bounds for Policy-Based Average Reward Reinforcement Learning Algorithms' accepted and presented at INFORMS Annual Meeting (October 2023)
  • Co-organized RLMA S workshop in conjunction with Performance 2023 (November 2023)
  • Co-organizing SC&RL workshop in conjunction with ACM SIGMETRICS 2025 (May 2025)
  • Invited speaker at multiple institutions and conferences including ITA 2025, Tippie College of Business (University of Iowa), IIT Guwahati, and IIT Kharagpur